diff --git a/ci_cd/generate_model_prices_schema.py b/ci_cd/generate_model_prices_schema.py
index 4ca09155d1b..96634fb74fe 100644
--- a/ci_cd/generate_model_prices_schema.py
+++ b/ci_cd/generate_model_prices_schema.py
@@ -122,8 +122,9 @@ OBJECT_KEYS: dict[str, JsonSchema] = {
         "properties": {
             "model": NON_BLANK_STRING,
             "region": NON_BLANK_STRING,
+            "litellm_provider": {"type": "string", "enum": ["bedrock", "bedrock_mantle"]},
         },
-        "description": "Model that counts tokens for this one, and the AWS region its count API runs in.",
+        "description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in.",
     },
 }
 
diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
index 7ae03992007..3010879627c 100644
--- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
+++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
@@ -2,7 +2,9 @@
 Polls LiteLLM_ManagedObjectTable to check if the batch job is complete, and if the cost has been tracked.
 """
 
-from collections.abc import Sequence
+import json
+import re
+from collections.abc import Mapping, Sequence
 from dataclasses import replace as dataclasses_replace
 from datetime import datetime, timedelta, timezone
 from types import MappingProxyType
@@ -27,7 +29,12 @@ if TYPE_CHECKING:
     from litellm.types.utils import LiteLLMBatch
 
 
+def _error_names_resource(error: Exception, resource_id: str) -> bool:
+    return resource_id in re.findall(r"""[^\s"'`]+""", str(error))
+
+
 CHECK_BATCH_COST_USER_AGENT = "LiteLLM Proxy/CheckBatchCost"
+RECENT_BATCH_POLL_WINDOW: Final = timedelta(hours=48)
 
 PROVIDER_TERMINAL_BATCH_STATUSES: Final[Tuple[str, ...]] = (
     "completed",
@@ -44,6 +51,12 @@ TERMINAL_MANAGED_OBJECT_STATUSES: Final[Tuple[str, ...]] = (
 
 
 class _ManagedObjectRow(Protocol):
+    @property
+    def created_at(self) -> datetime: ...
+
+    @property
+    def updated_at(self) -> datetime: ...
+
     @property
     def id(self) -> str: ...
 
@@ -98,6 +111,11 @@ class CheckBatchCost:
         # the guaranteed-failing primary query on every subsequent cycle.
         self._has_batch_processed_column: bool = True
         self.batch_processed_support_confirmed: bool = False
+        self._poll_cursor: tuple[datetime, str] | None = None
+        self._poll_before: datetime = datetime.now(timezone.utc)
+        self._arrival_cursor: tuple[datetime, str] | None = None
+        self._arrival_before: datetime = self._poll_before
+        self._poll_arrivals: bool = False
 
     @staticmethod
     def _is_missing_batch_processed_column_error(err: Exception) -> bool:
@@ -269,29 +287,9 @@ class CheckBatchCost:
                 f"(older than {MANAGED_OBJECT_STALENESS_CUTOFF_DAYS} days) as stale_expired"
             )
 
-        if not self._has_batch_processed_column:
-            return
-
-        # A row already in a terminal status is never rewritten by the sweep above, so
-        # without this it keeps a poll-page slot forever and starves newer batches.
-        retired: Final = await _managed_object_table(self.prisma_client).update_many(
-            where={
-                "file_purpose": "batch",
-                "batch_processed": False,
-                "status": {"in": ["complete", "completed"]},
-                "created_at": {"lt": cutoff},
-            },
-            data={"batch_processed": True},
-        )
-        if retired > 0:
-            verbose_proxy_logger.warning(
-                f"CheckBatchCost: gave up on {retired} completed managed objects older than "
-                f"{MANAGED_OBJECT_STALENESS_CUTOFF_DAYS} days that were never costed"
-            )
-
     async def _fallback_find_jobs(self) -> "Sequence[_ManagedObjectRow]":
         """Query batch jobs without the batch_processed filter (for older schemas)."""
-        return await _managed_object_table(self.prisma_client).find_many(
+        return await self._find_jobs(
             where={
                 "file_purpose": "batch",
                 "status": {
@@ -305,10 +303,59 @@ class CheckBatchCost:
                     ]
                 },
             },
-            take=MAX_OBJECTS_PER_POLL_CYCLE,
-            order={"created_at": "asc"},
         )
 
+    async def _find_jobs(self, where: Mapping[str, object]) -> Sequence[_ManagedObjectRow]:
+        arrivals: Final = self._poll_arrivals
+        page: Final = await self._find_job_page(where, arrivals=arrivals)
+        self._poll_arrivals = not arrivals if page else arrivals
+        if page:
+            return page
+        return await self._find_job_page(where, arrivals=not arrivals)
+
+    async def _find_job_page(self, where: Mapping[str, object], *, arrivals: bool) -> Sequence[_ManagedObjectRow]:
+        cursor: Final = self._arrival_cursor if arrivals else self._poll_cursor
+        if cursor is None:
+            if arrivals:
+                self._arrival_before = datetime.now(timezone.utc)
+            else:
+                self._poll_before = datetime.now(timezone.utc) - RECENT_BATCH_POLL_WINDOW
+        before: Final = self._arrival_before if arrivals else self._poll_before
+        page: Final = await _managed_object_table(self.prisma_client).find_many(
+            where={
+                **where,
+                "created_at": {
+                    "lte": before,
+                    **({"gt": before - RECENT_BATCH_POLL_WINDOW} if arrivals else {}),
+                },
+                **(
+                    {
+                        "OR": [
+                            {"created_at": {"gt": cursor[0]}},
+                            {"created_at": cursor[0], "id": {"gt": cursor[1]}},
+                        ]
+                    }
+                    if cursor is not None
+                    else {}
+                ),
+            },
+            take=MAX_OBJECTS_PER_POLL_CYCLE,
+            order=[{"created_at": "asc"}, {"id": "asc"}],
+        )
+        next_cursor: Final = (page[-1].created_at, page[-1].id) if len(page) == MAX_OBJECTS_PER_POLL_CYCLE else None
+        if arrivals:
+            self._arrival_cursor = next_cursor
+        else:
+            self._poll_cursor = next_cursor
+        return page
+
+    def _unprocessed_snapshot(self, job: _ManagedObjectRow) -> Mapping[str, object]:
+        return {
+            "id": job.id,
+            "updated_at": job.updated_at,
+            **({"batch_processed": False} if self._has_batch_processed_column else {}),
+        }
+
     async def _retire_job(self, job: "_ManagedObjectRow", reason: str) -> None:
         """
         Take a row that can never be costed out of the poll page. Leaving it selectable
@@ -316,27 +363,23 @@ class CheckBatchCost:
         once enough such rows accumulate no newer batch is ever reached. Older schemas
         without batch_processed can only be excluded through the status filter.
         """
-        data: Final = (
-            {"batch_processed": True}
-            if self._has_batch_processed_column
-            else {"status": "stale_expired"}
-        )
+        data: Final = {"batch_processed": True} if self._has_batch_processed_column else {"status": "stale_expired"}
         try:
-            await _managed_object_table(self.prisma_client).update(
-                where={"id": job.id},
+            retired: Final = await _managed_object_table(self.prisma_client).update_many(
+                where=self._unprocessed_snapshot(job),
                 data=data,
             )
         except Exception as db_err:
-            verbose_proxy_logger.error(
-                f"CheckBatchCost: failed to retire uncostable job {job.id} ({reason}): {db_err}"
-            )
+            verbose_proxy_logger.error(f"CheckBatchCost: failed to retire uncostable job {job.id} ({reason}): {db_err}")
+            return
+        if retired == 0:
             return
         verbose_proxy_logger.warning(
             f"CheckBatchCost: job {job.id} can never be costed ({reason}), "
             "so it will no longer be polled"
         )
 
-    async def _claim_job_for_costing(self, job: "_ManagedObjectRow") -> bool:
+    async def _claim_job_for_costing(self, job: "_ManagedObjectRow", response: "LiteLLMBatch") -> bool:
         """
         Atomically flip batch_processed from false to true, returning whether this pod won
         the row. Every pod and uvicorn worker schedules its own poller against the shared
@@ -350,10 +393,16 @@ class CheckBatchCost:
         """
         if not self._has_batch_processed_column:
             return True
+        from litellm_enterprise.proxy.hooks.managed_files import postgres_storable_json
+
         try:
             claimed: Final = await _managed_object_table(self.prisma_client).update_many(
                 where={"id": job.id, "batch_processed": False},
-                data={"batch_processed": True},
+                data={
+                    "batch_processed": True,
+                    "status": response.status if response.status != "completed" else "complete",
+                    "file_object": postgres_storable_json(response),
+                },
             )
         except Exception as db_err:
             verbose_proxy_logger.error(
@@ -362,7 +411,9 @@ class CheckBatchCost:
             return False
         return claimed > 0
 
-    async def _release_job_claim(self, job: "_ManagedObjectRow") -> None:
+    async def _release_job_claim(
+        self, job: "_ManagedObjectRow", original_status: str | None, original_file_object: object
+    ) -> None:
         """Give a claimed row back once billing it failed, so a later poll cycle retries it.
 
         Safe to match on batch_processed=True: while this poller is active the retrieve
@@ -374,7 +425,11 @@ class CheckBatchCost:
         try:
             await _managed_object_table(self.prisma_client).update_many(
                 where={"id": job.id, "batch_processed": True},
-                data={"batch_processed": False},
+                data={
+                    "batch_processed": False,
+                    "status": original_status,
+                    "file_object": json.dumps(original_file_object),
+                },
             )
         except Exception as db_err:
             verbose_proxy_logger.error(
@@ -408,13 +463,13 @@ class CheckBatchCost:
 
         from litellm.exceptions import NotFoundError
 
-        return isinstance(error, (NotFoundError, openai.NotFoundError)) and batch_id in str(error)
+        return isinstance(error, (NotFoundError, openai.NotFoundError)) and _error_names_resource(error, batch_id)
 
     def _batch_deployment_exists(self, model_id: str) -> bool:
         """A 404 only proves the batch is gone when it came from the batch's own
         deployment. Once that deployment leaves the router, default fallbacks can
         silently send the retrieve to a provider that never saw the batch, so its
-        404 must not retire the row; the staleness sweep bounds it instead."""
+        404 must not retire a potentially recoverable row."""
         return self.llm_router.get_deployment(model_id=model_id) is not None
 
     @staticmethod
@@ -429,7 +484,7 @@ class CheckBatchCost:
 
         if not output_file_id:
             return False
-        return isinstance(error, (NotFoundError, openai.NotFoundError)) and output_file_id in str(error)
+        return isinstance(error, (NotFoundError, openai.NotFoundError)) and _error_names_resource(error, output_file_id)
 
     async def _finalize_unbilled_terminal_job(
         self, job: "_ManagedObjectRow", response: "LiteLLMBatch"
@@ -451,15 +506,17 @@ class CheckBatchCost:
                 db_batch_object=job,
                 unified_batch_id=_is_base64_encoded_unified_file_id(job.unified_object_id),
             )
-            update_data: Final[dict] = {
+            update_data: Final[dict[str, object]] = {
                 "status": response.status,
                 "file_object": response.model_dump_json(),
                 **({"batch_processed": True} if self._has_batch_processed_column else {}),
             }
-            await _managed_object_table(self.prisma_client).update(
-                where={"id": job.id},
+            finalized: Final = await _managed_object_table(self.prisma_client).update_many(
+                where=self._unprocessed_snapshot(job),
                 data=update_data,
             )
+            if finalized == 0:
+                return
             verbose_proxy_logger.info(
                 f"CheckBatchCost: marked job {job.id} as {response.status} in DB"
             )
@@ -671,8 +728,6 @@ class CheckBatchCost:
 
     @staticmethod
     def _get_input_file_id(job: "_ManagedObjectRow") -> Optional[str]:
-        import json
-
         from litellm.types.utils import LiteLLMBatch
 
         file_object = job.file_object
@@ -876,8 +931,9 @@ class CheckBatchCost:
                 failed_requests=output_file_result.failed_requests + error_file_failed_requests,
             )
         )
+        logging_model: Final = batch_result.models[0] if batch_result.models else litellm_model_name or model_id
         logging_obj = LiteLLMLogging(
-            model=batch_result.models[0],
+            model=logging_model,
             messages=[{"role": "user", "content": "<retrieve_batch>"}],
             stream=False,
             call_type="aretrieve_batch",
@@ -908,27 +964,35 @@ class CheckBatchCost:
             custom_llm_provider=str(llm_provider) if llm_provider else None,
         )
 
-        if not await self._claim_job_for_costing(job):
+        original_status: Final = job.status
+        original_file_object: Final = job.file_object
+        if not await self._claim_job_for_costing(job, response.model_copy(update={"usage": batch_result.usage})):
             verbose_proxy_logger.info(
                 f"CheckBatchCost: batch {batch_id} (job {job.id}) was claimed by another pod "
                 "in this window, so its cost is already being tracked there"
             )
             return None
 
-        try:
-            await logging_obj.async_success_handler(
-                result=response,
-                batch_cost=batch_result.cost,
-                batch_usage=batch_result.usage,
-                batch_models=batch_result.models,
-                batch_successful_requests=batch_result.successful_requests,
-                batch_failed_requests=batch_result.failed_requests,
-                batch_prompt_cost=batch_result.prompt_cost,
-                batch_completion_cost=batch_result.completion_cost,
-            )
-        except Exception:
-            await self._release_job_claim(job)
-            raise
+        from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting
+
+        with track_batch_accounting(logging_obj.litellm_call_id) as accounting:
+            try:
+                await logging_obj.async_success_handler(
+                    result=response,
+                    batch_cost=batch_result.cost,
+                    batch_usage=batch_result.usage,
+                    batch_models=batch_result.models,
+                    batch_successful_requests=batch_result.successful_requests,
+                    batch_failed_requests=batch_result.failed_requests,
+                    batch_prompt_cost=batch_result.prompt_cost,
+                    batch_completion_cost=batch_result.completion_cost,
+                )
+            finally:
+                if accounting.retryable_failure:
+                    await self._release_job_claim(job, original_status, original_file_object)
+
+        if accounting.retryable_failure:
+            return None
 
         # Record batch duration (completed_at - created_at)
         if prom_logger and response.completed_at and response.created_at:
@@ -976,7 +1040,7 @@ class CheckBatchCost:
                 # endpoint may transition a batch to "complete" before
                 # CheckBatchCost runs.  The batch_processed=False filter
                 # already prevents reprocessing finished batches.
-                jobs = await _managed_object_table(self.prisma_client).find_many(
+                jobs = await self._find_jobs(
                     where={
                         "file_purpose": "batch",
                         "batch_processed": False,
@@ -989,8 +1053,6 @@ class CheckBatchCost:
                             ]
                         },
                     },
-                    take=MAX_OBJECTS_PER_POLL_CYCLE,
-                    order={"created_at": "asc"},
                 )
                 self.batch_processed_support_confirmed = True
             except Exception as query_err:
@@ -1060,7 +1122,7 @@ class CheckBatchCost:
                         continue
                     verbose_proxy_logger.error(
                         f"CheckBatchCost: failed to track cost for batch {batch_id} "
-                        f"(job {job.id}); leaving it unprocessed so the next poll retries: {tracking_err}"
+                        f"(job {job.id}): {tracking_err}"
                     )
                     self._record_error(prom_logger, "cost_tracking_error")
                     continue
@@ -1070,22 +1132,19 @@ class CheckBatchCost:
                 # Track this job for the final metrics summary
                 processed_models.append(tracked)
 
-                # mark the job as complete
-                try:
-                    update_data: dict = {
-                        "status": response.status if response.status != "completed" else "complete",
-                        "file_object": response.model_dump_json(),
-                    }
-                    if self._has_batch_processed_column:
-                        update_data["batch_processed"] = True
-                    await _managed_object_table(self.prisma_client).update(
-                        where={"id": job.id},
-                        data=update_data,
-                    )
-                except Exception as db_err:
-                    verbose_proxy_logger.error(
-                        f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}"
-                    )
+                if not self._has_batch_processed_column:
+                    try:
+                        await _managed_object_table(self.prisma_client).update(
+                            where={"id": job.id},
+                            data={
+                                "status": response.status if response.status != "completed" else "complete",
+                                "file_object": response.model_dump_json(),
+                            },
+                        )
+                    except Exception as db_err:
+                        verbose_proxy_logger.error(
+                            f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}"
+                        )
 
             elif response.status in PROVIDER_TERMINAL_BATCH_STATUSES:
                 from litellm.proxy.openai_files_endpoints.common_utils import (
diff --git a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
index 21bf7abdc2e..ce1988a0af0 100644
--- a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
+++ b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
@@ -22,7 +22,7 @@ from uuid import NAMESPACE_URL, uuid5
 
 import httpx
 from fastapi import HTTPException
-from pydantic import ValidationError
+from pydantic import BaseModel, JsonValue, TypeAdapter, ValidationError
 
 import litellm
 from litellm import Router, verbose_logger
@@ -205,6 +205,31 @@ def _managed_object_table(prisma_client: PrismaClient) -> _ManagedObjectTableAct
     return prisma_client.db.litellm_managedobjecttable
 
 
+_JSON_VALUE_ADAPTER: Final[TypeAdapter[JsonValue]] = TypeAdapter(JsonValue)
+_POSTGRES_UNSTORABLE_CHARACTER: Final = "\x00"
+
+
+def _storable_text(text: str) -> str:
+    return text.replace(_POSTGRES_UNSTORABLE_CHARACTER, "")
+
+
+def _storable_json_value(value: JsonValue) -> JsonValue:
+    if isinstance(value, str):
+        return _storable_text(value)
+    if isinstance(value, list):
+        return [_storable_json_value(item) for item in value]
+    if isinstance(value, dict):
+        return {_storable_text(key): _storable_json_value(item) for key, item in value.items()}
+    return value
+
+
+def postgres_storable_json(file_object: BaseModel) -> str:
+    dumped: Final = file_object.model_dump_json()
+    if "\\u0000" not in dumped:
+        return dumped
+    return _JSON_VALUE_ADAPTER.dump_json(_storable_json_value(_JSON_VALUE_ADAPTER.validate_json(dumped))).decode()
+
+
 def _storage_metadata_of(file_object: OpenAIFileObject | None) -> Mapping[str, str]:
     hidden_params: Final = cast(  # cast-ok: _hidden_params is an untyped attribute the upload path sets
         "Mapping[str, object]", getattr(file_object, "_hidden_params", None) or {}
diff --git a/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs b/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs
index 07c2eb46eaa..ceb03e158bc 100644
--- a/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs
+++ b/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs
@@ -140,11 +140,14 @@ impl BaseAnthropicMessagesConfig for AnthropicMessagesConfig {
     }
 
     fn request_headers(&self, headers: Headers, request: &AnthropicMessagesRequest) -> Headers {
-        update_headers_with_anthropic_beta(headers, request)
+        merge_beta_headers(
+            update_headers_with_anthropic_beta(headers, request),
+            safeguards_betas(&request.params),
+        )
     }
 }
 
-fn update_headers_with_anthropic_beta(
+pub(crate) fn update_headers_with_anthropic_beta(
     headers: Headers,
     request: &AnthropicMessagesRequest,
 ) -> Headers {
@@ -199,6 +202,20 @@ fn uses_structured_output(params: &AnthropicMessagesOptionalParams) -> bool {
             .is_some_and(|config| config.format.is_some())
 }
 
+fn safeguards_betas(params: &AnthropicMessagesOptionalParams) -> BetaSet {
+    carries_safeguards(params)
+        .then_some(AnthropicBeta::DangerousToolUse20260903)
+        .into_iter()
+        .collect()
+}
+
+fn carries_safeguards(params: &AnthropicMessagesOptionalParams) -> bool {
+    params
+        .extra
+        .get("safeguards")
+        .is_some_and(|value| !value.is_null())
+}
+
 fn messages_carry_output_config(messages: &[AnthropicMessage]) -> bool {
     messages
         .iter()
@@ -1047,6 +1064,12 @@ mod tests {
         json!({"messages": [{"role": "user", "content": "hi", "output_config": {"effort": "low"}}]}),
         &[("anthropic-beta", "claude-code-20250219,context-management-2025-06-27,effort-2025-11-24,interleaved-thinking-2025-05-14,per-turn-control-2026-07-01")],
     )]
+    #[case::safeguards_add_the_dangerous_tool_use_beta(
+        &[("anthropic-beta", "claude-code-20250219")],
+        json!({"safeguards": [{"type": "dangerous_tool_use"}]}),
+        &[("anthropic-beta", "claude-code-20250219,dangerous-tool-use-2026-09-03")],
+    )]
+    #[case::null_safeguards_add_no_beta(&[("x-api-key", "k")], json!({"safeguards": null}), &[("x-api-key", "k")])]
     fn request_headers_merge_the_feature_betas(
         #[case] input: &[(&str, &str)],
         #[case] fields: Value,
diff --git a/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs b/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs
index 0c1434afb5d..4080af35fdf 100644
--- a/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs
+++ b/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs
@@ -12,7 +12,9 @@ use crate::{
     Error,
     anthropic::{
         common_utils::{API_KEY_PLACEMENT, MESSAGES_PATH_SUFFIX, non_empty},
-        messages::transformation::{ANTHROPIC_MESSAGES_CONFIG, AnthropicMessagesConfig},
+        messages::transformation::{
+            ANTHROPIC_MESSAGES_CONFIG, AnthropicMessagesConfig, update_headers_with_anthropic_beta,
+        },
     },
     base_llm::{
         anthropic_messages::transformation::{
@@ -103,7 +105,7 @@ impl BaseAnthropicMessagesConfig for AzureAnthropicMessagesConfig {
     }
 
     fn request_headers(&self, headers: Headers, request: &AnthropicMessagesRequest) -> Headers {
-        self.anthropic.request_headers(headers, request)
+        update_headers_with_anthropic_beta(headers, request)
     }
 }
 
diff --git a/litellm-rust/crates/model-catalog/src/model_info.rs b/litellm-rust/crates/model-catalog/src/model_info.rs
index 7b8ce15fbd6..de8390046ab 100644
--- a/litellm-rust/crates/model-catalog/src/model_info.rs
+++ b/litellm-rust/crates/model-catalog/src/model_info.rs
@@ -29,10 +29,16 @@ pub struct ModelInfo {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_creation_input_token_cost_above_32k_tokens: Option<f64>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub cache_creation_input_token_cost_above_100k_tokens: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub cache_creation_input_token_cost_above_100k_tokens_batches: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_creation_input_token_cost_above_128k_tokens: Option<f64>,
     /// Rate applied once the prompt exceeds the token threshold in the field name.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_creation_input_token_cost_above_1hr: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub cache_creation_input_token_cost_above_1hr_above_100k_tokens: Option<f64>,
     /// Rate applied once the prompt exceeds the token threshold in the field name.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_creation_input_token_cost_above_1hr_above_200k_tokens: Option<f64>,
@@ -76,6 +82,10 @@ pub struct ModelInfo {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_read_input_token_cost_above_32k_tokens: Option<f64>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub cache_read_input_token_cost_above_100k_tokens: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub cache_read_input_token_cost_above_100k_tokens_batches: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub cache_read_input_token_cost_above_128k_tokens: Option<f64>,
     /// Rate applied once the prompt exceeds the token threshold in the field name.
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -183,6 +193,10 @@ pub struct ModelInfo {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub input_cost_per_token_above_32k_tokens: Option<f64>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub input_cost_per_token_above_100k_tokens: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub input_cost_per_token_above_100k_tokens_batches: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub input_cost_per_token_above_128k_tokens: Option<f64>,
     /// Rate applied once the prompt exceeds the token threshold in the field name.
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -329,6 +343,10 @@ pub struct ModelInfo {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub output_cost_per_token_above_32k_tokens: Option<f64>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub output_cost_per_token_above_100k_tokens: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub output_cost_per_token_above_100k_tokens_batches: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub output_cost_per_token_above_128k_tokens: Option<f64>,
     /// Rate applied once the prompt exceeds the token threshold in the field name.
     #[serde(skip_serializing_if = "Option::is_none")]
diff --git a/litellm-rust/crates/model-catalog/tests/registry_validation.rs b/litellm-rust/crates/model-catalog/tests/registry_validation.rs
index 8f555e1f884..67589010aba 100644
--- a/litellm-rust/crates/model-catalog/tests/registry_validation.rs
+++ b/litellm-rust/crates/model-catalog/tests/registry_validation.rs
@@ -74,3 +74,20 @@ fn checked_in_catalog_and_backup_match() {
         "invalid registry aliases"
     );
 }
+
+#[rstest]
+#[case::input("input_cost_per_token_above_100k_tokens")]
+#[case::input_batches("input_cost_per_token_above_100k_tokens_batches")]
+#[case::output("output_cost_per_token_above_100k_tokens")]
+#[case::output_batches("output_cost_per_token_above_100k_tokens_batches")]
+#[case::cache_creation("cache_creation_input_token_cost_above_100k_tokens")]
+#[case::cache_creation_batches("cache_creation_input_token_cost_above_100k_tokens_batches")]
+#[case::cache_creation_1hr("cache_creation_input_token_cost_above_1hr_above_100k_tokens")]
+#[case::cache_read("cache_read_input_token_cost_above_100k_tokens")]
+#[case::cache_read_batches("cache_read_input_token_cost_above_100k_tokens_batches")]
+fn registry_validation_keeps_above_100k_tier_rates(#[case] field: &str) {
+    let mut entry = Map::new();
+    entry.insert("litellm_provider".into(), "anthropic".into());
+    entry.insert(field.into(), 5e-7.into());
+    validate_model_entry("test", &Value::Object(entry)).unwrap();
+}
diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json
index 3a28d65e47c..dbc6060396a 100644
--- a/litellm/anthropic_beta_headers_config.json
+++ b/litellm/anthropic_beta_headers_config.json
@@ -46,7 +46,7 @@
     "computer-use-2025-11-24": "computer-use-2025-11-24",
     "context-1m-2025-08-07": "context-1m-2025-08-07",
     "context-management-2025-06-27": "context-management-2025-06-27",
-    "dangerous-tool-use-2026-09-03": null,
+    "dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03",
     "effort-2025-11-24": "effort-2025-11-24",
     "fast-mode-2026-02-01": null,
     "files-api-2025-04-14": "files-api-2025-04-14",
@@ -217,7 +217,7 @@
     "computer-use-2025-11-24": "computer-use-2025-11-24",
     "context-1m-2025-08-07": "context-1m-2025-08-07",
     "context-management-2025-06-27": "context-management-2025-06-27",
-    "dangerous-tool-use-2026-09-03": null,
+    "dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03",
     "effort-2025-11-24": "effort-2025-11-24",
     "fast-mode-2026-02-01": "fast-mode-2026-02-01",
     "files-api-2025-04-14": "files-api-2025-04-14",
diff --git a/litellm/anthropic_beta_headers_manager.py b/litellm/anthropic_beta_headers_manager.py
index 7e7099a53b0..35df2a09004 100644
--- a/litellm/anthropic_beta_headers_manager.py
+++ b/litellm/anthropic_beta_headers_manager.py
@@ -22,17 +22,28 @@ Environment Variables:
 - LITELLM_ANTHROPIC_BETA_HEADERS_URL: Custom URL for remote config (optional)
 """
 
+import asyncio
 import json
 import os
+import threading
+from collections.abc import Mapping
+from concurrent.futures import ThreadPoolExecutor
+from functools import cache
 from importlib.resources import files
-from typing import Final
+from typing import Final, TypeAlias
 
 import httpx
+from pydantic import TypeAdapter
 
 from litellm.litellm_core_utils.litellm_logging import verbose_logger
 
 # Cache for the loaded configuration
 _BETA_HEADERS_CONFIG: dict | None = None
+_BETA_HEADERS_CONFIG_LOCK: Final = threading.Lock()
+_BETA_HEADERS_CONFIG_LOADER: Final = ThreadPoolExecutor(max_workers=1, thread_name_prefix="litellm-beta-headers-config")
+
+BetaHeadersConfig: TypeAlias = Mapping[str, str | Mapping[str, str | None]]
+_BETA_HEADERS_CONFIG_ADAPTER: Final = TypeAdapter(BetaHeadersConfig)
 
 
 class GetAnthropicBetaHeadersConfig:
@@ -174,13 +185,27 @@ def _load_beta_headers_config() -> dict:
     if _BETA_HEADERS_CONFIG is not None:
         return _BETA_HEADERS_CONFIG
 
-    # Get the URL from environment or use default
-    from litellm import anthropic_beta_headers_url
+    with _BETA_HEADERS_CONFIG_LOCK:
+        if _BETA_HEADERS_CONFIG is not None:
+            return _BETA_HEADERS_CONFIG
 
-    _BETA_HEADERS_CONFIG = get_beta_headers_config(url=anthropic_beta_headers_url)
-    verbose_logger.debug("Loaded and cached beta headers config")
+        # Get the URL from environment or use default
+        from litellm import anthropic_beta_headers_url
 
-    return _BETA_HEADERS_CONFIG
+        _BETA_HEADERS_CONFIG = get_beta_headers_config(url=anthropic_beta_headers_url)
+        verbose_logger.debug("Loaded and cached beta headers config")
+
+        return _BETA_HEADERS_CONFIG
+
+
+async def aload_beta_headers_config() -> None:
+    if _BETA_HEADERS_CONFIG is None:
+        await asyncio.get_running_loop().run_in_executor(_BETA_HEADERS_CONFIG_LOADER, _load_beta_headers_config)
+
+
+@cache
+def _bundled_beta_headers_config() -> BetaHeadersConfig:
+    return _BETA_HEADERS_CONFIG_ADAPTER.validate_python(GetAnthropicBetaHeadersConfig.load_local_beta_headers_config())
 
 
 def reload_beta_headers_config() -> dict:
@@ -288,6 +313,14 @@ def is_beta_header_supported(
     return beta_header in provider_mapping and provider_mapping[beta_header] is not None
 
 
+def is_beta_header_supported_by_bundled_config(beta_header: str, provider: str) -> bool:
+    config: Final = _bundled_beta_headers_config()
+    aliases: Final = config.get("provider_aliases", {})
+    canonical_provider: Final = (aliases.get(provider) if isinstance(aliases, Mapping) else None) or provider
+    provider_mapping: Final = config.get(canonical_provider, {})
+    return isinstance(provider_mapping, Mapping) and provider_mapping.get(beta_header) is not None
+
+
 def get_provider_beta_header(
     anthropic_beta_header: str,
     provider: str,
diff --git a/litellm/batches/batch_utils.py b/litellm/batches/batch_utils.py
index cdc2625239f..b99901bceaf 100644
--- a/litellm/batches/batch_utils.py
+++ b/litellm/batches/batch_utils.py
@@ -3,7 +3,7 @@ from collections.abc import Iterable, Iterator, Mapping
 from dataclasses import dataclass
 from dataclasses import replace as dataclasses_replace
 from enum import Enum
-from typing import Any, Final, Literal
+from typing import Any, Final, Literal, cast
 
 import litellm
 from litellm._logging import verbose_logger
@@ -768,9 +768,17 @@ def _batch_response_was_successful(
     message batch results lines report ``result.type == "succeeded"``; Bedrock
     batch output lines report ``modelOutput`` (and no ``error``).
     """
-    if custom_llm_provider == "anthropic":
-        return _get_anthropic_result_from_batch_results_line(batch_job_output_file).get("type") == "succeeded"
     if custom_llm_provider == "bedrock":
         return batch_job_output_file.get("modelOutput") is not None and batch_job_output_file.get("error") is None
-    _response: Final[dict] = batch_job_output_file.get("response", None) or {}
-    return _response.get("status_code", None) == 200
+    envelope_key: Final = "result" if custom_llm_provider == "anthropic" else "response"
+    envelope: Final = batch_job_output_file.get(envelope_key)
+    if not isinstance(envelope, Mapping):
+        if envelope is not None:
+            verbose_logger.warning("batch output %s must be an object, treating the line as unsuccessful", envelope_key)
+        return False
+    response: Final = cast(Mapping[object, object], envelope)  # cast-ok: mapping shape validated above
+    return (
+        response.get("type") == "succeeded"
+        if custom_llm_provider == "anthropic"
+        else response.get("status_code") == 200
+    )
diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
index 80e96b8e888..bbc41974daf 100644
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -8,7 +8,7 @@ from types import MappingProxyType
 from typing import TYPE_CHECKING, Any, Final, Literal, cast
 
 from httpx import Response
-from pydantic import BaseModel
+from pydantic import BaseModel, TypeAdapter
 from typing_extensions import ReadOnly, TypedDict, assert_never
 
 import litellm
@@ -126,6 +126,7 @@ from litellm.types.utils import (
     TranscriptionUsageTokensObject,
     Usage,
     VectorStoreSearchResponse,
+    is_server_derived_pricing_key,
 )
 from litellm.utils import (
     CallTypes,
@@ -138,6 +139,8 @@ from litellm.utils import (
     TextCompletionResponse,
     TranscriptionResponse,
     _cached_get_model_info_helper,
+    model_info_with_pricing_overrides,
+    runtime_model_cost_registrations,
     token_counter,
 )
 
@@ -403,6 +406,7 @@ def cost_per_token(
     ### REQUEST MODEL ###
     request_model: str | None = None,  # original request model for router detection
     custom_model_info: OCRPricing | None = None,
+    bedrock_model_info: ModelInfo | None = None,
 ) -> tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@@ -690,6 +694,15 @@ def cost_per_token(
     elif custom_llm_provider == "anthropic":
         return anthropic_cost_per_token(model=model, usage=usage_block, service_tier=service_tier)
     elif custom_llm_provider == "bedrock":
+        resolved_bedrock_info: Final = bedrock_model_info or _bedrock_pricing_info(model, None, "bedrock", False)
+        if resolved_bedrock_info is not None:
+            return generic_cost_per_token(
+                model=model,
+                usage=usage_block,
+                custom_llm_provider="bedrock",
+                service_tier=service_tier,
+                model_info=resolved_bedrock_info,
+            )
         return bedrock_cost_per_token(model=model, usage=usage_block, service_tier=service_tier)
     elif custom_llm_provider == "openai":
         return openai_cost_per_token(
@@ -803,6 +816,55 @@ def _cost_map_entry_prices_anything(entry: Mapping[str, object]) -> bool:
     )
 
 
+_LOGGED_LITELLM_PARAMS: Final = TypeAdapter(Mapping[str, object])
+
+
+def _bedrock_registration_has_prices(entry: Mapping[str, object]) -> bool:
+    return _cost_map_entry_prices_anything(entry) or any(
+        value is not None and field.startswith("cache_") and is_server_derived_pricing_key(field)
+        for field, value in entry.items()
+    )
+
+
+def _bedrock_pricing_info(
+    model: str | None,
+    invoked_model_id: str | None,
+    custom_llm_provider: str | None,
+    explicit_pricing: bool,
+) -> ModelInfo | None:
+    if explicit_pricing or custom_llm_provider != "bedrock" or not model:
+        return None
+    registration: Final = next(
+        (
+            (key, entry)
+            for key, entry in runtime_model_cost_registrations(model, "bedrock")
+            if _bedrock_registration_has_prices(entry)
+        ),
+        None,
+    )
+    profile: Final = _cost_map_model_info(invoked_model_id, "bedrock") if invoked_model_id else None
+    if profile is None or not _declares_rates(profile):
+        return _cost_map_model_info(registration[0], None) if registration is not None else None
+    if registration is None or registration[0] == profile["key"]:
+        return profile
+    return model_info_with_pricing_overrides(profile, registration[1])
+
+
+def _declares_rates(model_info: ModelInfo | None) -> bool:
+    entry: Final = _raw_cost_map_entry(model_info["key"]) if model_info is not None else None
+    return entry is not None and _cost_map_entry_prices_anything(entry)
+
+
+def _invoked_model_id_for_cost(
+    optional_params: object,
+    logging_obj: LitellmLoggingObject | None,
+) -> str | None:
+    recorded: Final[object] = getattr(logging_obj, "model_call_details", None)
+    return _get_hidden_str_for_cost_calc(optional_params, "model_id") or _get_hidden_str_for_cost_calc(
+        recorded, "model_id"
+    )
+
+
 def _select_model_name_for_cost_calc(
     model: str | None,
     completion_response: object | None,
@@ -811,6 +873,7 @@ def _select_model_name_for_cost_calc(
     custom_llm_provider: str | None = None,
     router_model_id: str | None = None,
     region_name: str | None = None,
+    invoked_model_id: str | None = None,
 ) -> str | None:
     """
     1. If custom pricing is true, return received model name
@@ -831,6 +894,13 @@ def _select_model_name_for_cost_calc(
     hidden_params: Final[dict | None] = getattr(completion_response, "_hidden_params", None)
     provider_response_model: Final = _get_hidden_str_for_cost_calc(hidden_params, "provider_response_model")
     explicit_pricing: Final = custom_pricing is True or base_model is not None
+    configured_model: Final = model or (
+        completion_response_model if isinstance(completion_response_model, str) else None
+    )
+    bedrock_model_info: Final = _bedrock_pricing_info(
+        configured_model, invoked_model_id, custom_llm_provider, explicit_pricing
+    )
+    bedrock_pricing_model: Final = bedrock_model_info["key"] if bedrock_model_info is not None else None
     priced_from_response: Final = provider_response_model is not None or completion_response_model is not None
     priced_region: Final = (
         _get_hidden_str_for_cost_calc(hidden_params, "region_name") or region_name
@@ -848,8 +918,8 @@ def _select_model_name_for_cost_calc(
         else:
             return_model = model
 
-    elif base_model is not None or provider_response_model is not None:
-        return_model = base_model if base_model is not None else provider_response_model
+    elif base_model is not None or bedrock_pricing_model is not None or provider_response_model is not None:
+        return_model = base_model if base_model is not None else bedrock_pricing_model or provider_response_model
 
     elif completion_response_model is None and hidden_params is not None:
         if hidden_params.get("model", None) is not None and len(hidden_params["model"]) > 0:
@@ -1428,6 +1498,10 @@ def completion_cost(
         service_tier = _normalize_service_tier(service_tier)
 
         explicit_pricing: Final = custom_pricing is True or base_model is not None
+        invoked_model_id: Final = _invoked_model_id_for_cost(
+            _LOGGED_LITELLM_PARAMS.validate_python(optional_params) if optional_params is not None else None,
+            litellm_logging_obj,
+        )
         selected_model: Final = _select_model_name_for_cost_calc(
             model=model,
             completion_response=completion_response,
@@ -1436,6 +1510,14 @@ def completion_cost(
             base_model=base_model,
             router_model_id=router_model_id,
             region_name=region_name,
+            invoked_model_id=invoked_model_id,
+        )
+
+        bedrock_model_info: Final = _bedrock_pricing_info(
+            model or _get_response_model(completion_response),
+            invoked_model_id,
+            _get_provider_for_cost_calc(model, custom_llm_provider),
+            explicit_pricing,
         )
 
         potential_model_names: Final = [
@@ -1810,6 +1892,7 @@ def completion_cost(
                     vertex_location=vertex_location,
                     response=completion_response,
                     custom_model_info=_ocr_model_info(litellm_logging_obj, custom_pricing, router_model_id),
+                    bedrock_model_info=bedrock_model_info,
                 )
 
                 # Get additional costs from provider (e.g., routing fees, infrastructure costs)
@@ -1898,6 +1981,7 @@ def completion_cost(
                             data_residency=data_residency,
                             vertex_location=vertex_location,
                             custom_cost_per_token=custom_cost_per_token,
+                            model_info=bedrock_model_info,
                         )
                         _reasoning_cost = _token_type_breakdown.reasoning_cost
                         _cache_read_cost = _token_type_breakdown.cache_read_cost
@@ -2139,7 +2223,16 @@ def pricing_entry_for_cost_calc(
         custom_llm_provider=custom_llm_provider,
         router_model_id=router_model_id,
         region_name=region_name,
+        invoked_model_id=_invoked_model_id_for_cost(None, litellm_logging_obj),
     )
+    bedrock_model_info: Final = _bedrock_pricing_info(
+        model or _get_response_model(completion_response),
+        _invoked_model_id_for_cost(None, litellm_logging_obj),
+        _get_provider_for_cost_calc(model, custom_llm_provider),
+        custom_pricing is True or base_model is not None,
+    )
+    if bedrock_model_info is not None:
+        return bedrock_model_info["key"], bedrock_model_info
     candidates: Final = (selected_model, _get_response_model(completion_response), model)
     resolved: Final = next(
         (info for info in (_cost_map_model_info(name, custom_llm_provider) for name in candidates if name) if info),
diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index 0f3cc84b126..821abe56580 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -5889,6 +5889,7 @@ class StandardLoggingPayloadSetup:
         custom_llm_provider: str | None,
         init_response_obj: object,
         api_base: str | None = None,
+        router_model_id: str | None = None,
     ) -> StandardLoggingModelInformation:
         model_cost_name: Final = _select_model_name_for_cost_calc(
             model=base_model if custom_pricing else None,
@@ -5896,12 +5897,23 @@ class StandardLoggingPayloadSetup:
             base_model=base_model,
             custom_pricing=custom_pricing,
         )
+        pricing_model_name: Final = (
+            _select_model_name_for_cost_calc(
+                model=base_model if custom_pricing else None,
+                completion_response=init_response_obj,
+                base_model=base_model,
+                custom_pricing=custom_pricing,
+                router_model_id=router_model_id,
+            )
+            if router_model_id is not None
+            else model_cost_name
+        )
         if model_cost_name is None:
             model_cost_information = StandardLoggingModelInformation(model_map_key="", model_map_value=None)
         else:
             try:
                 _model_cost_information: Final = litellm.get_model_info(
-                    model=model_cost_name,
+                    model=pricing_model_name or model_cost_name,
                     custom_llm_provider=custom_llm_provider,
                     api_base=api_base,
                 )
@@ -6566,6 +6578,7 @@ def get_standard_logging_object_payload(
             custom_llm_provider=kwargs.get("custom_llm_provider"),
             init_response_obj=init_response_obj,
             api_base=litellm_params.get("api_base"),
+            router_model_id=logging_obj.get_router_model_id(),
         )
 
         error_information, error_str = StandardLoggingPayloadSetup.get_error_information_for_logging_payload(
diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py
index 35ebf68e7d1..d935823fe5c 100644
--- a/litellm/litellm_core_utils/llm_cost_calc/utils.py
+++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py
@@ -75,6 +75,9 @@ _SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType(
         ServiceTier.ULTRAFAST.value: ServiceTier.ULTRAFAST.value,
     }
 )
+SERVICE_TIER_COST_KEY_SUFFIXES: Final[tuple[str, ...]] = tuple(
+    sorted(frozenset(f"_{suffix}" for suffix in _SERVICE_TIER_TO_COST_KEY_SUFFIX.values()))
+)
 
 _INCLUSIVE_THRESHOLD_PROVIDERS: Final = frozenset({"xai"})
 _BATCH_KEY_SUFFIX: Final = "_batches"
@@ -272,7 +275,7 @@ def _parse_token_threshold(threshold: str) -> float:
 
 
 def _parse_above_token_threshold(key: str) -> float:
-    return _parse_token_threshold(key.split("_above_")[1].split("_tokens")[0])
+    return _parse_token_threshold(key.rsplit("_above_", 1)[1].split("_tokens")[0])
 
 
 def _prompt_exceeds_threshold(prompt_tokens: int, threshold: float, inclusive: bool) -> bool:
@@ -665,20 +668,26 @@ def _get_token_base_cost(
     # Exclude service_tier-specific variants (e.g. input_cost_per_token_above_200k_tokens_priority)
     # so that the threshold detection loop only processes standard keys.  The
     # service_tier-specific above-threshold key is resolved later via _get_service_tier_cost_key.
+    tier_key_suffix: Final = _get_service_tier_cost_key("", service_tier)
+    threshold_prefixes: Final = tuple(f"{prefix}_above_" for prefix in _BATCH_RATE_PREFIXES)
     threshold_keys: Final = [
         k
         for k in model_info
-        if k.startswith("input_cost_per_token_above_") and not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES)
+        if k.startswith(threshold_prefixes)
+        and "_tokens" in k
+        and (
+            not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES) or (tier_key_suffix != "" and k.endswith(tier_key_suffix))
+        )
     ]
 
     # Only sort the threshold keys (typically 1-2 keys instead of 66+)
     threshold: float | None = None
-    for key in sorted(threshold_keys, key=_parse_above_token_threshold, reverse=True):
+    for key in sorted(threshold_keys, key=_parse_above_token_threshold):
         value = model_info.get(key)
         if value is not None:
             try:
                 # Handle both formats: _above_128k_tokens and _above_128_tokens
-                threshold_str = key.split("_above_")[1].split("_tokens")[0]
+                threshold_str = key.rsplit("_above_", 1)[1].split("_tokens")[0]
                 threshold = _parse_above_token_threshold(key)
                 if _prompt_exceeds_threshold(usage.prompt_tokens, threshold, threshold_is_inclusive):
                     # Prefer a service_tier-specific above-threshold key when available,
@@ -691,7 +700,7 @@ def _get_token_base_cost(
                             service_tier,
                         )
                         if service_tier
-                        else key
+                        else f"input_cost_per_token_above_{threshold_str}_tokens"
                     )
                     prompt_base_cost = cast(
                         float,
@@ -747,8 +756,6 @@ def _get_token_base_cost(
                     )
 
                     cache_read_cost = _get_cost_per_unit(model_info, cache_read_tiered_key, cache_read_cost)
-
-                    break
             except (IndexError, ValueError):
                 continue
             except Exception:
@@ -1663,20 +1670,23 @@ def get_billed_token_rates(
     vertex_location: str | None = None,
     current_time: datetime | None = None,
     custom_cost_per_token: CostPerToken | None = None,
+    model_info: ModelInfo | None = None,
 ) -> BilledTokenRates | None:
     """Rates the cost calculator bills ``usage`` at, resolved exactly as the totals and the token-type
     breakdown resolve them. None when the model's pricing cannot be resolved."""
     if custom_cost_per_token is not None:
         return _custom_pricing_rates(custom_cost_per_token)
     try:
-        model_info: Final = apply_provider_cache_read_default(
-            get_model_info(model=model, custom_llm_provider=custom_llm_provider),
+        resolved_model_info: Final = apply_provider_cache_read_default(
+            model_info
+            if model_info is not None
+            else get_model_info(model=model, custom_llm_provider=custom_llm_provider),
             custom_llm_provider,
         )
     except Exception:  # noqa: BLE001  # get_model_info raises a bare Exception for an unmapped model: no rates
         return None
     return _cost_map_billed_rates(
-        model_info=model_info,
+        model_info=resolved_model_info,
         usage=usage,
         custom_llm_provider=custom_llm_provider,
         service_tier=service_tier,
@@ -1695,6 +1705,7 @@ def get_token_type_cost_breakdown(
     vertex_location: str | None = None,
     current_time: datetime | None = None,
     custom_cost_per_token: CostPerToken | None = None,
+    model_info: ModelInfo | None = None,
 ) -> TokenTypeCostBreakdown:
     """
     Provider-agnostic cost of reasoning and cache tokens, derived from the usage
@@ -1719,6 +1730,7 @@ def get_token_type_cost_breakdown(
         vertex_location=vertex_location,
         current_time=current_time,
         custom_cost_per_token=custom_cost_per_token,
+        model_info=model_info,
     )
     if rates is None:
         return TokenTypeCostBreakdown(0.0, 0.0, 0.0)
diff --git a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py
index a83e23d83d5..91e84027163 100644
--- a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py
+++ b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py
@@ -3,6 +3,7 @@ from typing import Any, Final
 
 import httpx
 
+from litellm.anthropic_beta_headers_manager import is_beta_header_supported_by_bundled_config
 from litellm.exceptions import AuthenticationError
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.litellm_core_utils.litellm_logging import verbose_logger
@@ -611,6 +612,7 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
         optional_params: dict,
         custom_llm_provider: str = "anthropic",
         messages: Sequence[object] = (),
+        beta_map_provider: str | None = None,
     ) -> dict:
         """
         Auto-inject anthropic-beta headers based on features used.
@@ -627,8 +629,9 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
             optional_params: Optional parameters including tools, context_management, output_format, speed
             custom_llm_provider: Provider name for looking up correct tool search header
             messages: Request messages, scanned for per-message output_config
+            beta_map_provider: Provider whose beta map column gates safeguards, defaults to custom_llm_provider
         """
-        beta_values: Final[set] = set()
+        beta_values: Final[set[str]] = set()
 
         existing_beta: Final = tuple(
             piece.strip()
@@ -678,6 +681,12 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig):
         if optional_params.get("speed") == "fast":
             beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.FAST_MODE_2026_02_01.value)
 
+        if optional_params.get("safeguards") is not None and is_beta_header_supported_by_bundled_config(
+            ANTHROPIC_BETA_HEADER_VALUES.DANGEROUS_TOOL_USE_2026_09_03.value,
+            beta_map_provider or custom_llm_provider,
+        ):
+            beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.DANGEROUS_TOOL_USE_2026_09_03.value)
+
         if _messages_carry_output_config(messages):
             beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.PER_TURN_CONTROL_2026_07_01.value)
 
diff --git a/litellm/llms/azure/chat/gpt_5_transformation.py b/litellm/llms/azure/chat/gpt_5_transformation.py
index 3189f5b57ac..a9b6c27a0df 100644
--- a/litellm/llms/azure/chat/gpt_5_transformation.py
+++ b/litellm/llms/azure/chat/gpt_5_transformation.py
@@ -1,12 +1,10 @@
 """Support for Azure OpenAI gpt-5 model family."""
 
-from typing import Final
+from typing import ClassVar, Final
 
 import litellm
-from litellm.exceptions import UnsupportedParamsError
 from litellm.llms.openai.chat.gpt_5_transformation import (
     OpenAIGPT5Config,
-    _get_effort_level,
     is_gpt_reasoning_series_name,
 )
 from litellm.types.llms.openai import AllMessageValues
@@ -15,9 +13,16 @@ from .gpt_transformation import AzureOpenAIConfig
 
 
 class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
-    """Azure specific handling for gpt-5 models."""
+    """Azure specific handling for gpt-5 models.
+
+    reasoning_effort none joins xhigh as opt-in here: Azure rejected it on every gpt-5
+    deployment before gpt-5.1 (https://github.com/BerriAI/litellm/issues/16704), and a deployment
+    name the map never heard of must not forward it. See
+    https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning
+    """
 
     GPT5_SERIES_ROUTE = "gpt5_series/"
+    OPT_IN_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("xhigh", "none"))
 
     @classmethod
     def _model_map_lookup_name(cls, model: str) -> str:
@@ -27,11 +32,18 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
         model_prices_and_context_window.json; ``azure/gpt-5.1`` is. Overriding the shared
         resolver rather than one lookup means the supports, explicitly-disabled and
         default-effort answers all read the same entry.
+
+        An ``azure_ai/`` name reaches this config when ``get_llm_provider`` re-routes a Foundry
+        deployment on an OpenAI-v1 host to the azure provider with the prefix intact. It is the
+        same product the azure_ai config reads ``azure_ai/<model>`` for, so that row answers when
+        the map carries it, and the azure/ twin when it does not.
         """
         if model.startswith(cls.GPT5_SERIES_ROUTE):
             return "azure/" + model[len(cls.GPT5_SERIES_ROUTE) :]
         if model.startswith("azure/"):
             return model
+        if model.startswith("azure_ai/"):
+            return model if model in litellm.model_cost else "azure/" + model.removeprefix("azure_ai/")
         return "azure/" + model
 
     @classmethod
@@ -75,34 +87,7 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
         drop_params: bool,
         api_version: str = "",
     ) -> dict:
-        reasoning_effort_value = non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort")
-        effective_effort: Final = _get_effort_level(reasoning_effort_value)
-
-        # gpt-5.1/5.2/5.4 support reasoning_effort='none', but other gpt-5 models don't
-        # See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning
-        supports_none: Final = self._supports_reasoning_effort_level(model, "none")
-
-        if effective_effort == "none" and not supports_none:
-            if litellm.drop_params is True or (drop_params is not None and drop_params is True):
-                non_default_params = non_default_params.copy()
-                optional_params = optional_params.copy()
-                if _get_effort_level(non_default_params.get("reasoning_effort")) == "none":
-                    non_default_params.pop("reasoning_effort")
-                if _get_effort_level(optional_params.get("reasoning_effort")) == "none":
-                    optional_params.pop("reasoning_effort")
-            else:
-                raise UnsupportedParamsError(
-                    status_code=400,
-                    message=(
-                        "Azure OpenAI does not support reasoning_effort='none' for this model. "
-                        "Supported values are: 'low', 'medium', and 'high'. "
-                        "To drop this parameter, set `litellm.drop_params=True` or for proxy:\n\n"
-                        "`litellm_settings:\n drop_params: true`\n"
-                        "Issue: https://github.com/BerriAI/litellm/issues/16704"
-                    ),
-                )
-
-        result: Final = OpenAIGPT5Config.map_openai_params(
+        return OpenAIGPT5Config.map_openai_params(
             self,
             non_default_params=non_default_params,
             optional_params=optional_params,
@@ -110,17 +95,6 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
             drop_params=drop_params,
         )
 
-        # Only drop reasoning_effort='none' for models that don't support it
-        result_effort: Final = _get_effort_level(result.get("reasoning_effort"))
-        if result_effort == "none" and not supports_none:
-            result.pop("reasoning_effort")
-
-        # Azure gpt-5.4+ with tools + reasoning_effort is now routed to the
-        # Responses API bridge (same as OpenAI), so we no longer need to drop
-        # reasoning_effort here.  See: responses_api_bridge_check() in main.py.
-
-        return result
-
     def transform_request(
         self,
         model: str,
diff --git a/litellm/llms/azure/responses/transformation.py b/litellm/llms/azure/responses/transformation.py
index 2a82b42df7b..7ff983aa333 100644
--- a/litellm/llms/azure/responses/transformation.py
+++ b/litellm/llms/azure/responses/transformation.py
@@ -30,10 +30,18 @@ class AzureOpenAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
     def custom_llm_provider(self) -> LlmProviders:
         return LlmProviders.AZURE
 
+    @staticmethod
+    def _is_gpt_5_model(model: str) -> bool:
+        return AzureOpenAIGPT5Config.is_model_gpt_5_model(model)
+
     @staticmethod
     def _supports_reasoning_effort_none(model: str) -> bool:
         return AzureOpenAIGPT5Config._supports_reasoning_effort_level(model, "none")
 
+    @staticmethod
+    def _effort_level_is_disabled(model: str, level: str) -> bool:
+        return AzureOpenAIGPT5Config.row_disables_reasoning_effort_level(model, level)
+
     @staticmethod
     def _effort_resolves_to_none(model: str, effort: str | None) -> bool:
         return AzureOpenAIGPT5Config.effort_resolves_to_none(model, effort)
diff --git a/litellm/llms/azure_ai/responses/transformation.py b/litellm/llms/azure_ai/responses/transformation.py
index 66a284c821d..07d0f777473 100644
--- a/litellm/llms/azure_ai/responses/transformation.py
+++ b/litellm/llms/azure_ai/responses/transformation.py
@@ -3,6 +3,7 @@ from typing import Final
 import httpx
 
 from litellm.llms.azure.responses.transformation import AzureOpenAIResponsesAPIConfig
+from litellm.llms.azure_ai.chat.transformation import AzureAIGPT5Config
 from litellm.llms.azure_ai.common_utils import (
     AzureFoundryModelInfo,
     api_key_header_for_base,
@@ -27,6 +28,18 @@ class AzureAIResponsesAPIConfig(AzureOpenAIResponsesAPIConfig):
     def custom_llm_provider(self) -> LlmProviders:
         return LlmProviders.AZURE_AI
 
+    @staticmethod
+    def _supports_reasoning_effort_none(model: str) -> bool:
+        return AzureAIGPT5Config._supports_reasoning_effort_level(model, "none")
+
+    @staticmethod
+    def _effort_level_is_disabled(model: str, level: str) -> bool:
+        return AzureAIGPT5Config.row_disables_reasoning_effort_level(model, level)
+
+    @staticmethod
+    def _effort_resolves_to_none(model: str, effort: str | None) -> bool:
+        return AzureAIGPT5Config.effort_resolves_to_none(model, effort)
+
     def validate_environment(self, headers: dict, model: str, litellm_params: GenericLiteLLMParams | None) -> dict:
         params: Final = litellm_params or GenericLiteLLMParams()
         auth_headers: Final = get_azure_ai_auth_headers(
diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index 2a2f3052b2a..19a426018e3 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -2659,13 +2659,13 @@ class AmazonConverseConfig(BaseConfig):
 
         ## HANDLE TOOL CALLS
         _message: Final = Message(**chat_completion_message)
-        initial_finish_reason = map_finish_reason(completion_response["stopReason"])
+        mapped_finish_reason: Final = map_finish_reason(completion_response["stopReason"])
 
-        # When json_mode filtered out all synthetic tool calls the response
-        # is plain content, not a pending tool invocation. Fix finish_reason
-        # so callers (e.g. OpenAI SDK) don't misinterpret it.
-        if resolved_json_mode and not filtered_tools and tools:
-            initial_finish_reason = "stop"
+        initial_finish_reason: Final = (
+            "stop"
+            if resolved_json_mode and not filtered_tools and tools and mapped_finish_reason == "tool_calls"
+            else mapped_finish_reason
+        )
 
         (
             returned_message,
diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py
index ef13483e2f8..49977269067 100644
--- a/litellm/llms/custom_httpx/llm_http_handler.py
+++ b/litellm/llms/custom_httpx/llm_http_handler.py
@@ -3,7 +3,7 @@ import json
 import ssl
 from collections.abc import AsyncGenerator, AsyncIterator, Coroutine, Iterator, Mapping, Sequence
 from contextlib import asynccontextmanager
-from functools import lru_cache, partial
+from functools import lru_cache, partial, reduce
 from types import MappingProxyType, ModuleType
 from typing import (
     TYPE_CHECKING,
@@ -32,7 +32,7 @@ import litellm.litellm_core_utils
 import litellm.types
 import litellm.types.utils
 from litellm._logging import _redact_string, verbose_logger
-from litellm.anthropic_beta_headers_manager import update_headers_with_filtered_beta
+from litellm.anthropic_beta_headers_manager import aload_beta_headers_config, update_headers_with_filtered_beta
 from litellm.constants import MAX_FILE_LIST_LIMIT, REALTIME_WEBSOCKET_MAX_MESSAGE_SIZE_BYTES
 from litellm.files.types import FileContentStreamingResult
 from litellm.litellm_core_utils.agentic_followup_kwargs import build_agentic_followup_kwargs
@@ -46,6 +46,7 @@ from litellm.litellm_core_utils.audio_utils.subtitle_utils import (
     synthesize_subtitle_document,
 )
 from litellm.litellm_core_utils.core_helpers import set_provider_response_headers_in_hidden_params
+from litellm.litellm_core_utils.dot_notation_indexing import delete_nested_value
 from litellm.litellm_core_utils.get_litellm_params import AWS_CREDENTIAL_KWARGS_KEYS
 from litellm.litellm_core_utils.llm_request_utils import serialize_multipart_form_fields
 from litellm.litellm_core_utils.realtime_errors import (
@@ -2116,6 +2117,16 @@ class BaseLLMHTTPHandler:
             merged_headers.update(extra_headers_from_kwargs)
         if provider_specific_headers:
             merged_headers.update(provider_specific_headers)
+        request_params: Final = reduce(
+            delete_nested_value,
+            litellm_params.get("additional_drop_params") or (),
+            anthropic_messages_optional_request_params,
+        )
+        if (
+            request_params.get("safeguards") is not None
+            and anthropic_messages_provider_config.should_filter_anthropic_beta_headers()
+        ):
+            await aload_beta_headers_config()
         (
             headers,
             api_base,
@@ -2123,7 +2134,7 @@ class BaseLLMHTTPHandler:
             headers=merged_headers or {},
             model=model,
             messages=messages,
-            optional_params=anthropic_messages_optional_request_params,
+            optional_params=request_params,
             litellm_params=dict(litellm_params),
             api_key=api_key,
             api_base=api_base,
@@ -2154,20 +2165,11 @@ class BaseLLMHTTPHandler:
             custom_llm_provider=custom_llm_provider,
         )
 
-        additional_drop_params: Final[list[str]] = litellm_params.get("additional_drop_params") or []
-        if additional_drop_params:
-            from litellm.litellm_core_utils.dot_notation_indexing import delete_nested_value
-
-            for path in additional_drop_params:
-                anthropic_messages_optional_request_params = delete_nested_value(
-                    anthropic_messages_optional_request_params, path
-                )
-
         # Prepare request body
         request_body: Final = anthropic_messages_provider_config.transform_anthropic_messages_request(
             model=model,
             messages=messages,
-            anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+            anthropic_messages_optional_request_params=request_params,
             litellm_params=litellm_params,
             headers=headers,
         )
@@ -2273,7 +2275,7 @@ class BaseLLMHTTPHandler:
 
             held_back_tool_names: Final = self._server_fulfilled_tools_in_request(
                 logging_obj=logging_obj,
-                tools=anthropic_messages_optional_request_params.get("tools"),
+                tools=request_params.get("tools"),
             )
             initial_response = AgenticAnthropicStreamingIterator(
                 completion_stream=completion_stream,
@@ -2281,7 +2283,7 @@ class BaseLLMHTTPHandler:
                 model=model,
                 messages=messages,
                 anthropic_messages_provider_config=anthropic_messages_provider_config,
-                anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+                anthropic_messages_optional_request_params=request_params,
                 logging_obj=logging_obj,
                 custom_llm_provider=custom_llm_provider,
                 kwargs=kwargs_for_agentic,
@@ -2304,7 +2306,7 @@ class BaseLLMHTTPHandler:
             model=model,
             messages=messages,
             anthropic_messages_provider_config=anthropic_messages_provider_config,
-            anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+            anthropic_messages_optional_request_params=request_params,
             logging_obj=logging_obj,
             custom_llm_provider=custom_llm_provider,
             kwargs=kwargs_for_agentic,
diff --git a/litellm/llms/databricks/chat/transformation.py b/litellm/llms/databricks/chat/transformation.py
index 538904b34e6..b51b6815210 100644
--- a/litellm/llms/databricks/chat/transformation.py
+++ b/litellm/llms/databricks/chat/transformation.py
@@ -7,7 +7,7 @@ from collections.abc import AsyncIterator, Coroutine, Iterator, Mapping, Sequenc
 from typing import TYPE_CHECKING, Any, Final, Literal, cast, overload
 
 import httpx
-from pydantic import BaseModel
+from pydantic import BaseModel, TypeAdapter
 
 from litellm.constants import RESPONSE_FORMAT_TOOL_NAME
 from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import (
@@ -21,6 +21,9 @@ from litellm.litellm_core_utils.prompt_templates.common_utils import (
     strip_name_from_message,
 )
 from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
+from litellm.llms.base_llm.base_utils import (
+    type_to_response_format_param,  # pyright: ignore[reportUnknownVariableType]  # base_utils helper returns an untyped dict
+)
 from litellm.types.llms.anthropic import AllAnthropicToolsValues
 from litellm.types.llms.databricks import (
     AllDatabricksContentValues,
@@ -59,6 +62,10 @@ from ...anthropic.chat.transformation import (
 from ...openai_like.chat.transformation import OpenAILikeChatConfig
 from ..common_utils import DatabricksBase, DatabricksException
 
+_RESPONSE_FORMAT_ADAPTER: (  # mutable-ok: mirrors the dict return contract of get_json_schema_from_pydantic_object
+    Final[TypeAdapter[dict[str, object] | None]]
+) = TypeAdapter(dict[str, object] | None)
+
 
 def _is_bare_assistant_message(message_dict: Mapping[str, object]) -> bool:
     """Databricks rejects assistant messages with neither content nor tool calls, e.g. a replayed
@@ -68,6 +75,15 @@ def _is_bare_assistant_message(message_dict: Mapping[str, object]) -> bool:
     )
 
 
+def _collapse_single_text_block(message: Mapping[str, object]) -> Mapping[str, object]:
+    content: Final = message.get("content")
+    match content:
+        case [{"type": "text", "text": str() as text}] if content == [{"type": "text", "text": text}]:
+            return {**message, "content": text}
+        case _:
+            return message
+
+
 def _sanitize_empty_content(message_dict: dict[str, object]) -> None:
     """
     Remove or filter content so empty text blocks are not sent.
@@ -191,6 +207,14 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
     def get_config(cls, *, model: str | None = None):
         return super().get_config()
 
+    def get_json_schema_from_pydantic_object(
+        self,
+        response_format: (  # mutable-ok: matches BaseConfig override signature
+            type[BaseModel] | dict[str, object] | None
+        ),
+    ) -> dict[str, object] | None:  # mutable-ok: BaseConfig contract returns a dict
+        return _RESPONSE_FORMAT_ADAPTER.validate_python(type_to_response_format_param(response_format=response_format))
+
     def get_required_params(self) -> list[ProviderField]:
         """For a given provider, return it's required fields with a description"""
         return [
@@ -447,6 +471,7 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
         Databricks does not support:
         - 'name' in user message.
         - litellm's internal `thinking_blocks` / `reasoning_content` on assistant messages.
+        - non-Claude json_object "json" checks read only string content, so a single text block is sent as a string.
         """
         new_messages = []
         for idx, message in enumerate(messages):
@@ -462,7 +487,7 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
             _sanitize_empty_content(cast(dict[str, Any], _message))
             if _is_bare_assistant_message(_message):
                 continue
-            new_messages.append(_message)
+            new_messages.append(_collapse_single_text_block(_message) if "claude" not in model else _message)
 
         if "claude" not in model:
             new_messages = _split_parallel_tool_calls(
diff --git a/litellm/llms/openai/chat/gpt_5_transformation.py b/litellm/llms/openai/chat/gpt_5_transformation.py
index d0e5ff01e71..05e40ec70bb 100644
--- a/litellm/llms/openai/chat/gpt_5_transformation.py
+++ b/litellm/llms/openai/chat/gpt_5_transformation.py
@@ -1,7 +1,7 @@
 """Support for OpenAI gpt-5 model family."""
 
 import re
-from typing import Final
+from typing import ClassVar, Final
 
 import litellm
 from litellm.utils import (
@@ -67,6 +67,10 @@ def _get_effort_level(value: str | dict | None) -> str | None:
 GPT_REASONING_SERIES_MARKERS: Final = ("gpt-5", "gpt-6")
 
 
+def unsupported_reasoning_effort_message(param: str, level: str, model: str) -> str:
+    return f"{param}={level} is not supported for {model}. To drop unsupported params set `litellm.drop_params = True`"
+
+
 def is_gpt_reasoning_series_name(model: str) -> bool:
     normalized: Final = model.split("/")[-1]
     return any(marker in model for marker in GPT_REASONING_SERIES_MARKERS) and not normalized.startswith("gpt-5-chat")
@@ -82,6 +86,9 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
     - Support for GPT-5-Codex models optimized for code generation.
     """
 
+    OPT_IN_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("xhigh",))
+    ROUTE_SPECIFIC_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("max",))
+
     @classmethod
     def is_model_gpt_5_model(cls, model: str) -> bool:
         return is_gpt_reasoning_series_name(model)
@@ -193,15 +200,10 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
         return False
 
     @classmethod
-    def _is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool:
+    def is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool:
         """Return True only when the model map explicitly sets the capability to False.
 
-        Unlike ``_supports_reasoning_effort_level`` (which requires an explicit True),
-        this method returns True only when ``supports_{level}_reasoning_effort`` is
-        explicitly set to ``False`` in the model map.  A missing key is treated as
-        supported (i.e. this method returns False = not disabled).
-
-        Use this for opt-out checks where unknown models should be allowed through.
+        A missing key is not a disable. Unknown models pass through.
         """
         return is_explicitly_disabled_factory(
             model=cls._model_map_lookup_name(model),
@@ -209,6 +211,39 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
             key=f"supports_{level}_reasoning_effort",
         )
 
+    @classmethod
+    def _is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool:
+        return cls.is_reasoning_effort_level_explicitly_disabled(model, level)
+
+    @classmethod
+    def refuses_reasoning_effort_level(cls, model: str, level: str) -> bool:
+        """The chat gate for any requested effort level, read off the model's map row alone.
+
+        An opt-in level (xhigh here; Azure adds none) is refused unless the row says true, since
+        the providers rejected it on most of the family when it arrived. Every other level is
+        refused only when the row says false: a model the map never heard of, or a row without the
+        flag, keeps forwarding what it was sent, and a level with no flag at all (medium, high) is
+        never refused. So a new model in the family needs its map row and no code change, the
+        row's supports_<level>_reasoning_effort flags being the whole contract.
+
+        A route-specific level (max) is never refused by either gate: the same model honors it
+        on Responses and refuses it on Chat Completions, so one row flag cannot gate it on
+        either route. Chat forwards it for the Responses bridge and a plain chat call gets the
+        provider's own 400, exactly as before the gate read every level.
+        """
+        if level in cls.ROUTE_SPECIFIC_REASONING_EFFORTS:
+            return False
+        if level in cls.OPT_IN_REASONING_EFFORTS:
+            return not cls._supports_reasoning_effort_level(model, level)
+        return cls.is_reasoning_effort_level_explicitly_disabled(model, level)
+
+    @classmethod
+    def row_disables_reasoning_effort_level(cls, model: str, level: str) -> bool:
+        """The Responses gate: opt-out for every level except the route-specific ones."""
+        if level in cls.ROUTE_SPECIFIC_REASONING_EFFORTS:
+            return False
+        return cls.is_reasoning_effort_level_explicitly_disabled(model, level)
+
     def get_supported_openai_params(self, model: str) -> list:
         if self.is_model_gpt_5_search_model(model):
             return [
@@ -269,12 +304,12 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
                 drop_params=drop_params,
             )
 
-        # Get raw reasoning_effort and effective effort level for all guards.
-        # Use effective_effort (extracted string) for xhigh validation, "none" checks, and
-        # tool/sampling guards — dict inputs like {"effort": "none", "summary": "detailed"}
-        # must be treated as effort="none" to avoid incorrect tool-drop or sampling errors.
-        raw_reasoning_effort = non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort")
-        effective_effort: Final = _get_effort_level(raw_reasoning_effort)
+        # Dict inputs like {"effort": "none", "summary": "detailed"} are judged by their effort
+        # string so the gate, the sampling guard, and the temperature guard all see one level.
+        raw_reasoning_effort: Final = non_default_params.get("reasoning_effort") or optional_params.get(
+            "reasoning_effort"
+        )
+        requested_effort: Final = _get_effort_level(raw_reasoning_effort)
 
         # Normalize dict reasoning_effort to string for Chat Completions API.
         # Example: {"effort": "high", "summary": "detailed"} -> "high"
@@ -286,31 +321,20 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
                 if "reasoning_effort" in optional_params:
                     optional_params["reasoning_effort"] = normalized
 
-        if effective_effort == "xhigh":
-            # xhigh is an opt-in capability: only allow if model explicitly supports it.
-            if not self._supports_reasoning_effort_level(model, effective_effort):
-                if litellm.drop_params or drop_params:
-                    non_default_params.pop("reasoning_effort", None)
-                    optional_params.pop("reasoning_effort", None)
-                else:
-                    raise litellm.utils.UnsupportedParamsError(
-                        message=(f"reasoning_effort={effective_effort} is not supported for this model."),
-                        status_code=400,
-                    )
-        elif effective_effort in ("minimal", "low"):
-            # minimal/low are opt-out: unknown models pass through; only block when
-            # the model map explicitly sets supports_{level}_reasoning_effort=false.
-            # Example: gpt-5.5-pro only accepts {medium, high, xhigh}, so it sets
-            # supports_low_reasoning_effort=false (and supports_minimal=false).
-            if self._is_reasoning_effort_level_explicitly_disabled(model, effective_effort):
-                if litellm.drop_params or drop_params:
-                    non_default_params.pop("reasoning_effort", None)
-                    optional_params.pop("reasoning_effort", None)
-                else:
-                    raise litellm.utils.UnsupportedParamsError(
-                        message=(f"reasoning_effort={effective_effort} is not supported for this model."),
-                        status_code=400,
-                    )
+        if requested_effort is not None and self.refuses_reasoning_effort_level(model, requested_effort):
+            if litellm.drop_params or drop_params:
+                non_default_params.pop("reasoning_effort", None)
+                optional_params.pop("reasoning_effort", None)
+            else:
+                raise litellm.utils.UnsupportedParamsError(
+                    message=unsupported_reasoning_effort_message("reasoning_effort", requested_effort, model),
+                    status_code=400,
+                )
+
+        # The level the provider will see: None once dropped, so the guards below judge by the model's default effort
+        effective_effort: Final = _get_effort_level(
+            non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort")
+        )
 
         ################################################################
         # max_tokens is not supported for gpt-5 models on OpenAI API
diff --git a/litellm/llms/openai/responses/transformation.py b/litellm/llms/openai/responses/transformation.py
index 6c1d8698652..4ab02370d77 100644
--- a/litellm/llms/openai/responses/transformation.py
+++ b/litellm/llms/openai/responses/transformation.py
@@ -22,7 +22,10 @@ from litellm.litellm_core_utils.prompt_templates.common_utils import (
 from litellm.litellm_core_utils.safe_json_loads import safe_json_loads
 from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig
-from litellm.llms.openai.chat.gpt_5_transformation import is_gpt_reasoning_series_name
+from litellm.llms.openai.chat.gpt_5_transformation import (
+    is_gpt_reasoning_series_name,
+    unsupported_reasoning_effort_message,
+)
 from litellm.responses.litellm_completion_transformation.custom_tools import TOOL_CALL_ITEM_ID_PREFIX_BY_TYPE
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.llms.openai import *
@@ -136,6 +139,20 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
 
         return supports_none_reasoning_effort(model=model, custom_llm_provider=None)
 
+    @staticmethod
+    def _effort_level_is_disabled(model: str, level: str) -> bool:
+        """Whether the model's cost-map row turns this effort level off.
+
+        The same row the chat gate reads, so a level the row refuses is refused on both wires
+        and a new model needs its row, not code. This surface stays opt-out for every level,
+        xhigh included, since it never refused a level the row omits; max is the exception, a
+        level the row cannot gate because the same model takes it here and refuses it on chat.
+        Azure overrides this so a bare deployment name reads the azure/ entry.
+        """
+        from litellm.llms.openai.chat.gpt_5_transformation import OpenAIGPT5Config
+
+        return OpenAIGPT5Config.row_disables_reasoning_effort_level(model, level)
+
     @staticmethod
     def _effort_resolves_to_none(model: str, effort: str | None) -> bool:
         """Whether this request's reasoning effort ends up as "none", the one condition
@@ -242,7 +259,25 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig):
         lookup_name: Final = self._model_map_lookup_name(model)
         if self._is_gpt_5_model(model=lookup_name):
             reasoning: Final = params.get("reasoning") or {}
-            effort: Final = reasoning.get("effort") if isinstance(reasoning, dict) else None
+            requested_effort: Final = reasoning.get("effort") if isinstance(reasoning, dict) else None
+            if (
+                isinstance(reasoning, dict)
+                and isinstance(requested_effort, str)
+                and self._effort_level_is_disabled(lookup_name, requested_effort)
+            ):
+                if not (drop_params or litellm.drop_params):
+                    raise litellm.UnsupportedParamsError(
+                        message=unsupported_reasoning_effort_message("reasoning.effort", requested_effort, model),
+                        status_code=400,
+                    )
+                remaining: Final = reasoning.copy()
+                remaining.pop("effort", None)
+                if remaining:
+                    params["reasoning"] = remaining
+                else:
+                    params.pop("reasoning", None)
+            forwarded_reasoning: Final = params.get("reasoning")
+            effort: Final = forwarded_reasoning.get("effort") if isinstance(forwarded_reasoning, dict) else None
             supports_none: Final = self._supports_reasoning_effort_none(model=lookup_name)
             effort_is_none: Final = supports_none and self._effort_resolves_to_none(lookup_name, effort)
 
diff --git a/litellm/llms/openai_like/messages/transformation.py b/litellm/llms/openai_like/messages/transformation.py
index bae190c88c0..1426fcab3dd 100644
--- a/litellm/llms/openai_like/messages/transformation.py
+++ b/litellm/llms/openai_like/messages/transformation.py
@@ -8,6 +8,7 @@ from litellm.llms.anthropic.experimental_pass_through.messages.transformation im
 from litellm.llms.openai_like.json_loader import SimpleProviderConfig
 from litellm.secret_managers.main import get_secret_str
 from litellm.types.router import GenericLiteLLMParams
+from litellm.types.utils import LlmProviders
 
 DEFAULT_ANTHROPIC_API_VERSION: Final = "2023-06-01"
 
@@ -57,6 +58,7 @@ class OpenAILikeAnthropicMessagesConfig(AnthropicMessagesConfig):
             headers=normalized,
             optional_params=optional_params,
             messages=messages,
+            beta_map_provider=LlmProviders.OPENAI_LIKE.value,
         )
         return merged, api_base
 
diff --git a/litellm/main.py b/litellm/main.py
index 12854db15d0..4aa4159d771 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -1057,6 +1057,18 @@ def _resolve_openai_api_base(api_base: str | None) -> str:
     )
 
 
+def _chat_gate_refuses_reasoning_effort_none(model: str, custom_llm_provider: str) -> bool:
+    from litellm.llms.azure_ai.chat.transformation import AzureAIGPT5Config
+
+    match custom_llm_provider:
+        case "azure":
+            return litellm.AzureOpenAIGPT5Config.refuses_reasoning_effort_level(model, "none")
+        case "azure_ai":
+            return AzureAIGPT5Config.refuses_reasoning_effort_level(model, "none")
+        case _:
+            return OpenAIGPT5Config.refuses_reasoning_effort_level(model, "none")
+
+
 def responses_api_bridge_check(
     model: str,
     custom_llm_provider: str,
@@ -1129,10 +1141,13 @@ def responses_api_bridge_check(
         )
         for tool in (tools or ())
     )
-    if isinstance(reasoning_effort, dict):
-        reasoning_active = reasoning_effort.get("effort") != "none" or reasoning_effort.get("summary") is not None
-    else:
-        reasoning_active = reasoning_effort != "none"
+    requested_effort: Final = reasoning_effort.get("effort") if isinstance(reasoning_effort, dict) else reasoning_effort
+    requested_summary: Final = reasoning_effort.get("summary") if isinstance(reasoning_effort, dict) else None
+    reasoning_active: Final = (
+        requested_effort != "none"
+        or requested_summary is not None
+        or _chat_gate_refuses_reasoning_effort_none(model, custom_llm_provider)
+    )
     # The reasoning+tools constraint is enforced by the real OpenAI backend behind any api.openai.com
     # host (the default URL or a PrivateLink hostname such as <region>.privatelink.api.openai.com) and
     # by Azure OpenAI through the azure provider. Resolve the effective OpenAI base arg>global>env>default
@@ -5707,6 +5722,7 @@ def completion(
             optional_params=processed_non_default_params,  # [IMPORTANT] - using processed_non_default_params ensures consistent params logged to langfuse for finetuning / eval datasets.
             litellm_params=litellm_params,
             custom_llm_provider=custom_llm_provider,
+            model_id=optional_params.get("model_id"),
         )
         if mock_response or mock_tool_calls or mock_timeout:
             kwargs.pop("mock_timeout", None)  # remove for any fallbacks triggered
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index d0020004e19..98fee42de3c 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -99,22 +99,22 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md"
     },
     "ai21.jamba-1-5-mini-v1:0": {
         "deprecation_date": "2026-11-26",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md"
     },
     "ai21.jamba-instruct-v1:0": {
         "input_cost_per_token": 5e-07,
@@ -293,6 +293,7 @@
         "supports_nova_canvas_image_edit": true
     },
     "us.writer.palmyra-x4-v1:0": {
+        "deprecation_date": "2027-03-09",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -300,23 +301,25 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "us.writer.palmyra-x5-v1:0": {
+        "deprecation_date": "2027-03-21",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-x4-v1:0": {
+        "deprecation_date": "2027-03-09",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -324,42 +327,52 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-x5-v1:0": {
+        "deprecation_date": "2027-03-21",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-vision-7b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_vision": true
     },
     "amazon.nova-lite-v1:0": {
         "cache_read_input_token_cost": 1.5e-08,
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -369,13 +382,19 @@
     },
     "amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_priority": 1.3125e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -386,16 +405,21 @@
         "supports_vision": true
     },
     "amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.125e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_image_token": 1.25e-06,
+        "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_priority": 2.1875e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_priority": 1.75e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -406,14 +430,14 @@
         "supports_vision": true
     },
     "apac.amazon.nova-2-lite-v1:0": {
-        "cache_read_input_token_cost": 8.25e-08,
-        "input_cost_per_token": 3.3e-07,
+        "cache_read_input_token_cost": 9.9e-08,
+        "input_cost_per_token": 3.96e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token": 3.311e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -424,16 +448,17 @@
         "supports_vision": true
     },
     "apac.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "source": "https://aws.amazon.com/nova/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -444,14 +469,14 @@
         "supports_vision": true
     },
     "eu.amazon.nova-2-lite-v1:0": {
-        "cache_read_input_token_cost": 8.25e-08,
-        "input_cost_per_token": 3.3e-07,
+        "cache_read_input_token_cost": 1.0725e-07,
+        "input_cost_per_token": 4.29e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token": 3.597e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -462,16 +487,17 @@
         "supports_vision": true
     },
     "eu.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "source": "https://aws.amazon.com/nova/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -483,13 +509,22 @@
     },
     "us.amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 8.25e-08,
+        "cache_read_input_token_cost_flex": 4.125e-08,
+        "cache_read_input_token_cost_priority": 1.44375e-07,
         "input_cost_per_token": 3.3e-07,
+        "input_cost_per_token_batches": 1.65e-07,
+        "input_cost_per_token_flex": 1.65e-07,
+        "input_cost_per_token_priority": 5.775e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token_batches": 1.375e-06,
+        "output_cost_per_token_flex": 1.375e-06,
+        "output_cost_per_token_priority": 4.8125e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -500,16 +535,21 @@
         "supports_vision": true
     },
     "us.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
+        "input_cost_per_token_batches": 6.875e-07,
+        "input_cost_per_token_priority": 2.40625e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "output_cost_per_token_priority": 1.925e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -539,26 +579,60 @@
     "amazon.nova-micro-v1:0": {
         "cache_read_input_token_cost": 8.75e-09,
         "input_cost_per_token": 3.5e-08,
+        "input_cost_per_token_batches": 1.75e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 1.4e-07,
+        "output_cost_per_token_batches": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "amazon.nova-premier-v1:0": {
+        "cache_read_input_token_cost": 6.25e-07,
+        "cache_read_input_token_cost_priority": 1.09375e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_priority": 4.375e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 10000,
+        "max_tokens": 10000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-05,
+        "output_cost_per_token_batches": 6.25e-06,
+        "output_cost_per_token_priority": 2.1875e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 8e-07,
+        "input_cost_per_token_batches": 4e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "input_cost_per_token_priority": 1.4e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_flex": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -639,16 +713,20 @@
         "mode": "image_generation"
     },
     "amazon.titan-image-generator-v2": {
+        "deprecation_date": "2026-06-30",
         "input_cost_per_image": 0.0,
         "output_cost_per_image": 0.008,
         "litellm_provider": "bedrock",
-        "mode": "image_generation"
+        "mode": "image_generation",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html"
     },
     "amazon.titan-image-generator-v2:0": {
+        "deprecation_date": "2026-06-30",
         "input_cost_per_image": 0.0,
         "output_cost_per_image": 0.008,
         "litellm_provider": "bedrock",
-        "mode": "image_generation"
+        "mode": "image_generation",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html"
     },
     "twelvelabs.marengo-embed-2-7-v1:0": {
         "deprecation_date": "2026-11-30",
@@ -738,51 +816,58 @@
         "supports_image_input": true
     },
     "twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "us.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "eu.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "global.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
         "supports_video_input": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md"
     },
     "amazon.titan-text-express-v1": {
-        "input_cost_per_token": 1.3e-06,
+        "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
-        "output_cost_per_token": 1.7e-06
+        "output_cost_per_token": 6e-07
     },
     "amazon.titan-text-lite-v1": {
-        "input_cost_per_token": 3e-07,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 4000,
         "max_tokens": 4000,
         "mode": "chat",
-        "output_cost_per_token": 4e-07
+        "output_cost_per_token": 2e-07
     },
     "amazon.titan-text-premier-v1:0": {
         "input_cost_per_token": 5e-07,
@@ -837,7 +922,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5e-07,
-        "output_cost_per_token_batches": 2.5e-06
+        "output_cost_per_token_batches": 2.5e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-haiku-4-5@20251001": {
         "cache_creation_input_token_cost": 1.25e-06,
@@ -869,7 +958,7 @@
     "anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
@@ -879,10 +968,6 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 3e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07
     },
@@ -891,7 +976,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -903,11 +988,7 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 3e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07
+        "supports_vision": true
     },
     "anthropic.claude-3-7-sonnet-20240620-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -999,7 +1080,11 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -1058,7 +1143,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1094,7 +1183,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1130,7 +1223,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1166,7 +1263,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1202,7 +1303,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "au.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1238,7 +1343,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1276,7 +1385,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-mythos-preview": {
         "cache_creation_input_token_cost": 3.4375e-05,
@@ -1334,7 +1448,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1372,7 +1491,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1410,7 +1534,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1448,7 +1577,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "anthropic.claude-fable-5": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1480,13 +1614,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1557,13 +1696,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1634,13 +1778,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.375e-05,
@@ -1711,7 +1860,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -1793,7 +1942,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1833,7 +1987,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1871,7 +2030,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1911,7 +2075,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1949,7 +2118,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1989,7 +2163,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2027,7 +2206,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "eu.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2105,7 +2289,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "au.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2145,7 +2334,12 @@
         "prompt_cache_min_tokens": 512,
         "thinking_always_on": true,
         "supports_forced_tool_use": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2257,12 +2451,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2296,12 +2496,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2335,12 +2541,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2374,12 +2586,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2413,12 +2631,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2452,12 +2676,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "jp.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2494,7 +2724,12 @@
         "supports_minimal_reasoning_effort": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2528,12 +2763,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2567,12 +2808,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2606,12 +2853,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2645,12 +2898,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2684,12 +2943,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2723,6 +2988,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -2749,7 +3015,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2763,7 +3029,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2784,7 +3054,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2798,7 +3068,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2819,7 +3093,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2833,7 +3107,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2854,7 +3132,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2868,7 +3146,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "au.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2889,7 +3171,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2903,7 +3185,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "jp.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2924,7 +3210,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2938,7 +3224,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -2950,7 +3240,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -2971,18 +3261,23 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
+        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -3009,7 +3304,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-v1": {
         "input_cost_per_token": 8e-06,
@@ -3180,13 +3479,16 @@
     },
     "apac.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.1e-07,
+        "cache_read_input_token_cost_flex": 1.05e-07,
         "input_cost_per_token": 8.4e-07,
+        "input_cost_per_token_flex": 4.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.36e-06,
+        "output_cost_per_token_flex": 1.68e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -3219,7 +3521,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -3231,7 +3537,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -3252,7 +3558,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "assemblyai/best": {
         "input_cost_per_second": 3.333e-05,
@@ -3276,6 +3586,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -3302,17 +3613,21 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "azure/ada": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
         "max_tokens": 8191,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/codex-mini": {
         "cache_read_input_token_cost": 3.75e-07,
@@ -3358,7 +3673,7 @@
         "supports_function_calling": true
     },
     "azure_ai/claude-haiku-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-15",
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
@@ -3378,10 +3693,11 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-opus-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-24",
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
@@ -3402,7 +3718,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-opus-4-6": {
         "deprecation_date": "2027-02-02",
@@ -3588,6 +3905,7 @@
         "cache_creation_input_token_cost": 5e-06,
         "cache_creation_input_token_cost_above_1hr": 8e-06,
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-09-18",
         "supports_adaptive_thinking": true,
         "thinking_always_on": true,
         "supports_assistant_prefill": false,
@@ -3604,7 +3922,8 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_max_reasoning_effort": true,
-        "prompt_cache_min_tokens": 512
+        "prompt_cache_min_tokens": 512,
+        "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
     },
     "azure_ai/claude-opus-4-8": {
         "deprecation_date": "2027-09-01",
@@ -3640,7 +3959,7 @@
         "prompt_cache_min_tokens": 1024
     },
     "azure_ai/claude-sonnet-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-30",
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -3660,7 +3979,8 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-sonnet-5": {
         "deprecation_date": "2027-06-30",
@@ -3705,11 +4025,11 @@
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -3720,7 +4040,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models"
     },
     "azure/computer-use-preview": {
         "input_cost_per_token": 3e-06,
@@ -3751,9 +4072,10 @@
         "supports_vision": true
     },
     "azure/container": {
-        "code_interpreter_cost_per_session": 0.03,
+        "code_interpreter_cost_per_session": 0.033,
         "litellm_provider": "azure",
-        "mode": "chat"
+        "mode": "chat",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/"
     },
     "azure_ai/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
@@ -3805,7 +4127,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_cache_breakpoint": true,
@@ -3916,6 +4238,55 @@
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
+    "azure_ai/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "azure_ai/gpt-5.5": {
         "deprecation_date": "2027-10-26",
         "cache_read_input_token_cost": 5e-07,
@@ -3927,7 +4298,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -3965,7 +4336,7 @@
     },
     "azure_ai/gpt-chat-latest": {
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 272000,
@@ -4062,7 +4433,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4109,7 +4480,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4156,7 +4527,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4204,7 +4575,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4252,7 +4623,7 @@
         "input_cost_per_token_priority": 6e-05,
         "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -4298,7 +4669,7 @@
         "input_cost_per_token_priority": 6e-05,
         "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -4545,6 +4916,26 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/eu/gpt-4o": {
+        "deprecation_date": "2027-04-14",
+        "cache_creation_input_token_cost": 1.38e-06,
+        "cache_read_input_token_cost": 1.375e-06,
+        "input_cost_per_token": 2.75e-06,
+        "input_cost_per_token_batches": 1.375e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/gpt-4o-2024-11-20": {
         "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
@@ -4565,6 +4956,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/eu/gpt-4o-mini": {
+        "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
+        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token_batches": 8.3e-08,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
         "deprecation_date": "2027-04-14",
@@ -4606,6 +5016,7 @@
     "azure/eu/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2.2e-05,
         "cache_read_input_token_cost": 2.75e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.00011,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
@@ -4615,6 +5026,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.00022,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -4628,12 +5040,13 @@
         "input_cost_per_audio_token": 4.4e-05,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 8.8e-05,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_modalities": [
             "text",
             "audio"
@@ -4873,6 +5286,25 @@
         "supports_vision": true,
         "cache_read_input_token_cost_batches": 2.75e-09
     },
+    "azure/eu/o1": {
+        "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.65e-05,
+        "input_cost_per_token_batches": 8.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-05,
+        "output_cost_per_token_batches": 3.3e-05,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
         "deprecation_date": "2026-11-19",
@@ -4909,6 +5341,24 @@
         "supports_prompt_caching": true,
         "supports_vision": false
     },
+    "azure/eu/o3-mini": {
+        "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/eu/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
         "deprecation_date": "2026-11-19",
@@ -5140,12 +5590,13 @@
         "supports_tool_choice": true
     },
     "azure/gpt-3.5-turbo-instruct-0914": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-35-turbo": {
         "input_cost_per_token": 5e-07,
@@ -5184,20 +5635,22 @@
         "supports_tool_choice": true
     },
     "azure/gpt-35-turbo-instruct": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-35-turbo-instruct-0914": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-4": {
         "deprecation_date": "2025-06-06",
@@ -5274,38 +5727,41 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4-turbo": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_tool_choice": true
     },
     "azure/gpt-4-turbo-2024-04-09": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
     },
     "azure/gpt-4-turbo-vision-preview": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -5692,14 +6148,14 @@
     },
     "azure/gpt-audio-1.5": {
         "deprecation_date": "2027-08-24",
-        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
             "/v1/chat/completions"
@@ -5721,19 +6177,20 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-audio-1.5-2026-02-23": {
         "deprecation_date": "2027-08-24",
-        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -5853,13 +6310,13 @@
     "azure/gpt-4o-mini": {
         "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -5888,15 +6345,16 @@
         "supports_vision": true
     },
     "azure/gpt-4o-mini-audio-preview-2024-12-17": {
-        "input_cost_per_audio_token": 4e-05,
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
-        "output_cost_per_token": 1e-05,
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 6e-07,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -6079,7 +6537,7 @@
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
-        "deprecation_date": "2027-07-31",
+        "deprecation_date": "2027-06-25",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image_token": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -6090,7 +6548,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 2.4e-05,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -6114,7 +6572,7 @@
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 6e-08,
-        "deprecation_date": "2027-07-31",
+        "deprecation_date": "2027-06-25",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_image_token": 8e-07,
         "input_cost_per_token": 6e-07,
@@ -6125,7 +6583,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -6215,7 +6673,7 @@
     },
     "azure/gpt-4o-mini-transcribe": {
         "deprecation_date": "2027-06-15",
-        "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
@@ -6228,7 +6686,7 @@
     },
     "azure/gpt-4o-mini-tts": {
         "deprecation_date": "2027-06-15",
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "azure",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
@@ -6248,6 +6706,7 @@
     "azure/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2e-05,
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.0001,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
@@ -6257,6 +6716,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.0002,
         "output_cost_per_token": 2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -6269,12 +6729,13 @@
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
         "output_cost_per_audio_token": 8e-05,
         "output_cost_per_token": 2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supported_modalities": [
             "text",
             "audio"
@@ -6291,27 +6752,29 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4o-transcribe": {
-        "deprecation_date": "2026-12-31",
-        "input_cost_per_audio_token": 2.5e-06,
+        "deprecation_date": "2026-10-15",
+        "input_cost_per_audio_token": 6e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
     },
     "azure/gpt-4o-transcribe-diarize": {
         "deprecation_date": "2027-04-15",
-        "input_cost_per_audio_token": 2.5e-06,
+        "input_cost_per_audio_token": 6e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
@@ -6320,6 +6783,9 @@
         "deprecation_date": "2027-05-06",
         "input_cost_per_second": 0.0002833333333333333,
         "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "audio_transcription",
         "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper",
         "supported_endpoints": [
@@ -7374,7 +7840,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7430,7 +7896,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7480,7 +7946,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7530,7 +7996,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7586,7 +8052,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7636,7 +8102,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7687,7 +8153,7 @@
         "input_cost_per_token_batches": 1.5e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -7736,7 +8202,7 @@
         "input_cost_per_token_batches": 1.5e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -8251,7 +8717,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8300,7 +8766,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8413,11 +8879,17 @@
     "azure/gpt-6-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8425,11 +8897,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8462,11 +8932,17 @@
     "azure/gpt-6-sol-2026-09-22": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8474,11 +8950,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8508,9 +8982,254 @@
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
+    "azure/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/gpt-6.1-sol-2026-09-29": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/us/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/eu/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.4e-06,
+        "input_cost_per_token_above_272k_tokens": 4.8e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/apac/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.4e-06,
+        "input_cost_per_token_above_272k_tokens": 4.8e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "azure/gpt-chat-latest": {
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8841,7 +9560,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8906,10 +9625,16 @@
         "deprecation_date": "2028-03-11",
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8917,11 +9642,9 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
+        "output_cost_per_token_priority": 2.2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8953,7 +9676,7 @@
     },
     "azure/us/gpt-chat-latest": {
         "cache_read_input_token_cost": 5.5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -9228,7 +9951,7 @@
         "input_cost_per_token_batches": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9287,7 +10010,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9342,7 +10065,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9394,7 +10117,7 @@
         "input_cost_per_token_priority": 1.25e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9454,7 +10177,7 @@
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9513,7 +10236,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9566,7 +10289,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9620,7 +10343,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9673,7 +10396,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -10001,6 +10724,7 @@
         "cache_read_input_token_cost_batches": 1e-08
     },
     "azure/gpt-image-1": {
+        "cache_read_input_image_token_cost": 2.5e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
@@ -10008,28 +10732,32 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 4e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/hd/1024-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 7.629e-08,
+        "input_cost_per_pixel": 8.39233e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/hd/1024-x-1792/dall-e-3": {
-        "input_cost_per_pixel": 6.539e-08,
+        "input_cost_per_pixel": 7.19343e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/hd/1792-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 6.539e-08,
+        "input_cost_per_pixel": 7.19343e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/high/1024-x-1024/gpt-image-1": {
         "deprecation_date": "2026-10-23",
@@ -10122,6 +10850,7 @@
         ]
     },
     "azure/gpt-image-1-mini": {
+        "cache_read_input_image_token_cost": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "deprecation_date": "2027-04-07",
         "input_cost_per_image_token": 2.5e-06,
@@ -10129,12 +10858,14 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 8e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-1.5": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2026-12-16",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10142,12 +10873,15 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-1.5-2025-12-16": {
+        "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-12-16",
         "input_cost_per_token": 5e-06,
@@ -10155,12 +10889,15 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-2": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-10-21",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10168,6 +10905,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10176,6 +10914,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2.5-flare": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-09-09",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10183,6 +10922,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10191,6 +10931,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2.5-sunburst": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-09-09",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10198,6 +10939,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10206,6 +10948,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2-2026-04-21": {
+        "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2027-10-21",
         "input_cost_per_token": 5e-06,
@@ -10213,6 +10956,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10481,7 +11225,6 @@
         },
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10550,7 +11293,6 @@
         "output_cost_per_token_batches": 4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10582,7 +11324,6 @@
         "output_cost_per_token_batches": 4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10659,52 +11400,55 @@
         "output_cost_per_token": 0.0
     },
     "azure/standard/1024-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 3.81469e-08,
+        "input_cost_per_pixel": 4.19617e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/standard/1024-x-1792/dall-e-3": {
-        "input_cost_per_pixel": 4.359e-08,
+        "input_cost_per_pixel": 4.79562e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/standard/1792-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 4.359e-08,
+        "input_cost_per_pixel": 4.79562e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-3-large": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1.3e-07,
+        "input_cost_per_token": 1.43e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-3-small": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 2e-08,
+        "input_cost_per_token": 2.2e-08,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-ada-002": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/speech/azure-tts": {
         "input_cost_per_character": 1.5e-05,
@@ -10737,9 +11481,10 @@
     },
     "azure/tts-1-hd": {
         "deprecation_date": "2026-12-15",
-        "input_cost_per_character": 3e-05,
+        "input_cost_per_character": 3.3e-05,
         "litellm_provider": "azure",
-        "mode": "audio_speech"
+        "mode": "audio_speech",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/us/gpt-4.1-2025-04-14": {
         "deprecation_date": "2027-04-14",
@@ -10871,6 +11616,26 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/gpt-4o": {
+        "deprecation_date": "2027-04-14",
+        "cache_creation_input_token_cost": 1.38e-06,
+        "cache_read_input_token_cost": 1.375e-06,
+        "input_cost_per_token": 2.75e-06,
+        "input_cost_per_token_batches": 1.375e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/gpt-4o-2024-11-20": {
         "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
@@ -10891,6 +11656,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/gpt-4o-mini": {
+        "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
+        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token_batches": 8.3e-08,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
         "deprecation_date": "2027-04-14",
@@ -10932,6 +11716,7 @@
     "azure/us/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2.2e-05,
         "cache_read_input_token_cost": 2.75e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.00011,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
@@ -10941,6 +11726,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.00022,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -10954,12 +11740,13 @@
         "input_cost_per_audio_token": 4.4e-05,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 8.8e-05,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_modalities": [
             "text",
             "audio"
@@ -11199,6 +11986,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/o1": {
+        "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.65e-05,
+        "input_cost_per_token_batches": 8.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-05,
+        "output_cost_per_token_batches": 3.3e-05,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
         "deprecation_date": "2026-11-19",
@@ -11235,6 +12041,39 @@
         "supports_prompt_caching": true,
         "supports_vision": false
     },
+    "azure/us/o3": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_batches": 1.1e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-06,
+        "output_cost_per_token_batches": 4.4e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o3-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 5.5e-07,
@@ -11268,6 +12107,24 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/o3-mini": {
+        "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/us/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
         "deprecation_date": "2026-11-19",
@@ -11286,6 +12143,27 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "azure/us/o4-mini": {
+        "cache_read_input_token_cost": 3.03e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 3.03e-07,
         "deprecation_date": "2026-11-19",
@@ -11358,6 +12236,8 @@
     },
     "azure_ai/FLUX-1.1-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 5000,
+        "max_tokens": 5000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
         "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659",
@@ -11367,18 +12247,22 @@
     },
     "azure_ai/FLUX.1-Kontext-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 5000,
+        "max_tokens": 5000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
-        "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/",
         "supported_endpoints": [
             "/v1/images/generations"
         ]
     },
     "azure_ai/flux.2-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
+        "max_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
-        "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supported_endpoints": [
             "/v1/images/generations"
         ]
@@ -11699,34 +12583,37 @@
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
         "mode": "image_generation",
-        "output_cost_per_image": 0.05,
+        "output_cost_per_image": 0.048,
         "output_cost_per_image_token": 4.7e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ],
-        "deprecation_date": "2026-10-01"
+        "deprecation_date": "2026-10-01",
+        "max_input_tokens": 32000
     },
     "azure_ai/MAI-Image-2.5-Flash": {
         "input_cost_per_image_token": 1.75e-06,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure_ai",
         "mode": "image_generation",
-        "output_cost_per_image": 0.0338,
-        "output_cost_per_image_token": 3.3e-05,
+        "output_cost_per_image": 0.02,
+        "output_cost_per_image_token": 1.95e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ],
-        "deprecation_date": "2026-10-01"
+        "deprecation_date": "2026-10-01",
+        "max_input_tokens": 32000
     },
     "azure_ai/MAI-Image-2.5-Pro": {
         "deprecation_date": "2026-10-01",
         "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image": 0.1085,
         "output_cost_per_image_token": 0.000106,
@@ -11764,11 +12651,11 @@
         "input_cost_per_token": 7.1e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.1e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
@@ -11776,8 +12663,8 @@
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -11799,6 +12686,7 @@
         "supports_vision": true
     },
     "azure_ai/Meta-Llama-3-70B-Instruct": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -11806,9 +12694,11 @@
         "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 3.7e-07,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/Meta-Llama-3.1-70B-Instruct": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_token": 2.68e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11816,10 +12706,11 @@
         "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 3.54e-06,
-        "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/Phi-3-medium-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.7e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11827,11 +12718,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.8e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-medium-4k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.7e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 4096,
@@ -11839,11 +12731,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.8e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-mini-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11851,11 +12744,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-mini-4k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 4096,
@@ -11863,11 +12757,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-small-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11875,11 +12770,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-small-8k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -11887,11 +12783,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-MoE-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.6e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11899,11 +12796,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.4e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-mini-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11911,11 +12809,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-vision-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11923,7 +12822,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -12058,6 +12957,7 @@
         "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/"
     },
     "azure_ai/MAI-DS-R1": {
+        "deprecation_date": "2026-02-27",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12065,11 +12965,12 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
     "azure_ai/cohere-rerank-v3-english": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "azure_ai",
@@ -12077,9 +12978,11 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/cohere-rerank-v3-multilingual": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "azure_ai",
@@ -12087,7 +12990,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/cohere-rerank-v4.0-pro": {
         "input_cost_per_query": 0.0025,
@@ -12114,12 +13018,12 @@
     "azure_ai/deepseek-v3.2": {
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -12129,12 +13033,12 @@
     "azure_ai/deepseek-v3.2-speciale": {
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -12142,6 +13046,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/deepseek-v3": {
+        "deprecation_date": "2025-08-31",
         "input_cost_per_token": 1.14e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12149,7 +13054,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 4.56e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/deepseek-v4-pro": {
@@ -12190,11 +13095,11 @@
         "input_cost_per_token": 4.4e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12216,17 +13121,18 @@
             "text",
             "image"
         ],
-        "supports_embedding_image_input": true
+        "supports_embedding_image_input": true,
+        "input_cost_per_image_token": 4.7e-07
     },
     "azure_ai/grok-4": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 262000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -12239,12 +13145,12 @@
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
-        "max_output_tokens": 200000,
-        "max_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12265,7 +13171,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12315,9 +13221,9 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supports_function_calling": true,
@@ -12329,9 +13235,9 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supports_function_calling": true,
@@ -12343,18 +13249,19 @@
     "azure_ai/grok-code-fast-1": {
         "input_cost_per_token": 2e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "azure_ai/jais-30b-chat": {
+        "deprecation_date": "2026-01-30",
         "input_cost_per_token": 0.0032,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -12362,9 +13269,10 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.00971,
-        "source": "https://ai.azure.com/catalog/models/jais-30b-chat"
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/jamba-instruct": {
+        "deprecation_date": "2025-03-01",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 70000,
@@ -12372,6 +13280,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/kimi-k2.5": {
@@ -12416,6 +13325,7 @@
         "supports_prompt_caching": true
     },
     "azure_ai/ministral-3b": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 4e-08,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12428,6 +13338,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/mistral-large": {
+        "deprecation_date": "2025-04-15",
         "input_cost_per_token": 4e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 32000,
@@ -12435,10 +13346,12 @@
         "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "azure_ai/mistral-large-2407": {
+        "deprecation_date": "2025-05-13",
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12446,7 +13359,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
@@ -12476,6 +13389,7 @@
         "supports_vision": true
     },
     "azure_ai/mistral-medium-2505": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
@@ -12488,6 +13402,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/mistral-nemo": {
+        "deprecation_date": "2026-01-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
@@ -12495,10 +13410,11 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true
     },
     "azure_ai/mistral-small": {
+        "deprecation_date": "2025-07-31",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 32000,
@@ -12506,10 +13422,12 @@
         "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "azure_ai/mistral-small-2503": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12535,43 +13453,43 @@
         "source": "https://developers.openai.com/api/docs/pricing"
     },
     "bedrock/*/1-month-commitment/cohere.command-light-text-v14": {
+        "cost_per_second": 0.001902,
         "input_cost_per_second": 0.001902,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.001902,
         "supports_tool_choice": true
     },
     "bedrock/*/1-month-commitment/cohere.command-text-v14": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/*/6-month-commitment/cohere.command-light-text-v14": {
+        "cost_per_second": 0.0011416,
         "input_cost_per_second": 0.0011416,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.0011416,
         "supports_tool_choice": true
     },
     "bedrock/*/6-month-commitment/cohere.command-text-v14": {
+        "cost_per_second": 0.0066027,
         "input_cost_per_second": 0.0066027,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.0066027,
         "supports_tool_choice": true
     },
     "bedrock/guardrails": {
@@ -12590,61 +13508,61 @@
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.01475,
         "input_cost_per_second": 0.01475,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.01475,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0455,
         "input_cost_per_second": 0.0455,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0455
+        "mode": "chat"
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0455,
         "input_cost_per_second": 0.0455,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0455,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.008194,
         "input_cost_per_second": 0.008194,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.008194,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.02527,
         "input_cost_per_second": 0.02527,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.02527
+        "mode": "chat"
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.02527,
         "input_cost_per_second": 0.02527,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.02527,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/anthropic.claude-instant-v1": {
@@ -12679,12 +13597,14 @@
     },
     "bedrock/ap-northeast-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12692,32 +13612,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-northeast-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-northeast-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12725,71 +13649,86 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.3e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token_flex": 1.52e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-northeast-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/moonshotai.kimi-k2-thinking": {
-        "input_cost_per_token": 7.3e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
-        "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
-        "output_cost_per_token": 3.03e-06,
-        "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart",
+        "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12800,31 +13739,37 @@
         "supports_response_schema": true
     },
     "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.18e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.2e-06
+        "output_cost_per_token": 4.2e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 7.2e-07
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/ap-south-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12832,32 +13777,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-south-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-south-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12865,59 +13814,69 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.1e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.94e-06,
+        "output_cost_per_token_flex": 1.47e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/ap-south-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-south-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/ap-southeast-2/minimax.minimax-m2.5": {
-        "input_cost_per_token": 3.09e-07,
+        "input_cost_per_token": 3.1e-07,
+        "input_cost_per_token_flex": 1.55e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12925,16 +13884,19 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.236e-06
+        "output_cost_per_token": 1.24e-06,
+        "output_cost_per_token_flex": 6.2e-07
     },
     "bedrock/ap-southeast-3/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12942,32 +13904,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-southeast-3/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-southeast-3/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12975,66 +13941,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-southeast-3/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.05e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.03e-06
+        "output_cost_per_token": 4.03e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6.9e-07
+        "output_cost_per_token": 6.9e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-north-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13042,32 +14019,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/eu-north-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-north-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13075,80 +14056,83 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-north-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.01635,
         "input_cost_per_second": 0.01635,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.01635,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0415,
         "input_cost_per_second": 0.0415,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0415
+        "mode": "chat"
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0415,
         "input_cost_per_second": 0.0415,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0415,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.009083,
         "input_cost_per_second": 0.009083,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.009083,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.02305,
         "input_cost_per_second": 0.02305,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.02305
+        "mode": "chat"
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.02305,
         "input_cost_per_second": 0.02305,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.02305,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/anthropic.claude-instant-v1": {
@@ -13181,29 +14165,33 @@
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-central-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13211,66 +14199,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-central-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.86e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.78e-06
+        "output_cost_per_token": 3.78e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6.5e-07
+        "output_cost_per_token": 6.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-west-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-west-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13278,66 +14277,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-west-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.45e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.55e-06
+        "output_cost_per_token": 4.55e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 7.8e-07
+        "output_cost_per_token": 7.8e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-west-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.7e-07,
+        "input_cost_per_token_flex": 2.35e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-west-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 4.7e-07,
+        "input_cost_per_token_flex": 2.35e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13345,16 +14355,19 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.86e-06
+        "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07
     },
     "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": {
         "input_cost_per_token": 2.3e-07,
+        "input_cost_per_token_flex": 1.15e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 1.01e-06,
+        "output_cost_per_token_flex": 5.05e-07,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -13366,75 +14379,85 @@
     },
     "bedrock/eu-west-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 7.8e-07,
+        "input_cost_per_token_flex": 3.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 5.2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.56e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 9.1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/eu-south-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-south-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13442,23 +14465,26 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-south-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -13479,31 +14505,37 @@
         "cache_creation_input_token_cost": 3.75e-06
     },
     "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.45e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 5.88e-06
+        "output_cost_per_token": 5.88e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.01e-06
+        "output_cost_per_token": 1.01e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/sa-east-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13511,32 +14543,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/sa-east-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/sa-east-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13544,107 +14580,116 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.3e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token_flex": 1.52e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/sa-east-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/sa-east-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0175
+        "mode": "chat"
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0175,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.00611,
         "input_cost_per_second": 0.00611,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00611,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.00972
+        "mode": "chat"
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00972,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/anthropic.claude-instant-v1": {
@@ -13678,62 +14723,72 @@
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13741,29 +14796,34 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-east-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-east-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -13773,59 +14833,69 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html"
     },
     "bedrock/us-east-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-east-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-east-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-east-2/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13833,32 +14903,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-east-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-east-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13866,50 +14940,59 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.2e-06
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07
     },
     "bedrock/us-east-2/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-east-2/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-east-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.4e-07,
@@ -13995,7 +15078,11 @@
         "supports_vision": true,
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -14114,7 +15201,7 @@
         "output_vector_size": 1536
     },
     "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": {
-        "input_cost_per_token": 2e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_tokens": 8192,
@@ -14123,13 +15210,13 @@
         "output_vector_size": 1024
     },
     "bedrock/us-gov-west-1/amazon.titan-text-express-v1": {
-        "input_cost_per_token": 1.3e-06,
+        "input_cost_per_token": 8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
-        "output_cost_per_token": 1.7e-06
+        "output_cost_per_token": 1.6e-06
     },
     "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": {
         "input_cost_per_token": 3e-07,
@@ -14172,7 +15259,11 @@
         "supports_vision": true,
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -14220,79 +15311,83 @@
         "supports_pdf_input": true
     },
     "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0175
+        "mode": "chat"
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0175,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.00611,
         "input_cost_per_second": 0.00611,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00611,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.00972
+        "mode": "chat"
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00972,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/anthropic.claude-instant-v1": {
@@ -14326,44 +15421,50 @@
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -14371,29 +15472,34 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-west-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-west-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -14403,50 +15509,58 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html"
     },
     "bedrock/us-west-2/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-west-2/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-west-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "cache_creation_input_token_cost": 1e-06,
@@ -14642,6 +15756,7 @@
         "source": "https://developers.openai.com/api/docs/pricing"
     },
     "claude-haiku-4-5-20251001": {
+        "supports_web_search": true,
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_creation_input_token_cost_batches": 6.25e-07,
@@ -14699,18 +15814,14 @@
     "claude-sonnet-4-5": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_batches": 1.875e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_read_input_token_cost_batches": 1.5e-07,
+        "deprecation_date": "2026-11-30",
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "anthropic",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -14737,18 +15848,14 @@
     "claude-sonnet-4-5-20250929": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_batches": 1.875e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_read_input_token_cost_batches": 1.5e-07,
+        "deprecation_date": "2026-11-30",
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "anthropic",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -14774,6 +15881,7 @@
         "source": "https://docs.anthropic.com/en/docs/about-claude/pricing"
     },
     "claude-sonnet-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_1hr": 4e-06,
@@ -14817,7 +15925,54 @@
         "prompt_cache_min_tokens": 1024,
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
+    "claude-sonnet-5-5": {
+        "supports_anthropic_compaction": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "provider_specific_entry": {
+            "us": 1.1
+        },
+        "supports_output_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing",
+        "supports_web_search": true
+    },
     "claude-sonnet-4-6": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
@@ -14840,7 +15995,7 @@
         },
         "supports_adaptive_thinking": true,
         "supports_legacy_thinking": true,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -14891,6 +16046,7 @@
         "output_cost_per_token_batches": 7.5e-06
     },
     "claude-opus-4-5-20251101": {
+        "supports_web_search": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_creation_input_token_cost_batches": 3.125e-06,
@@ -14960,6 +16116,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15045,6 +16202,7 @@
         "prompt_cache_min_tokens": 4096
     },
     "claude-opus-4-7": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15132,6 +16290,7 @@
         "prompt_cache_min_tokens": 2048
     },
     "claude-fable-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_1hr": 2e-05,
@@ -15176,6 +16335,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-fable-5-1": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_1hr": 2e-05,
@@ -15221,6 +16381,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 5e-06,
         "cache_creation_input_token_cost_above_1hr": 8e-06,
@@ -15258,9 +16419,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_max_reasoning_effort": true,
-        "provider_specific_entry": {
-            "fast": 2.0
-        },
+        "provider_specific_entry": {"us":1.1,"fast":2},
         "supports_output_config": true,
         "supports_speed": true,
         "supports_fast_mode": true,
@@ -15268,6 +16427,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15315,6 +16475,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-8": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15361,6 +16522,82 @@
         "prompt_cache_min_tokens": 1024,
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
+    "cloudflare/clef-omni": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 64000,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/",
+        "supports_audio_input": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef-omni": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 64000,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/",
+        "supports_audio_input": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "cloudflare/clef": {
+        "input_cost_per_token": 2.4e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/clef-flash": {
+        "input_cost_per_token": 9e-08,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef": {
+        "input_cost_per_token": 2.4e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef-flash": {
+        "input_cost_per_token": 9e-08,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/clairic": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "extraction",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clairic/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clairic": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "extraction",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clairic/",
+        "supports_vision": true
+    },
     "cloudflare/@cf/meta/llama-2-7b-chat-fp16": {
         "input_cost_per_token": 1.923e-06,
         "litellm_provider": "cloudflare",
@@ -15796,7 +17033,31 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_vector_size": 1536,
-        "supports_embedding_image_input": true
+        "supports_embedding_image_input": true,
+        "input_cost_per_image_token": 4.7e-07,
+        "source": "https://cohere.com/pricing"
+    },
+    "cohere/embed-v5.0-pro": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048,
+        "supports_embedding_image_input": true,
+        "source": "https://cohere.com/pricing"
+    },
+    "cohere/embed-v5.0-fast": {
+        "input_cost_per_token": 8e-08,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048,
+        "supports_embedding_image_input": true,
+        "source": "https://cohere.com/pricing"
     },
     "cohere/parse-v5.0": {
         "litellm_provider": "cohere",
@@ -15811,11 +17072,12 @@
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 32000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md"
     },
     "command-a-03-2025": {
         "input_cost_per_token": 2.5e-06,
@@ -15896,6 +17158,144 @@
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
+    "coralbricks/glm-5.3-fast": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/glm-5.3-fp4": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/glm-5.3": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/deepseek-v4.1-flash-fast": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "coralbricks/deepseek-v4.1-flash-fast-fp4": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "coralbricks/deepseek-v4.1-flash": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "computer-use-preview": {
         "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
@@ -15926,8 +17326,39 @@
         "supports_vision": true,
         "source": "https://platform.openai.com/docs/models/computer-use-preview"
     },
+    "computer-use-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 1024,
+        "max_tokens": 1024,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://developers.openai.com/api/docs/models/computer-use-preview"
+    },
     "deepseek-chat": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "litellm_provider": "deepseek",
         "max_input_tokens": 131072,
@@ -15949,6 +17380,7 @@
     },
     "deepseek-reasoner": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "litellm_provider": "deepseek",
         "max_input_tokens": 131072,
@@ -16810,7 +18242,9 @@
         ]
     },
     "dashscope/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "dashscope",
         "max_input_tokens": 991808,
@@ -16961,6 +18395,281 @@
             "/v1/images/generations"
         ]
     },
+    "dashscope/wan3.0-video": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.165025,
+        "output_cost_per_second_480p": 0.041256,
+        "output_cost_per_second_720p": 0.082513,
+        "output_cost_per_second_1080p": 0.165025,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan3.0-video-prime": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.254399,
+        "output_cost_per_second_480p": 0.0636,
+        "output_cost_per_second_720p": 0.127199,
+        "output_cost_per_second_1080p": 0.254399,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "qwencloud/deepseek-v4-flash": {
         "cache_read_input_token_cost": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -17802,7 +19511,9 @@
         ]
     },
     "qwencloud/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "qwencloud",
         "max_input_tokens": 991808,
@@ -17913,6 +19624,281 @@
             "/v1/images/generations"
         ]
     },
+    "qwencloud/wan3.0-video": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.2,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.2,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan3.0-video-prime": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.28,
+        "output_cost_per_second_480p": 0.068,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.28,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "qwen_ai_platform/deepseek-v4-flash": {
         "cache_read_input_token_cost": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -18754,7 +20740,9 @@
         ]
     },
     "qwen_ai_platform/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "qwen_ai_platform",
         "max_input_tokens": 991808,
@@ -18905,6 +20893,281 @@
             "/v1/images/generations"
         ]
     },
+    "qwen_ai_platform/wan3.0-video": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.165025,
+        "output_cost_per_second_480p": 0.041256,
+        "output_cost_per_second_720p": 0.082513,
+        "output_cost_per_second_1080p": 0.165025,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan3.0-video-prime": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.254399,
+        "output_cost_per_second_480p": 0.0636,
+        "output_cost_per_second_720p": 0.127199,
+        "output_cost_per_second_1080p": 0.254399,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "databricks/databricks-bge-large-en": {
         "cache_creation_input_token_cost": 1.0003e-07,
         "cache_read_input_token_cost": 1.0003e-07,
@@ -19094,7 +21357,7 @@
         "output_cost_per_token": 2.5000010000000002e-05,
         "output_dbu_cost_per_token": 0.000357143,
         "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_legacy_thinking": true,
         "supports_prompt_caching": true,
@@ -19186,6 +21449,41 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "databricks/databricks-claude-opus-5-5": {
+        "cache_creation_input_token_cost": 5.00003e-06,
+        "cache_creation_input_token_cost_above_1hr": 8.00002e-06,
+        "cache_read_input_token_cost": 1.9999e-07,
+        "input_cost_per_token": 4.00001e-06,
+        "input_dbu_cost_per_token": 5.7143e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "metadata": {
+            "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.999998e-05,
+        "output_dbu_cost_per_token": 0.000285714,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_adaptive_thinking": true,
+        "supports_anthropic_thinking_payload": true,
+        "supports_assistant_prefill": false,
+        "supports_forced_tool_use": false,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_output_config": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true
+    },
     "databricks/databricks-claude-sonnet-4": {
         "cache_creation_input_token_cost": 3.74997e-06,
         "cache_read_input_token_cost": 3.0002e-07,
@@ -19274,7 +21572,7 @@
         "output_cost_per_token": 1.5000020000000002e-05,
         "output_dbu_cost_per_token": 0.000214286,
         "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_legacy_thinking": true,
         "supports_prompt_caching": true,
@@ -19317,6 +21615,7 @@
         "input_cost_per_token": 1.4e-07,
         "input_dbu_cost_per_token": 2e-06,
         "litellm_provider": "databricks",
+        "token_count_framing": 97,
         "max_input_tokens": 1000000,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
@@ -19337,8 +21636,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_vision": false,
-        "token_count_framing": 97
+        "supports_vision": false
     },
     "databricks/system.ai.deepseek-v4-flash-0731": {
         "litellm_provider": "databricks",
@@ -19623,6 +21921,7 @@
         ],
         "supports_function_calling": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19647,6 +21946,7 @@
         ],
         "supports_function_calling": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19678,6 +21978,7 @@
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19741,6 +22042,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -20313,6 +22615,7 @@
         "input_cost_per_token": 2.99999e-06,
         "input_dbu_cost_per_token": 4.2857e-05,
         "litellm_provider": "databricks",
+        "token_count_framing": 100,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1048576,
         "max_tokens": 1048576,
@@ -20334,8 +22637,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 100
+        "supports_vision": true
     },
     "databricks/system.ai.kimi-k3": {
         "litellm_provider": "databricks",
@@ -20463,6 +22765,30 @@
         "output_vector_size": 1024,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
     },
+    "databricks/databricks-openjev-qwen35-4b": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "databricks",
+        "metadata": {
+            "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost."
+        },
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
+    },
+    "databricks/ai_decide": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "databricks",
+        "metadata": {
+            "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it."
+        },
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide"
+    },
     "dataforseo/search": {
         "input_cost_per_query": 0.003,
         "litellm_provider": "dataforseo",
@@ -21844,6 +24170,7 @@
     "deepseek/deepseek-chat": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "input_cost_per_token_cache_hit": 2.8e-08,
         "litellm_provider": "deepseek",
@@ -21898,6 +24225,7 @@
     },
     "deepseek/deepseek-reasoner": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "input_cost_per_token_cache_hit": 2.8e-08,
         "litellm_provider": "deepseek",
@@ -21953,14 +24281,15 @@
         "supports_tool_choice": true
     },
     "deepseek.v3-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 81920,
-        "max_tokens": 81920,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -21968,17 +24297,23 @@
     },
     "deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_batches": 3.1e-07,
+        "input_cost_per_token_flex": 3.1e-07,
+        "input_cost_per_token_priority": 1.085e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 164000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_batches": 9.25e-07,
+        "output_cost_per_token_flex": 9.25e-07,
+        "output_cost_per_token_priority": 3.2375e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -22198,6 +24533,265 @@
         "litellm_provider": "perplexity",
         "mode": "search"
     },
+    "sail/moonshotai/Kimi-K3": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 2.5e-06,
+        "output_cost_per_token": 1.25e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token_balanced": 2e-06,
+        "output_cost_per_token_balanced": 1e-05,
+        "cache_read_input_token_cost_balanced": 2e-07,
+        "input_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_flex": 6.25e-06,
+        "cache_read_input_token_cost_flex": 1.5e-07,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/zai-org/GLM-5.3": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9.8e-07,
+        "output_cost_per_token": 3.08e-06,
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token_balanced": 5e-07,
+        "output_cost_per_token_balanced": 2.5e-06,
+        "cache_read_input_token_cost_balanced": 1.2e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "output_cost_per_token_flex": 1.8e-06,
+        "cache_read_input_token_cost_flex": 8e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/zai-org/GLM-5.3-Flash": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 1.1e-07,
+        "output_cost_per_token": 3.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_balanced": 8e-08,
+        "output_cost_per_token_balanced": 2.8e-07,
+        "cache_read_input_token_cost_balanced": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1.8e-07,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4-Pro-0813": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9.2e-07,
+        "output_cost_per_token": 2.77e-06,
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token_balanced": 7.4e-07,
+        "output_cost_per_token_balanced": 2.22e-06,
+        "cache_read_input_token_cost_balanced": 3e-08,
+        "input_cost_per_token_flex": 4.6e-07,
+        "output_cost_per_token_flex": 1.39e-06,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4-Flash-0731": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 1.8e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_balanced": 7e-08,
+        "output_cost_per_token_balanced": 1.4e-07,
+        "cache_read_input_token_cost_balanced": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 9e-08,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 3e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token_balanced": 7e-08,
+        "output_cost_per_token_balanced": 2.2e-07,
+        "cache_read_input_token_cost_balanced": 5e-09,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1.5e-07,
+        "cache_read_input_token_cost_flex": 4e-09,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/moonshotai/Kimi-K2.6": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1e-06,
+        "output_cost_per_token": 4e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_balanced": 4.5e-07,
+        "output_cost_per_token_balanced": 3e-06,
+        "cache_read_input_token_cost_balanced": 2e-07,
+        "input_cost_per_token_flex": 3.5e-07,
+        "output_cost_per_token_flex": 2e-06,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/google/gemma-4-31B-it": {
+        "max_tokens": 256000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "input_cost_per_token": 4e-07,
+        "output_cost_per_token": 6e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_balanced": 1.2e-07,
+        "output_cost_per_token_balanced": 6e-07,
+        "cache_read_input_token_cost_balanced": 8e-08,
+        "input_cost_per_token_flex": 6e-08,
+        "output_cost_per_token_flex": 3e-07,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/nvidia/Gemma-4-31B-IT-NVFP4": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token_balanced": 1.1e-07,
+        "output_cost_per_token_balanced": 3.2e-07,
+        "cache_read_input_token_cost_balanced": 6e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "output_cost_per_token_flex": 2e-07,
+        "cache_read_input_token_cost_flex": 4e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/google/gemma-4-12B-it": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2e-06,
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token_balanced": 1e-07,
+        "output_cost_per_token_balanced": 2e-06,
+        "cache_read_input_token_cost_balanced": 7e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1e-06,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/openai/gpt-oss-120b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 6e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 3e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/Qwen/Qwen3.6-35B-A3B": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 4e-07,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
     "searxng/search": {
         "litellm_provider": "searxng",
         "mode": "search",
@@ -22231,7 +24825,7 @@
         }
     },
     "agentcore/search": {
-        "input_cost_per_query": 0.0,
+        "input_cost_per_query": 0.007,
         "litellm_provider": "agentcore",
         "mode": "search",
         "metadata": {
@@ -22246,6 +24840,11 @@
             "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment."
         }
     },
+    "deepseek/search": {
+        "input_cost_per_query": 0.00075,
+        "litellm_provider": "deepseek",
+        "mode": "search"
+    },
     "tinyfish/search": {
         "input_cost_per_query": 0.0,
         "litellm_provider": "tinyfish",
@@ -22390,13 +24989,16 @@
     },
     "eu.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.625e-07,
+        "cache_read_input_token_cost_flex": 1.3125e-07,
         "input_cost_per_token": 1.05e-06,
+        "input_cost_per_token_flex": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 4.2e-06,
+        "output_cost_per_token_flex": 2.1e-06,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -22450,7 +25052,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -22547,7 +25153,11 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "deprecation_date": "2027-01-08"
+        "deprecation_date": "2027-01-08",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -22585,7 +25195,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -22606,7 +25216,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.125e-06,
@@ -22618,6 +25232,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -22644,9 +25259,14 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -22654,10 +25274,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "eu.meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -22665,6 +25287,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.9e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -22672,10 +25295,11 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -24984,9 +27608,10 @@
         "output_cost_per_token": 5e-07
     },
     "fireworks-ai-up-to-4b": {
-        "input_cost_per_token": 2e-07,
+        "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "output_cost_per_token": 2e-07
+        "output_cost_per_token": 1e-07,
+        "source": "https://docs.fireworks.ai/serverless/pricing"
     },
     "fireworks_ai/WhereIsAI/UAE-Large-V1": {
         "input_cost_per_token": 1.6e-08,
@@ -25013,7 +27638,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 20480,
         "max_tokens": 20480,
         "mode": "chat",
@@ -25025,7 +27650,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 160000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 160000,
         "max_tokens": 160000,
         "mode": "chat",
@@ -25037,7 +27662,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": {
         "input_cost_per_token": 5.5e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 20480,
         "max_tokens": 20480,
         "mode": "chat",
@@ -25049,7 +27674,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-v3": {
         "input_cost_per_token": 9e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -25182,7 +27807,7 @@
     "fireworks_ai/accounts/fireworks/models/glm-4p5": {
         "input_cost_per_token": 5.5e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 96000,
         "max_tokens": 96000,
         "mode": "chat",
@@ -25196,7 +27821,7 @@
     "fireworks_ai/accounts/fireworks/models/glm-4p5-air": {
         "input_cost_per_token": 2.2e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 96000,
         "max_tokens": 96000,
         "mode": "chat",
@@ -25211,7 +27836,7 @@
         "input_cost_per_token": 5.5e-07,
         "output_cost_per_token": 2.19e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25225,7 +27850,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25240,7 +27865,7 @@
         "cache_read_input_token_cost": 2.6e-07,
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
@@ -25275,6 +27900,7 @@
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
         "cache_read_input_token_cost_priority": 1.8e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
@@ -25284,7 +27910,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_priority": 7.2e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -25404,7 +28030,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25417,7 +28043,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25430,7 +28056,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
         "input_cost_per_token": 2e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25444,7 +28070,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25457,7 +28083,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25470,7 +28096,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
         "input_cost_per_token": 9e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25508,7 +28134,7 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 204800,
         "max_tokens": 204800,
         "mode": "chat",
@@ -25609,7 +28235,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25624,7 +28250,7 @@
         "cache_read_input_token_cost": 2.6e-07,
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
@@ -25675,6 +28301,7 @@
     "fireworks_ai/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
         "cache_read_input_token_cost_priority": 1.8e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
@@ -25684,7 +28311,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_priority": 7.2e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -25799,7 +28426,7 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 204800,
         "max_tokens": 204800,
         "mode": "chat",
@@ -26152,6 +28779,7 @@
     "ft:gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.875e-06,
         "cache_read_input_token_cost_batches": 9e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3.75e-06,
         "input_cost_per_token_batches": 2.225e-06,
         "litellm_provider": "openai",
@@ -26173,6 +28801,7 @@
     },
     "ft:gpt-4o-2024-11-20": {
         "cache_creation_input_token_cost": 1.875e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3.75e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -26191,6 +28820,7 @@
     "ft:gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 1.5e-07,
         "cache_read_input_token_cost_batches": 7.5e-08,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "litellm_provider": "openai",
@@ -26212,6 +28842,7 @@
     "ft:gpt-4.1-2025-04-14": {
         "cache_read_input_token_cost": 7.5e-07,
         "cache_read_input_token_cost_batches": 5e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "openai",
@@ -26232,6 +28863,7 @@
     "ft:gpt-4.1-mini-2025-04-14": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_batches": 1e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 8e-07,
         "input_cost_per_token_batches": 4e-07,
         "litellm_provider": "openai",
@@ -26371,7 +29003,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26429,7 +29062,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26481,7 +29115,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26510,11 +29145,13 @@
         "cache_read_input_token_cost": 5e-08,
         "cache_read_input_token_cost_batches": 2.5e-08,
         "cache_read_input_token_cost_flex": 2.5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -26525,10 +29162,12 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26571,7 +29210,8 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26600,10 +29240,13 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_batches": 1.25e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-06-28",
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -26614,10 +29257,12 @@
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.7e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26794,6 +29439,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -26820,7 +29466,7 @@
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
-        "mode": "image_generation",
+        "mode": "chat",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
@@ -27043,7 +29689,8 @@
             "search_context_size_high": 0.035
         },
         "gemini_native_audio": true,
-        "input_cost_per_image_token": 3e-06
+        "input_cost_per_image_token": 3e-06,
+        "input_cost_per_video_token": 3e-06
     },
     "gemini-live-2.5-flash-preview-native-audio-09-2025": {
         "input_cost_per_audio_token": 3e-06,
@@ -27194,22 +29841,32 @@
         "output_cost_per_token_priority": 1.8e-05
     },
     "gemini-3.1-pro-preview": {
-        "prompt_cache_min_tokens": 4096,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
+        "output_cost_per_image": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "output_cost_per_image": 0.00012,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27228,33 +29885,18 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_url_context": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 3.6e-06,
-        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
-        "output_cost_per_token_priority": 2.16e-05,
-        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
-        "cache_read_input_token_cost_priority": 3.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
-        "cache_read_input_token_cost_flex": 2e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_token_flex": 1e-06,
-        "output_cost_per_token_flex": 6e-06
+        "web_search_billing_unit": "per_query"
     },
     "gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -27369,15 +30011,25 @@
     "vertex_ai/gemini-3-flash-preview": {
         "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
-        "cache_read_input_token_cost_flex": 5e-08,
-        "input_cost_per_token": 5e-07,
+        "cache_read_input_token_cost_priority": 9e-08,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
+        "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
         "max_tokens": 65535,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27396,6 +30048,7 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -27405,23 +30058,7 @@
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 9e-07,
-        "input_cost_per_audio_token_priority": 1.8e-06,
-        "output_cost_per_token_priority": 5.4e-06,
-        "cache_read_input_token_cost_priority": 9e-08,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 5e-07,
-        "input_cost_per_token_batches": 2.5e-07,
-        "input_cost_per_token_flex": 2.5e-07,
-        "output_cost_per_token_batches": 1.5e-06,
-        "output_cost_per_token_flex": 1.5e-06
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.5-flash": {
         "prompt_cache_min_tokens": 4096,
@@ -27525,6 +30162,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -27535,6 +30173,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2026-11-19",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -27585,6 +30224,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -27595,6 +30235,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2027-01-28",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -27605,13 +30246,15 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/gemini-3.8-flash": {
-        "prompt_cache_min_tokens": 4096,
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_batches": 3.75e-08,
         "cache_read_input_token_cost_flex": 3.75e-08,
+        "cache_read_input_token_cost_priority": 1.35e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 7.5e-07,
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_priority": 1.35e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -27621,7 +30264,10 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "prompt_cache_min_tokens": 4096.0,
         "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27640,29 +30286,21 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 1.35e-06,
-        "output_cost_per_token_priority": 6.75e-06,
-        "cache_read_input_token_cost_priority": 1.35e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.8-flash-cyber": {
         "cache_read_input_token_cost": 1.5e-07,
@@ -27705,6 +30343,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": false,
         "supports_url_context": false,
@@ -27714,6 +30353,7 @@
         "supports_native_streaming": true
     },
     "vertex_ai/gemini-3.8-live": {
+        "gemini_audio_only_live": true,
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -27726,7 +30366,8 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 4.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "output_cost_per_video_token": 1e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/vertex_ai/live",
             "/v1/realtime"
@@ -27746,26 +30387,35 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true,
-        "gemini_audio_only_live": true
+        "supports_web_search": true
     },
     "vertex_ai/gemini-3.1-pro-preview": {
-        "prompt_cache_min_tokens": 4096,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
+        "output_cost_per_image": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "output_cost_per_image": 0.00012,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27784,33 +30434,18 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_url_context": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 3.6e-06,
-        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
-        "output_cost_per_token_priority": 2.16e-05,
-        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
-        "cache_read_input_token_cost_priority": 3.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
-        "cache_read_input_token_cost_flex": 2e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_token_flex": 1e-06,
-        "output_cost_per_token_flex": 6e-06
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -27953,7 +30588,7 @@
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
-        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_reasoning_token": 5e-06,
         "output_cost_per_token": 5e-06,
         "output_cost_per_token_batches": 2.5e-06,
         "search_context_cost_per_query": {
@@ -28174,8 +30809,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28218,8 +30853,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28334,7 +30969,7 @@
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 131072,
+        "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -28371,7 +31006,7 @@
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 131072,
+        "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -28456,6 +31091,7 @@
         "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"},
         "google_maps_grounding_cost_per_query": 0.025,
         "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
         "input_cost_per_token_priority": 5.4e-07,
@@ -28467,7 +31103,7 @@
     },
     "gemini/gemini-2.5-flash-image": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-02",
+        "deprecation_date": "2027-03-15",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
@@ -28487,8 +31123,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28533,6 +31169,7 @@
         "mode": "image_generation",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
+        "output_cost_per_image_token_batches": 6e-05,
         "output_cost_per_token": 1.2e-05,
         "rpm": 1000,
         "tpm": 4000000,
@@ -28542,8 +31179,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28554,7 +31191,7 @@
             "image"
         ],
         "supports_function_calling": false,
-        "supports_prompt_caching": true,
+        "supports_prompt_caching": false,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
@@ -28566,7 +31203,7 @@
         },
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "web_search_billing_unit": "per_query",
-        "supports_reasoning": false
+        "supports_reasoning": true
     },
     "gemini/nano-banana-pro-preview": {
         "input_cost_per_image": 0.0011,
@@ -28590,8 +31227,7 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28625,16 +31261,17 @@
         "mode": "image_generation",
         "output_cost_per_image": 0.045,
         "output_cost_per_image_token": 6e-05,
+        "output_cost_per_image_token_batches": 3e-05,
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
-        "rpm": 1000,
-        "tpm": 4000000,
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28645,17 +31282,14 @@
             "image"
         ],
         "supports_function_calling": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
+        "tpm": 4000000.0,
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-3.1-flash-lite-image": {
@@ -28675,8 +31309,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28687,8 +31321,9 @@
             "image"
         ],
         "supports_function_calling": false,
+        "supports_pdf_input": true,
         "supports_prompt_caching": false,
-        "supports_reasoning": false,
+        "supports_reasoning": true,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
@@ -28696,21 +31331,20 @@
         "tpm": 4000000
     },
     "gemini/deep-research-pro-preview-12-2025": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "image_generation",
-        "output_cost_per_image": 0.134,
-        "output_cost_per_image_token": 0.00012,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "rpm": 1000,
-        "tpm": 4000000,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035},
+        "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -28718,23 +31352,21 @@
         ],
         "supported_modalities": [
             "text",
-            "image"
+            "image",
+            "audio",
+            "video"
         ],
         "supported_output_modalities": [
-            "text",
-            "image"
+            "text"
         ],
         "supports_function_calling": false,
+        "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.035,
-            "search_context_size_medium": 0.035,
-            "search_context_size_high": 0.035
-        }
+        "tpm": 4000000.0
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_audio_token_cost": 3e-08,
@@ -28788,6 +31420,7 @@
         "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"},
         "google_maps_grounding_cost_per_query": 0.025,
         "input_cost_per_audio_token_batches": 1.5e-07,
+        "input_cost_per_audio_token_priority": 5.4e-07,
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_flex": 5e-08,
         "input_cost_per_token_priority": 1.8e-07,
@@ -28915,6 +31548,7 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-2.5-flash-preview-tts": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "gemini",
@@ -28994,9 +31628,11 @@
         "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "output_cost_per_token_batches": 5e-06,
-        "output_cost_per_token_flex": 5e-06
+        "output_cost_per_token_flex": 5e-06,
+        "supports_url_context": true
     },
     "gemini/gemini-2.5-computer-use-preview-10-2025": {
+        "deprecation_date": "2026-07-28",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "gemini",
@@ -29088,7 +31724,8 @@
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "web_search_billing_unit": "per_query",
         "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 2.5e-07
+        "input_cost_per_audio_token_batches": 2.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07
     },
     "gemini/gemini-3.5-flash-lite": {
         "cache_read_input_token_cost": 3e-08,
@@ -29133,6 +31770,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29317,6 +31955,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29379,6 +32018,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29441,6 +32081,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29493,7 +32134,7 @@
         "supports_video_input": true,
         "supports_vision": true,
         "tpm": 800000,
-        "deprecation_date": "2026-09-30"
+        "deprecation_date": "2026-10-22"
     },
     "gemini/gemini-3.1-pro-preview": {
         "prompt_cache_min_tokens": 4096,
@@ -29626,9 +32267,15 @@
     "gemini-3-flash-preview": {
         "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
-        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
@@ -29636,6 +32283,10 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 3e-06,
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -29654,6 +32305,7 @@
         ],
         "supports_audio_output": false,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -29664,23 +32316,7 @@
         "supports_url_context": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 9e-07,
-        "input_cost_per_audio_token_priority": 1.8e-06,
-        "output_cost_per_token_priority": 5.4e-06,
-        "cache_read_input_token_cost_priority": 9e-08,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 5e-07,
-        "input_cost_per_token_batches": 2.5e-07,
-        "input_cost_per_token_flex": 2.5e-07,
-        "output_cost_per_token_batches": 1.5e-06,
-        "output_cost_per_token_flex": 1.5e-06
+        "web_search_billing_unit": "per_query"
     },
     "gemini-omni-flash-preview": {
         "input_cost_per_audio_token": 1.5e-06,
@@ -29815,6 +32451,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29825,6 +32462,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2026-11-19",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -29875,6 +32513,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29885,6 +32524,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2027-01-28",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -29895,13 +32535,15 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3.8-flash": {
-        "prompt_cache_min_tokens": 4096,
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_batches": 3.75e-08,
         "cache_read_input_token_cost_flex": 3.75e-08,
+        "cache_read_input_token_cost_priority": 1.35e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 7.5e-07,
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_priority": 1.35e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -29911,6 +32553,9 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -29927,32 +32572,24 @@
         "supported_output_modalities": [
             "text"
         ],
-        "supports_audio_output": false,
         "supports_audio_input": true,
+        "supports_audio_output": false,
         "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 1.35e-06,
-        "output_cost_per_token_priority": 6.75e-06,
-        "cache_read_input_token_cost_priority": 1.35e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "web_search_billing_unit": "per_query"
     },
     "gemini-3.8-flash-cyber": {
         "cache_read_input_token_cost": 1.5e-07,
@@ -29995,6 +32632,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": false,
         "supports_url_context": false,
@@ -30005,6 +32643,7 @@
     },
     "gemini/gemini-2.5-pro-preview-tts": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-06,
         "input_cost_per_token_batches": 5e-07,
@@ -30265,6 +32904,7 @@
         "output_cost_per_image": 0.08
     },
     "gemini/veo-3.1-fast-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30281,6 +32921,7 @@
         ]
     },
     "gemini/veo-3.1-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30296,6 +32937,7 @@
         ]
     },
     "gemini/veo-3.1-lite-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30341,83 +32983,270 @@
             "video"
         ]
     },
-    "github_copilot/claude-haiku-4.5": {
+    "github_copilot/claude-fable-5": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
         "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
-            "/v1/chat/completions"
+            "/v1/chat/completions",
+            "/v1/messages"
         ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_vision": true
-    },
-    "github_copilot/claude-opus-4.5": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_vision": true,
-        "supports_output_config": true
-    },
-    "github_copilot/claude-opus-4.6-fast": {
         "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-fable-5.1": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-haiku-4.5": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token": 5e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
         "supports_vision": true
     },
-    "github_copilot/claude-opus-41": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 80000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_vision": true
-    },
-    "github_copilot/claude-sonnet-4": {
+    "github_copilot/claude-haiku-5.5": {
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_above_100k_tokens": 5e-07,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
-            "/v1/chat/completions"
+            "/v1/chat/completions",
+            "/v1/messages"
         ],
+        "supports_adaptive_thinking": true,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": false
+    },
+    "github_copilot/claude-opus-4.8": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
         "supports_vision": true
     },
-    "github_copilot/claude-sonnet-4.5": {
+    "github_copilot/claude-opus-4.8-fast": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
         "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-opus-5": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-opus-5.5": {
+        "cache_creation_input_token_cost": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-sonnet-5": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-sonnet-5.5": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/gemini-3.7-flash": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.75e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
+        "supports_vision": true
+    },
+    "github_copilot/gemini-3.8-flash": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 3.75e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_vision": true
     },
     "github_copilot/gpt-3.5-turbo": {
@@ -30462,22 +33291,26 @@
         "supports_parallel_function_calling": true
     },
     "github_copilot/gpt-4.1": {
+        "deprecation_date": "2026-06-01",
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
         "supports_vision": true
     },
     "github_copilot/gpt-4.1-2025-04-14": {
+        "deprecation_date": "2026-06-01",
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -30544,82 +33377,304 @@
         "supports_function_calling": true,
         "supports_parallel_function_calling": true
     },
-    "github_copilot/gpt-5": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
     "github_copilot/gpt-5-mini": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2.5e-07,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.1": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.1-codex-max": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "responses",
-        "supported_endpoints": [
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.2": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
+        "output_cost_per_token": 2e-06,
+        "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
         "supports_vision": true
     },
     "github_copilot/gpt-5.3-codex": {
+        "cache_read_input_token_cost": 1.75e-07,
+        "input_cost_per_token": 1.75e-06,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "output_cost_per_token": 1.4e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4-mini": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 4.5e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 5e-06,
+        "input_cost_per_token_above_272k_tokens": 1e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 3e-05,
+        "output_cost_per_token_above_272k_tokens": 4.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.5e-07,
+        "cache_creation_input_token_cost_above_200k_tokens": 5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_200k_tokens": 4e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_200k_tokens": 1.8e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 8e-07,
+        "input_cost_per_token": 4e-06,
+        "input_cost_per_token_above_272k_tokens": 8e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-05,
+        "output_cost_per_token_above_272k_tokens": 3e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-astra": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "input_cost_per_token": 1e-05,
+        "input_cost_per_token_above_272k_tokens": 2e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 5e-05,
+        "output_cost_per_token_above_272k_tokens": 7.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-luna": {
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_above_272k_tokens": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/kimi-k3": {
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 917504,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/mai-code-1.1-flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
             "/v1/responses"
         ],
@@ -30628,38 +33683,6 @@
         "supports_response_schema": true,
         "supports_vision": true
     },
-    "github_copilot/mai-code-1-flash": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true
-    },
-    "github_copilot/mai-code-1-flash-internal": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true
-    },
     "github_copilot/text-embedding-3-small": {
         "litellm_provider": "github_copilot",
         "max_input_tokens": 8191,
@@ -30678,6 +33701,90 @@
         "max_tokens": 8191,
         "mode": "embedding"
     },
+    "chatgpt/gpt-6-sol": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6-luna": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6-astra": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6.1-sol": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "chatgpt/gpt-5.5": {
         "litellm_provider": "chatgpt",
         "source": "https://platform.openai.com/docs/models/gpt-5.5",
@@ -30810,9 +33917,9 @@
         "supports_response_schema": true,
         "supports_vision": true,
         "supports_reasoning": true,
-        "supports_none_reasoning_effort": false,
-        "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": true
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
     },
     "chatgpt/gpt-5.3-codex-spark": {
         "litellm_provider": "chatgpt",
@@ -31143,24 +34250,28 @@
         "output_cost_per_token": 1.2e-06
     },
     "baseten/MiniMaxAI/MiniMax-M2.5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 1.2e-06
     },
     "baseten/nvidia/Nemotron-120B-A12B": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 7.5e-07
     },
     "baseten/zai-org/GLM-5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 3.15e-06
     },
     "baseten/zai-org/GLM-4.7": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.2e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
@@ -31178,24 +34289,28 @@
         "supports_vision": false
     },
     "baseten/zai-org/GLM-4.6": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 2.2e-06
     },
     "baseten/moonshotai/Kimi-K2.5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 3e-06
     },
     "baseten/moonshotai/Kimi-K2-Thinking": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 2.5e-06
     },
     "baseten/moonshotai/Kimi-K2-Instruct-0905": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
@@ -31219,12 +34334,14 @@
         "supports_vision": false
     },
     "baseten/deepseek-ai/DeepSeek-V3.1": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 1.5e-06
     },
     "baseten/deepseek-ai/DeepSeek-V3-0324": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 7.7e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
@@ -31250,14 +34367,21 @@
         "output_cost_per_token": 2e-06
     },
     "google.gemma-3-12b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 9e-08,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.9e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -31265,14 +34389,21 @@
         "supports_vision": true
     },
     "google.gemma-3-27b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.3e-07,
+        "input_cost_per_token_batches": 1.2e-07,
+        "input_cost_per_token_flex": 1.2e-07,
+        "input_cost_per_token_priority": 4e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 3.8e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.9e-07,
+        "output_cost_per_token_flex": 1.9e-07,
+        "output_cost_per_token_priority": 6.7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -31280,14 +34411,21 @@
         "supports_vision": true
     },
     "google.gemma-3-4b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 8e-08,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 4e-08,
+        "output_cost_per_token_flex": 4e-08,
+        "output_cost_per_token_priority": 1.4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -31308,6 +34446,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -31334,7 +34473,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -31346,7 +34489,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -31367,7 +34510,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.25e-06,
@@ -31395,17 +34542,27 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5e-07,
-        "output_cost_per_token_batches": 2.5e-06
+        "output_cost_per_token_batches": 2.5e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_priority": 1.3125e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -31628,6 +34785,7 @@
     "gpt-4.1-2025-04-14": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -31714,6 +34872,7 @@
     "gpt-4.1-mini-2025-04-14": {
         "cache_read_input_token_cost": 1e-07,
         "cache_read_input_token_cost_priority": 1.75e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 4e-07,
         "input_cost_per_token_priority": 7e-07,
         "input_cost_per_token_batches": 2e-07,
@@ -31879,6 +35038,7 @@
     "gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.25e-06,
         "cache_read_input_token_cost_priority": 2.125e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_priority": 4.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
@@ -31903,6 +35063,7 @@
     "gpt-4o-2024-11-20": {
         "cache_read_input_token_cost": 1.25e-06,
         "cache_read_input_token_cost_priority": 2.125e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_priority": 4.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
@@ -32108,6 +35269,44 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2026-07-23",
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/realtime",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "gpt-audio-mini-2025-12-15": {
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
@@ -32178,6 +35377,7 @@
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_priority": 1.25e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 2.5e-07,
         "input_cost_per_token_batches": 7.5e-08,
@@ -32268,6 +35468,34 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "gpt-4o-mini-search-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        },
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview"
+    },
     "gpt-4o-mini-transcribe": {
         "input_cost_per_audio_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
@@ -32302,6 +35530,26 @@
             "audio"
         ]
     },
+    "gpt-4o-mini-tts-2025-03-20": {
+        "deprecation_date": "2027-01-06",
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_second": 0.00025,
+        "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ]
+    },
     "gpt-4o-search-preview": {
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
@@ -32328,6 +35576,34 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "gpt-4o-search-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_batches": 1.25e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        },
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview"
+    },
     "gpt-4o-transcribe": {
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
@@ -32423,10 +35699,13 @@
     "gpt-image-2.5-flare": {
         "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost_batches": 6.25e-07,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_image_token_batches": 4e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
         "supported_endpoints": [
             "/v1/images/generations",
@@ -32455,10 +35734,13 @@
     "gpt-image-2.5-sunburst": {
         "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost_batches": 6.25e-07,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_image_token_batches": 4e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
         "supported_endpoints": [
             "/v1/images/generations",
@@ -32977,7 +36259,8 @@
         "output_cost_per_token_flex": 5e-06,
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": false
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.1-codex-mini": {
         "cache_read_input_token_cost": 2.5e-08,
@@ -33199,6 +36482,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -33316,6 +36600,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -33427,16 +36712,22 @@
         "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
         "cache_creation_input_token_cost_batches": 6.25e-06,
         "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
+        "cache_creation_input_token_cost_ultrafast": 7.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
         "cache_read_input_token_cost_flex": 5e-07,
         "cache_read_input_token_cost_priority": 2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-06,
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_above_272k_tokens": 2e-05,
         "input_cost_per_token_above_272k_tokens_flex": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 4e-05,
         "input_cost_per_token_batches": 5e-06,
         "input_cost_per_token_above_272k_tokens_batches": 1e-05,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
         "input_cost_per_token_flex": 5e-06,
         "input_cost_per_token_priority": 2e-05,
+        "input_cost_per_token_ultrafast": 6e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -33448,8 +36739,10 @@
         "output_cost_per_token_above_272k_tokens_priority": 0.00015,
         "output_cost_per_token_batches": 2.5e-05,
         "output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
         "output_cost_per_token_flex": 2.5e-05,
         "output_cost_per_token_priority": 0.0001,
+        "output_cost_per_token_ultrafast": 0.0003,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -33484,6 +36777,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33560,19 +36854,24 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
     "gpt-6-luna": {
         "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_decisions": 1e-07,
         "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_decisions": 2e-07,
         "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07,
         "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07,
         "cache_creation_input_token_cost_flex": 6.25e-08,
         "cache_creation_input_token_cost_priority": 2.5e-07,
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_decisions": 1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08,
         "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08,
         "cache_read_input_token_cost_batches": 5e-09,
@@ -33582,7 +36881,9 @@
         "cache_read_input_token_cost_flex": 5e-09,
         "cache_read_input_token_cost_priority": 2e-08,
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_decisions": 1e-07,
         "input_cost_per_token_above_272k_tokens": 2e-07,
+        "input_cost_per_token_above_272k_tokens_decisions": 2e-07,
         "input_cost_per_token_above_272k_tokens_flex": 1e-07,
         "input_cost_per_token_above_272k_tokens_priority": 4e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -33595,7 +36896,9 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
+        "output_cost_per_token_decisions": 0.0,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "output_cost_per_token_above_272k_tokens_decisions": 0.0,
         "output_cost_per_token_above_272k_tokens_flex": 3.75e-07,
         "output_cost_per_token_above_272k_tokens_priority": 1.5e-06,
         "output_cost_per_token_batches": 2.5e-07,
@@ -33637,6 +36940,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33710,6 +37014,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33785,6 +37090,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33859,6 +37165,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33933,6 +37240,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -34218,6 +37526,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34280,6 +37589,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34334,6 +37644,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34385,6 +37696,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34439,6 +37751,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
@@ -34496,6 +37809,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
@@ -34549,6 +37863,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34601,6 +37916,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34656,6 +37972,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34710,6 +38027,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34767,7 +38085,8 @@
         "default_reasoning_effort": "none",
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
-        "supports_minimal_reasoning_effort": false
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
@@ -35062,11 +38381,13 @@
         "supports_response_schema": true,
         "supports_system_messages": false,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_none_reasoning_effort": false,
-        "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": true
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.3-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
@@ -36446,6 +39767,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -36472,7 +39794,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.375e-06,
@@ -36500,7 +39826,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "crusoe/deepseek-ai/DeepSeek-R1-0528": {
         "input_cost_per_token": 3e-06,
@@ -36625,6 +39955,736 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
+    "inferenceapis/deepseek-ai/DeepSeek-V3": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-chat": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-reasoner": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v3": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4-flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4-pro": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4.1-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/glm-5.3": {
+        "cache_read_input_token_cost": 3.4e-07,
+        "input_cost_per_token": 1.82e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5.72e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/glm-5.3-flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/gpt-oss-120b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/gpt-oss-20b": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.9e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/kimi-k2.7-code": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 8.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4.42e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.1-8b-instant": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b-instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b-versatile": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/minimax-m3": {
+        "cache_read_input_token_cost": 8e-08,
+        "input_cost_per_token": 3.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/MiniMaxAI/MiniMax-M3": {
+        "cache_read_input_token_cost": 8e-08,
+        "input_cost_per_token": 3.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/moonshotai/Kimi-K2.7-Code": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 8.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4.42e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/openai/gpt-oss-120b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/openai/gpt-oss-20b": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.9e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/Qwen/Qwen3.8-Flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/qwen3-vl": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/qwen3-vl-235b": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/qwen3.8-flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/zai-org/GLM-5.3": {
+        "cache_read_input_token_cost": 3.4e-07,
+        "input_cost_per_token": 1.82e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5.72e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/zai-org/GLM-5.3-Flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "text-completion-inception/mercury-edit-2": {
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 2.5e-07,
@@ -37077,51 +41137,64 @@
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "meta.llama3-1-405b-instruct-v1:0": {
-        "input_cost_per_token": 5.32e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 2.4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.6e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-1-70b-instruct-v1:0": {
-        "input_cost_per_token": 9.9e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 9.9e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "meta.llama3-1-8b-instruct-v1:0": {
-        "input_cost_per_token": 2.2e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "meta.llama3-2-11b-instruct-v1:0": {
-        "input_cost_per_token": 3.5e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "meta.llama3-1-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-07,
+        "output_cost_per_token_batches": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "meta.llama3-2-11b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 1.6e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -37129,10 +41202,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -37140,60 +41215,73 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-2-90b-instruct-v1:0": {
-        "input_cost_per_token": 2e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 2e-06,
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "meta.llama3-3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "meta.llama4-maverick-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "input_cost_per_token_batches": 1.2e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
         "output_cost_per_token_batches": 4.85e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -37206,15 +41294,17 @@
         "supports_tool_choice": false
     },
     "meta.llama4-scout-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.7e-07,
         "input_cost_per_token_batches": 8.5e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 10000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
         "output_cost_per_token_batches": 3.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -37447,6 +41537,49 @@
         ],
         "supports_audio_input": true
     },
+    "meta/muse-wonder-1.0": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "meta",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 2e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.0025,
+            "search_context_size_low": 0.0025,
+            "search_context_size_medium": 0.0025
+        },
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "meta_llama/Llama-3.3-70B-Instruct": {
         "litellm_provider": "meta_llama",
         "max_input_tokens": 128000,
@@ -37514,14 +41647,21 @@
         "supports_tool_choice": true
     },
     "minimax.minimax-m2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37530,33 +41670,46 @@
         "supports_vision": false
     },
     "minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 196000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 196000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -37686,31 +41839,96 @@
         "max_input_tokens": 1000000,
         "max_output_tokens": 128000
     },
+    "minimax/MiniMax-H3": {
+        "litellm_provider": "minimax",
+        "mode": "video_generation",
+        "source": "https://platform.minimax.io/docs/guides/pricing-paygo",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_768p": 0.08,
+        "output_cost_per_second_2k": 0.13,
+        "input_cost_per_image": 0.04,
+        "provider_specific_entry": {
+            "minimax_free_input_images": 5
+        },
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "metadata": {
+            "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call."
+        }
+    },
+    "minimax/MiniMax-H3-Max": {
+        "litellm_provider": "minimax",
+        "mode": "video_generation",
+        "source": "https://platform.minimax.io/docs/guides/pricing-paygo",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_768p": 0.08,
+        "input_cost_per_image": 0.074,
+        "provider_specific_entry": {
+            "minimax_free_input_images": 2
+        },
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "metadata": {
+            "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call."
+        }
+    },
     "mistral.devstral-2-123b": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-07,
+        "input_cost_per_token_batches": 2e-07,
+        "input_cost_per_token_flex": 2e-07,
+        "input_cost_per_token_priority": 7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
+        "output_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_priority": 3.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "mistral.magistral-small-2509": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 40000,
         "max_tokens": 40000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.63e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -37720,13 +41938,19 @@
     },
     "mistral.ministral-3-14b-instruct": {
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_priority": 3.5e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_flex": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37736,13 +41960,19 @@
     },
     "mistral.ministral-3-3b-instruct": {
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 5e-08,
+        "output_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_priority": 1.7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37752,13 +41982,19 @@
     },
     "mistral.ministral-3-8b-instruct": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7e-08,
+        "output_cost_per_token_flex": 7e-08,
+        "output_cost_per_token_priority": 2.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37767,47 +42003,55 @@
         "supports_vision": true
     },
     "mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "mistral.mistral-large-2407-v1:0": {
-        "input_cost_per_token": 3e-06,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_token": 9e-06,
+        "output_cost_per_token": 6e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "mistral.mistral-large-3-675b-instruct": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.63e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37820,47 +42064,62 @@
         "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md",
         "supports_function_calling": true
     },
     "mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "mistral.voxtral-mini-3b-2507": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 32768,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 4e-08,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 2e-08,
+        "output_cost_per_token_flex": 2e-08,
+        "output_cost_per_token_priority": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": true,
         "supports_system_messages": true,
         "supports_native_structured_output": true
     },
     "mistral.voxtral-small-24b-2507": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.7e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 32768,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": true,
         "supports_system_messages": true,
         "supports_native_structured_output": true
@@ -38080,7 +42339,6 @@
     },
     "mistral/voxtral-small-2507": {
         "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_second": 6.666666666666667e-05,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "mistral",
         "max_input_tokens": 32768,
@@ -38096,7 +42354,6 @@
     },
     "mistral/voxtral-small-latest": {
         "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_second": 6.666666666666667e-05,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "mistral",
         "max_input_tokens": 32768,
@@ -38112,6 +42369,7 @@
     },
     "mistral/zai-glm-5-2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-10-31",
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "mistral",
         "max_input_tokens": 1048576,
@@ -38242,6 +42500,7 @@
         "source": "https://mistral.ai/pricing#api-pricing"
     },
     "mistral/mistral-ocr-4-0": {
+        "deprecation_date": "2026-09-30",
         "litellm_provider": "mistral",
         "ocr_cost_per_page": 0.004,
         "ocr_cost_per_page_batches": 0.002,
@@ -38337,6 +42596,48 @@
         "max_tokens": 8192,
         "mode": "embedding"
     },
+    "mistral/mistral-large-4": {
+        "cache_read_input_token_cost": 6.8e-08,
+        "input_cost_per_token": 6.8e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 2.09e-06,
+        "reasoning_effort_levels": [
+            "none",
+            "high"
+        ],
+        "source": "https://docs.mistral.ai/models/mistral-large-4",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "mistral/mistral-large-4-0": {
+        "cache_read_input_token_cost": 6.8e-08,
+        "input_cost_per_token": 6.8e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 2.09e-06,
+        "reasoning_effort_levels": [
+            "none",
+            "high"
+        ],
+        "source": "https://docs.mistral.ai/models/mistral-large-4",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "mistral/mistral-large-latest": {
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 5e-07,
@@ -38627,14 +42928,19 @@
         "supports_vision": true
     },
     "moonshot.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.38e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -38645,17 +42951,23 @@
     },
     "moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.25e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true
     },
@@ -39388,6 +43700,7 @@
     "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": {
         "input_cost_per_token": 1.32e-06,
         "litellm_provider": "nebius",
+        "max_input_tokens": 979000,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813",
@@ -39397,12 +43710,14 @@
     "nebius/deepseek-ai/DeepSeek-V4.1-Flash": {
         "input_cost_per_token": 3e-07,
         "litellm_provider": "nebius",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 1048576,
-        "max_tokens": 1048576,
+        "max_input_tokens": 1048000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
         "supports_vision": true
     },
     "nebius/MiniMaxAI/MiniMax-M2.5": {
@@ -39647,6 +43962,16 @@
         "supports_reasoning": true,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B"
     },
+    "nebius/Qwen/Qwen3.8-27B": {
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "nebius",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 3e-06,
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "nebius/zai-org/GLM-5.1": {
         "max_tokens": 202752,
         "max_input_tokens": 202752,
@@ -39674,8 +43999,8 @@
     "nebius/zai-org/GLM-5.3": {
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "nebius",
-        "max_input_tokens": 1048576,
-        "max_tokens": 1048576,
+        "max_input_tokens": 1024000,
+        "max_tokens": 1024000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3",
@@ -39692,7 +44017,8 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_reasoning": true,
-        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash"
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash",
+        "supports_vision": true
     },
     "nebius/BAAI/bge-en-icl": {
         "max_tokens": 32768,
@@ -39731,14 +44057,21 @@
         "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B"
     },
     "nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_priority": 3.5e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -39746,14 +44079,21 @@
         "supports_vision": true
     },
     "nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.2e-07,
+        "output_cost_per_token_flex": 1.2e-07,
+        "output_cost_per_token_priority": 4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -39762,16 +44102,22 @@
     },
     "nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "output_cost_per_token_flex": 1.2e-07,
+        "output_cost_per_token_priority": 4.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_native_structured_output": true,
         "supports_response_schema": true,
@@ -39779,13 +44125,19 @@
     },
     "nvidia.nemotron-super-3-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 6.5e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3.25e-07,
+        "output_cost_per_token_flex": 3.25e-07,
+        "output_cost_per_token_priority": 1.1375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -39955,6 +44307,39 @@
         "supports_web_search": true
     },
     "o3-deep-research": {
+        "cache_read_input_token_cost": 2.5e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "openai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "responses",
+        "output_cost_per_token": 4e-05,
+        "source": "https://developers.openai.com/api/docs/models/o3-deep-research",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "deprecation_date": "2026-07-23"
+    },
+    "o3-deep-research-2025-06-26": {
+        "deprecation_date": "2026-07-23",
         "cache_read_input_token_cost": 2.5e-06,
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
@@ -40184,6 +44569,39 @@
         "supports_web_search": true
     },
     "o4-mini-deep-research": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "responses",
+        "output_cost_per_token": 8e-06,
+        "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "deprecation_date": "2026-07-23"
+    },
+    "o4-mini-deep-research-2025-06-26": {
+        "deprecation_date": "2026-07-23",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "openai",
@@ -40658,6 +45076,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "reasoning_effort_levels": [],
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
         "supports_function_calling": true,
         "supports_response_schema": false
@@ -40674,6 +45093,72 @@
         "supports_function_calling": true,
         "supports_response_schema": false
     },
+    "oci/xai.grok-4.20-0309-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true
+    },
+    "oci/xai.grok-4.20-0309-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "oci/xai.grok-4.20-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true
+    },
+    "oci/xai.grok-4.20-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "oci/xai.grok-code-fast-1": {
         "input_cost_per_token": 5e-06,
         "litellm_provider": "oci",
@@ -40731,6 +45216,32 @@
         "supports_response_schema": true,
         "supports_vision": true
     },
+    "oci/openai.gpt-oss-120b": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true
+    },
+    "oci/openai.gpt-oss-20b": {
+        "input_cost_per_token": 7e-08,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3e-07,
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true
+    },
     "oci/cohere.embed-english-v3.0": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "oci",
@@ -41112,28 +45623,50 @@
         "output_cost_per_token": 0.0
     },
     "openai.gpt-oss-120b-1:0": {
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
     "openai.gpt-oss-20b-1:0": {
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.25e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -41141,14 +45674,21 @@
     },
     "openai.gpt-oss-safeguard-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -41156,2303 +45696,26 @@
     },
     "openai.gpt-oss-safeguard-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_flex": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_vision": false
     },
-    "openrouter/anthropic/claude-3-haiku": {
-        "cache_creation_input_token_cost": 3e-07,
-        "cache_creation_input_token_cost_above_1hr": 5e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_image": 0.0004,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "max_input_tokens": 200000,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-3.5-sonnet": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/anthropic/claude-3.7-sonnet": {
-        "input_cost_per_image": 0.0048,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/anthropic/claude-opus-4.1": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 1.875e-05,
-        "cache_creation_input_token_cost_above_1hr": 3e-05,
-        "cache_read_input_token_cost": 1.5e-06,
-        "input_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.6": {
-        "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.5": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.6": {
-        "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 4096,
-        "supports_response_schema": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.5": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-haiku-4.5": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.7": {
-        "supports_adaptive_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": false,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true,
-        "prompt_cache_min_tokens": 2048,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-5": {
-        "prompt_cache_min_tokens": 512,
-        "supports_adaptive_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": false,
-        "supports_audio_input": false,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_xhigh_reasoning_effort": true
-    },
-    "openrouter/anthropic/claude-opus-5.5": {
-        "cache_creation_input_token_cost": 5e-06,
-        "cache_creation_input_token_cost_above_1hr": 8e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/bytedance/ui-tars-1.5-7b": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat": {
-        "input_cost_per_token": 3.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 8.9e-07,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat-v3-0324": {
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 147456,
-        "max_tokens": 147456,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat-v3.1": {
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_cache_hit": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 9.5e-07,
-        "supports_assistant_prefill": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 1.3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.2": {
-        "cache_read_input_token_cost": 1.345e-07,
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 2.69e-07,
-        "input_cost_per_token_cache_hit": 1.345e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "supports_assistant_prefill": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.2-exp": {
-        "cache_read_input_token_cost": 2e-08,
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 2.7e-07,
-        "input_cost_per_token_cache_hit": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4.1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1": {
-        "cache_read_input_token_cost": 1.4e-07,
-        "input_cost_per_token": 7e-07,
-        "input_cost_per_token_cache_hit": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 64000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1-0528": {
-        "cache_read_input_token_cost": 3.5e-07,
-        "input_cost_per_token": 5e-07,
-        "input_cost_per_token_cache_hit": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2.15e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-pro": {
-        "input_cost_per_token": 8.44944e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "output_cost_per_token": 1.689888e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 7.0412e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4.1-flash": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 6e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 393216,
-        "max_tokens": 393216,
-        "mode": "chat",
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-pro-0813": {
-        "input_cost_per_token": 4.62e-07,
-        "input_cost_per_token_cache_hit": 1.9272e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "output_cost_per_token": 1.386e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 1.54e-08,
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":0.00000132,"output_cost_per_token":0.00000396,"cache_read_input_token_cost":4.4e-8},
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/fireworks/ember-1": {
-        "input_cost_per_token": 3e-06,
-        "output_cost_per_token": 1.5e-05,
-        "cache_read_input_token_cost": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_image_size": false,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-20",
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_pdf_input": true,
-        "supports_reasoning": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-pro": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_pdf_input": true,
-        "supports_reasoning": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3-pro-preview": {
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "input_cost_per_token_batches": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "output_cost_per_token_batches": 6e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3-flash-preview": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 3e-06,
-        "output_cost_per_token": 3e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-flash-lite-preview": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 5e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 1.5e-06,
-        "output_cost_per_token": 1.5e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000
-    },
-    "openrouter/google/gemini-3.1-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 5e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 1.5e-06,
-        "output_cost_per_token": 1.5e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000
-    },
-    "openrouter/google/gemini-3.1-pro-preview": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/gryphe/mythomax-l2-13b": {
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 3686,
-        "max_tokens": 3686,
-        "mode": "chat",
-        "output_cost_per_token": 1.1e-07,
-        "supports_tool_choice": false,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mancer/weaver": {
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 6000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "supports_tool_choice": false,
-        "max_input_tokens": 8000,
-        "max_output_tokens": 6000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3-70b-instruct": {
-        "input_cost_per_token": 5.9e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 7.9e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 8192,
-        "max_output_tokens": 8000
-    },
-    "openrouter/minimax/minimax-m2": {
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/devstral-2512": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-3b-2512": {
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-8b-2512": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-14b-2512": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-7b-instruct": {
-        "input_cost_per_token": 1.3e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_token": 1.3e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8191
-    },
-    "openrouter/mistralai/mistral-large": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 102400,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 128000,
-        "max_output_tokens": 102400,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-3.1-24b-instruct": {
-        "input_cost_per_token": 3.51e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 102400,
-        "mode": "chat",
-        "output_cost_per_token": 5.55e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 128000,
-        "max_output_tokens": 102400,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-3.2-24b-instruct": {
-        "input_cost_per_token": 9.375e-08,
-        "litellm_provider": "openrouter",
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 256000,
-        "max_output_tokens": 16384,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mixtral-8x22b-instruct": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 52428,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 65536,
-        "max_output_tokens": 52428,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.5": {
-        "cache_read_input_token_cost": 7e-08,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-lightning": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo": {
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-16k": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4": {
-        "input_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "supports_tool_choice": true,
-        "max_input_tokens": 8191,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4.1": {
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-mini": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-nano": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.25e-06,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o-2024-05-13": {
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-chat": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/openai/gpt-5-codex": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/openai/gpt-5.2-codex": {
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-mini": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-nano": {
-        "cache_read_input_token_cost": 5e-09,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex-max": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2": {
-        "input_cost_per_image": 0,
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-chat": {
-        "input_cost_per_image": 0,
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-pro": {
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 2.1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 0.000168,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "default_reasoning_effort": "medium",
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "reasoning_effort_levels": [
-            "none",
-            "low",
-            "medium",
-            "high",
-            "xhigh",
-            "max"
-        ],
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol-pro": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-oss-120b": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-120b:batch": {
-        "input_cost_per_token": 2.96e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 1.36e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-20b": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 1.8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 9e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o1": {
-        "cache_read_input_token_cost": 7.5e-06,
-        "input_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini": {
-        "input_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4.4e-06,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "cache_read_input_token_cost": 5.5e-07,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini-high": {
-        "input_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4.4e-06,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "cache_read_input_token_cost": 5.5e-07,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen-2.5-coder-32b-instruct": {
-        "input_cost_per_token": 6.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-vl-plus": {
-        "input_cost_per_token": 2.1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 6.3e-07,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/qwen/qwen3-coder": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_tool_choice": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-plus": {
-        "cache_creation_input_token_cost": 8.125e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 3.9e-07,
-        "input_cost_per_token_above_32k_tokens": 1.17e-06,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06,
-        "cache_read_input_token_cost_above_32k_tokens": 2.34e-07,
-        "output_cost_per_token_above_32k_tokens": 5.85e-06,
-        "cache_read_input_token_cost": 1.3e-07,
-        "input_cost_per_token": 6.5e-07,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3.25e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b-2507": {
-        "cache_read_input_token_cost": 1.75e-08,
-        "input_cost_per_token": 8.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b-thinking-2507": {
-        "input_cost_per_token": 2.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 2.3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-plus": {
-        "cache_creation_input_token_cost": 4.0625e-07,
-        "input_cost_per_token_above_256k_tokens": 1.3e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06,
-        "output_cost_per_token_above_256k_tokens": 3.9e-06,
-        "input_cost_per_token": 3.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.95e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-35b-a3b": {
-        "input_cost_per_token": 3.125e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.5625e-07,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-27b": {
-        "input_cost_per_token": 1.95e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.56e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-122b-a10b": {
-        "input_cost_per_token": 2.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 2.08e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-flash-02-23": {
-        "input_cost_per_token": 6.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 2.6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-plus-02-15": {
-        "input_cost_per_token": 2.6e-07,
-        "input_cost_per_token_above_256k_tokens": 3.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.56e-06,
-        "output_cost_per_token_above_256k_tokens": 1.95e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-397b-a17b": {
-        "cache_read_input_token_cost": 2.25e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 3.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/switchpoint/router": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.4e-06,
-        "source": "https://openrouter.ai/switchpoint/router",
-        "supports_tool_choice": true
-    },
-    "openrouter/undi95/remm-slerp-l2-13b": {
-        "input_cost_per_token": 3.5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 5529,
-        "mode": "chat",
-        "output_cost_per_token": 6.5e-07,
-        "supports_tool_choice": false,
-        "max_input_tokens": 6144,
-        "max_output_tokens": 5529,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/x-ai/grok-4",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-4.6": {
-        "input_cost_per_token": 4.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 8e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.6:exacto": {
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202800,
-        "max_output_tokens": 131000,
-        "max_tokens": 131000,
-        "mode": "chat",
-        "output_cost_per_token": 1.9e-06,
-        "source": "https://openrouter.ai/z-ai/glm-4.6:exacto",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/xiaomi/mimo-v2-flash": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true
-    },
-    "openrouter/xiaomi/mimo-v2.5-pro": {
-        "input_cost_per_token": 4.35e-07,
-        "output_cost_per_token": 8.7e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3.6e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/xiaomi/mimo-v2.5": {
-        "input_cost_per_token": 1.4e-07,
-        "output_cost_per_token": 2.8e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 2.8e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_video_input": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.7": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 1.75e-06,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.7-flash": {
-        "input_cost_per_token": 6.05e-08,
-        "output_cost_per_token": 4e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5": {
-        "cache_read_input_token_cost": 1.2e-07,
-        "input_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.92e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.1": {
-        "input_cost_per_token": 9.66e-07,
-        "output_cost_per_token": 3.036e-06,
-        "cache_read_input_token_cost": 1.794e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.1": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-08",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_computer_use": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.5": {
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1.08e-06,
-        "cache_read_input_token_cost": 2.7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_computer_use": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/openrouter/auto": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_tokens": 2000000,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_video_input": true
-    },
-    "openrouter/openrouter/free": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_tokens": 200000,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "openrouter/openrouter/bodybuilder": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat"
-    },
     "ovhcloud/DeepSeek-R1-Distill-Llama-70B": {
         "input_cost_per_token": 6.7e-07,
         "litellm_provider": "ovhcloud",
@@ -43655,66 +45918,6 @@
         "supports_response_schema": true,
         "supports_tool_choice": false
     },
-    "palm/chat-bison": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/chat-bison-001": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-001": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-safety-off": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-safety-recitation-off": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
     "parallel_ai/search": {
         "input_cost_per_query": 0.005,
         "litellm_provider": "parallel_ai",
@@ -43836,6 +46039,54 @@
         "mode": "chat",
         "output_cost_per_token": 2.8e-07
     },
+    "perplexity/pplx-decider-v1-27b": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/api-reference/decisions-post"
+    },
+    "perplexity/pplx-decider-v1.1-27b": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/getting-started/pricing"
+    },
+    "perplexity/pplx-decider-v1.2": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-latest": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-flash-v1.2": {
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-flash-latest": {
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
     "perplexity/sonar": {
         "input_cost_per_token": 1e-06,
         "litellm_provider": "perplexity",
@@ -44202,6 +46453,14 @@
         "supports_reasoning": true,
         "supports_function_calling": true
     },
+    "perplexity/perplexity/deepseek-v4-pro-0813": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1.32e-06,
+        "output_cost_per_token": 3.96e-06,
+        "cache_read_input_token_cost": 4.4e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
     "perplexity/perplexity/glm-5.2": {
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.4e-06,
@@ -44302,42 +46561,52 @@
         "supports_reasoning": true
     },
     "qwen.qwen3-coder-480b-a35b-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 262000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_native_structured_output": true,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html"
     },
     "qwen.qwen3-235b-a22b-2507-v1:0": {
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_flex": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 8.8e-07,
+        "output_cost_per_token_flex": 4.4e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_native_structured_output": true,
         "input_cost_per_token_batches": 1.1e-07,
-        "output_cost_per_token_batches": 4.4e-07
+        "output_cost_per_token_batches": 4.4e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"
     },
     "qwen.qwen3-coder-30b-a3b-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -44345,12 +46614,19 @@
     },
     "qwen.qwen3-32b-v1:0": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -44375,12 +46651,12 @@
     "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.45e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44391,12 +46667,12 @@
     "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.41e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44407,12 +46683,12 @@
     "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.545e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.236e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44423,12 +46699,12 @@
     "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.41e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44439,12 +46715,12 @@
     "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 2.3e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44455,12 +46731,12 @@
     "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.45e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44470,13 +46746,17 @@
     },
     "qwen.qwen3-vl-235b-a22b": {
         "input_cost_per_token": 5.3e-07,
+        "input_cost_per_token_batches": 2.6e-07,
+        "input_cost_per_token_priority": 9.3e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.66e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.33e-06,
+        "output_cost_per_token_priority": 4.66e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -44486,16 +46766,22 @@
     },
     "qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.75e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -45199,6 +47485,53 @@
         "supports_vision": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
+    "scx-ai/DeepSeek-V4.1-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 375000,
+        "max_tokens": 375000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://scx.ai/models/deepseek-v4-1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "scx-ai/GLM-5.3": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 9.8e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3.08e-06,
+        "source": "https://scx.ai/models/glm-5-3",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": false
+    },
+    "scx-ai/Kimi-K3": {
+        "cache_read_input_token_cost": 2.8e-07,
+        "input_cost_per_token": 2.83e-06,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 1.413e-05,
+        "source": "https://scx.ai/models/kimi-k3",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": false
+    },
     "scx-ai/GLM-5.2": {
         "cache_read_input_token_cost": 2.2e-07,
         "input_cost_per_token": 6.1e-07,
@@ -45649,78 +47982,169 @@
         "mode": "image_edit",
         "output_cost_per_image": 0.4
     },
+    "us.stability.stable-conservative-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.4,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-creative-upscale-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.6
     },
+    "us.stability.stable-creative-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.6,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-fast-upscale-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.03
     },
+    "us.stability.stable-fast-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.03,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-outpaint-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.06
     },
+    "us.stability.stable-outpaint-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.06,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-control-sketch-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-control-sketch-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-control-structure-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-control-structure-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-erase-object-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-erase-object-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-inpaint-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-inpaint-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-remove-background-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-remove-background-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-search-recolor-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-search-recolor-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-search-replace-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-search-replace-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-style-guide-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-style-guide-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-style-transfer-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.08
     },
+    "us.stability.stable-style-transfer-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.08,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-core-v1:1": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
@@ -45951,14 +48375,6 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
-    "together_ai/baai/bge-base-en-v1.5": {
-        "input_cost_per_token": 8e-09,
-        "litellm_provider": "together_ai",
-        "max_input_tokens": 512,
-        "mode": "embedding",
-        "output_cost_per_token": 0.0,
-        "output_vector_size": 768
-    },
     "together_ai/BAAI/bge-base-en-v1.5": {
         "input_cost_per_token": 8e-09,
         "litellm_provider": "together_ai",
@@ -46002,6 +48418,7 @@
         "supports_tool_choice": true
     },
     "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+        "deprecation_date": "2026-10-22",
         "input_cost_per_token": 1.04e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
@@ -46124,7 +48541,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
-        "source": "https://api.together.ai/v1/models",
+        "source": "https://www.together.ai/pricing",
         "supports_prompt_caching": true
     },
     "together_ai/Qwen/Qwen3.7-Plus": {
@@ -46158,7 +48575,7 @@
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-09-29",
+        "deprecation_date": "2026-10-22",
         "input_cost_per_token": 1.4e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1048576,
@@ -46188,7 +48605,6 @@
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": {
         "cache_read_input_token_cost": 1.3e-07,
-        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 1.32e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1048576,
@@ -46213,6 +48629,19 @@
         "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
+    "together_ai/meta-models/Muse-Spark-Open-816B-A42B": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://docs.together.ai/docs/serverless-models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "together_ai/moonshotai/Kimi-K3": {
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
@@ -46303,6 +48732,7 @@
         "supports_vision": true
     },
     "tts-1": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -46312,6 +48742,7 @@
         ]
     },
     "tts-1-hd": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_character": 3e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -46369,12 +48800,15 @@
     "us.amazon.nova-lite-v1:0": {
         "cache_read_input_token_cost": 1.5e-08,
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -46385,12 +48819,15 @@
     "us.amazon.nova-micro-v1:0": {
         "cache_read_input_token_cost": 8.75e-09,
         "input_cost_per_token": 3.5e-08,
+        "input_cost_per_token_batches": 1.75e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 1.4e-07,
+        "output_cost_per_token_batches": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
@@ -46398,13 +48835,22 @@
     },
     "us.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 8e-07,
+        "input_cost_per_token_batches": 4e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "input_cost_per_token_priority": 1.4e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_flex": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -46456,7 +48902,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -46554,7 +49004,11 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.125e-06,
@@ -46566,6 +49020,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -46592,7 +49047,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -46623,7 +49082,11 @@
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us-gov.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46648,6 +49111,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -46657,7 +49121,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46682,6 +49151,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -46691,7 +49161,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46724,7 +49199,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46759,7 +49239,12 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.5e-05,
@@ -46793,7 +49278,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5-1",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 7.2e-08,
@@ -46813,6 +49303,7 @@
         "supports_vision": false
     },
     "us-gov.nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -46820,6 +49311,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -46827,6 +49319,7 @@
         "supports_response_schema": true
     },
     "us-gov.nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -46834,6 +49327,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -46861,10 +49355,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -46874,19 +49374,31 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
     "us-gov.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2.64e-06,
         "output_cost_per_token": 7.92e-06,
         "cache_read_input_token_cost": 6.6e-07,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
@@ -46924,7 +49436,11 @@
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
         "output_cost_per_token_batches": 2.75e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -46983,7 +49499,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-opus-4-5-20251101-v1:0": {
         "cache_creation_input_token_cost": 6.25e-06,
@@ -47016,7 +49536,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-5-20251101-v1:0": {
         "cache_creation_input_token_cost": 6.875e-06,
@@ -47049,7 +49573,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -47061,7 +49589,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -47082,29 +49610,41 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.deepseek.r1-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
         "supports_function_calling": false,
         "supports_reasoning": true,
         "supports_tool_choice": false
     },
     "us.deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_batches": 3.1e-07,
+        "input_cost_per_token_flex": 3.1e-07,
+        "input_cost_per_token_priority": 1.085e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
         "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_batches": 9.25e-07,
+        "output_cost_per_token_flex": 9.25e-07,
+        "output_cost_per_token_priority": 3.2375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -47115,12 +49655,14 @@
     },
     "eu.deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
         "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -47130,51 +49672,64 @@
         "supports_vision": false
     },
     "us.meta.llama3-1-405b-instruct-v1:0": {
-        "input_cost_per_token": 5.32e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 2.4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.6e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-1-70b-instruct-v1:0": {
-        "input_cost_per_token": 9.9e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 9.9e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "us.meta.llama3-1-8b-instruct-v1:0": {
-        "input_cost_per_token": 2.2e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "us.meta.llama3-2-11b-instruct-v1:0": {
-        "input_cost_per_token": 3.5e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "us.meta.llama3-1-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-07,
+        "output_cost_per_token_batches": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "us.meta.llama3-2-11b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 1.6e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "us.meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -47182,10 +49737,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -47193,42 +49750,51 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-2-90b-instruct-v1:0": {
-        "input_cost_per_token": 2e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 2e-06,
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "us.meta.llama3-3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama4-maverick-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "input_cost_per_token_batches": 1.2e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
         "output_cost_per_token_batches": 4.85e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -47241,15 +49807,17 @@
         "supports_tool_choice": false
     },
     "us.meta.llama4-scout-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.7e-07,
         "input_cost_per_token_batches": 8.5e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 10000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
         "output_cost_per_token_batches": 3.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -47265,11 +49833,11 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -47659,7 +50227,7 @@
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -49431,7 +51999,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "cache_creation_input_token_cost_batches": 1.88e-06
     },
     "vertex_ai/claude-sonnet-5": {
         "deprecation_date": "2026-12-24",
@@ -49488,7 +52057,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -49539,7 +52108,8 @@
         "supports_vision": true,
         "supports_native_streaming": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "cache_creation_input_token_cost_batches": 1.88e-06
     },
     "vertex_ai/mistralai/codestral-2@001": {
         "input_cost_per_token": 3e-07,
@@ -49660,7 +52230,7 @@
         "supported_regions": [
             "global"
         ],
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -49681,7 +52251,7 @@
         "supported_regions": [
             "us-central1"
         ],
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -49708,7 +52278,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -49765,7 +52336,14 @@
         "output_cost_per_token_flex": 6e-06,
         "output_cost_per_token_priority": 2.16e-05,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
@@ -49792,17 +52370,26 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
         "supports_reasoning": false,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-image": {
         "cache_read_input_token_cost": 5e-08,
         "cache_read_input_token_cost_batches": 2.5e-08,
         "cache_read_input_token_cost_flex": 2.5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -49813,8 +52400,17 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "regional_endpoint_uplift_multiplier": 1.1,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
@@ -49832,16 +52428,26 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_batches": 1.25e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-06-28",
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -49852,10 +52458,12 @@
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.7e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -50034,6 +52642,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -50060,7 +52669,7 @@
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
-        "mode": "image_generation",
+        "mode": "chat",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
@@ -50945,6 +53554,26 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "voyage/rerank-1": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 8000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
+    "voyage/rerank-lite-1": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 4000,
+        "max_output_tokens": 4000,
+        "max_tokens": 4000,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/rerank-2.5": {
         "input_cost_per_token": 5e-08,
         "litellm_provider": "voyage",
@@ -51081,6 +53710,16 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
+    "voyage/voyage-large-2-instruct": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 16000,
+        "max_tokens": 16000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1024,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/voyage-law-2": {
         "input_cost_per_token": 1.2e-07,
         "litellm_provider": "voyage",
@@ -51630,13 +54269,16 @@
     },
     "xai/grok-4.20-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -51644,8 +54286,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -51674,9 +54319,13 @@
     "xai/grok-4.3": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_image_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
@@ -51684,6 +54333,8 @@
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -51696,9 +54347,13 @@
     "xai/grok-4.3-latest": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_image_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
@@ -51706,6 +54361,8 @@
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -51826,53 +54483,71 @@
         "supports_web_search": true
     },
     "zai.glm-4.7": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 203000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2.2e-06,
+        "output_cost_per_token_batches": 1.1e-06,
+        "output_cost_per_token_flex": 1.1e-06,
+        "output_cost_per_token_priority": 3.85e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "zai.glm-5": {
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "input_cost_per_token_priority": 1.75e-06,
         "output_cost_per_token": 3.2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "zai.glm-4.7-flash": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 203000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_flex": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -52081,6 +54756,70 @@
         "litellm_provider": "vertex_ai",
         "mode": "vector_store"
     },
+    "vertex_ai/semantic-ranker-default": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-002": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-003": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
     "openai/container": {
         "code_interpreter_cost_per_session": 0.03,
         "litellm_provider": "openai",
@@ -52129,7 +54868,7 @@
         ]
     },
     "azure/sora-2": {
-        "deprecation_date": "2026-10-15",
+        "deprecation_date": "2026-11-02",
         "litellm_provider": "azure",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -52839,7 +55578,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -52848,7 +55587,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -53308,7 +56047,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m2": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 196608,
         "max_output_tokens": 4096,
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 1.2e-06,
@@ -53479,7 +56218,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -53542,7 +56281,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": {
         "max_tokens": 131072,
-        "max_input_tokens": 131072,
+        "max_input_tokens": 128000,
         "max_output_tokens": 131072,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -53551,7 +56290,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": {
         "max_tokens": 131072,
-        "max_input_tokens": 131072,
+        "max_input_tokens": 128000,
         "max_output_tokens": 131072,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -54147,7 +56886,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 262144,
         "max_output_tokens": 4096,
         "input_cost_per_token": 9e-07,
         "output_cost_per_token": 9e-07,
@@ -54172,15 +56911,6 @@
         "litellm_provider": "fireworks_ai",
         "mode": "embedding"
     },
-    "fireworks_ai/accounts/fireworks/models/": {
-        "max_tokens": 40960,
-        "max_input_tokens": 40960,
-        "max_output_tokens": 40960,
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "fireworks_ai",
-        "mode": "embedding"
-    },
     "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": {
         "max_tokens": 4096,
         "max_input_tokens": 4096,
@@ -54274,7 +57004,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 262144,
         "max_output_tokens": 4096,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -56143,6 +58873,7 @@
         ]
     },
     "gpt-4o-mini-tts-2025-12-15": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -56361,6 +59092,7 @@
         ]
     },
     "gemini-2.0-flash-exp-image-generation": {
+        "deprecation_date": "2025-11-14",
         "input_cost_per_token": 0.0,
         "litellm_provider": "gemini",
         "max_input_tokens": 32768,
@@ -56381,6 +59113,7 @@
         "supports_vision": true
     },
     "gemini/gemini-2.0-flash-exp-image-generation": {
+        "deprecation_date": "2025-11-14",
         "input_cost_per_token": 0.0,
         "litellm_provider": "gemini",
         "max_input_tokens": 32768,
@@ -56455,6 +59188,7 @@
         "gemini_native_audio": true
     },
     "gemini-2.5-flash-native-audio-preview-12-2025": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "gemini",
@@ -56485,6 +59219,7 @@
         "supports_web_search": true
     },
     "gemini-3.1-flash-live-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -56646,6 +59381,7 @@
         "gemini_native_audio": true
     },
     "gemini/gemini-2.5-flash-native-audio-preview-12-2025": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "gemini",
@@ -56675,9 +59411,11 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.1-flash-live-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -56713,9 +59451,11 @@
         "rpm": 10,
         "gemini_audio_only_live": true,
         "input_cost_per_second": 8.33333333333e-05,
-        "supports_response_schema": false
+        "supports_response_schema": false,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.1-flash-tts-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 1e-06,
         "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "gemini",
@@ -56758,7 +59498,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
-        ]
+        ],
+        "supports_prompt_caching": true
     },
     "gemini/gemini-3.8-flash-lite-tts": {
         "cache_read_input_token_cost": 1.25e-07,
@@ -56782,9 +59523,11 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
-        ]
+        ],
+        "supports_prompt_caching": true
     },
     "gemini-2.5-flash-preview-tts": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "gemini",
@@ -57146,7 +59889,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -57175,12 +59918,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -57193,12 +59943,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "output_cost_per_token": 3e-07,
+        "output_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_priority": 5.25e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -57211,12 +59968,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -57227,12 +59991,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.2e-07,
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_flex": 1e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -57276,6 +60047,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57319,6 +60091,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57333,10 +60106,11 @@
         "cache_read_input_token_cost": 1.375e-06,
         "output_cost_per_token": 8.25e-05,
         "litellm_provider": "bedrock_mantle",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/responses"
@@ -57351,6 +60125,7 @@
         "supports_function_calling": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57427,6 +60202,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57436,6 +60212,7 @@
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html"
     },
     "us.openai.gpt-5.6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 4.4e-06,
         "input_cost_per_token_above_272k_tokens": 8.8e-06,
         "cache_creation_input_token_cost": 5.5e-06,
@@ -57445,11 +60222,12 @@
         "output_cost_per_token": 2.2e-05,
         "output_cost_per_token_above_272k_tokens": 3.3e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57466,10 +60244,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-5.6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 4e-06,
         "input_cost_per_token_above_272k_tokens": 8e-06,
         "cache_creation_input_token_cost": 5e-06,
@@ -57479,11 +60259,12 @@
         "output_cost_per_token": 2e-05,
         "output_cost_per_token_above_272k_tokens": 3e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57500,10 +60281,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-5.6-terra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
         "cache_creation_input_token_cost": 2.75e-06,
@@ -57513,11 +60296,12 @@
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57534,10 +60318,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-5.6-terra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "cache_creation_input_token_cost": 2.5e-06,
@@ -57547,11 +60333,12 @@
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_272k_tokens": 1.8e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57568,10 +60355,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-5.6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
         "cache_creation_input_token_cost": 2.75e-07,
@@ -57581,11 +60370,12 @@
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57602,6 +60392,7 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -57613,7 +60404,8 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_above_272k_tokens": 2.475e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57644,7 +60436,8 @@
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57675,7 +60468,8 @@
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57706,7 +60500,8 @@
         "output_cost_per_token": 3e-05,
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57730,6 +60525,7 @@
         ]
     },
     "global.openai.gpt-5.6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_above_272k_tokens": 4e-07,
         "cache_creation_input_token_cost": 2.5e-07,
@@ -57739,11 +60535,12 @@
         "output_cost_per_token": 1.2e-06,
         "output_cost_per_token_above_272k_tokens": 1.8e-06,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57760,6 +60557,7 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -57768,8 +60566,14 @@
         "input_cost_per_token_above_272k_tokens": 2.2e-05,
         "cache_creation_input_token_cost": 1.375e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165,
+        "cache_creation_input_token_cost_ultrafast": 8.25e-05,
         "cache_read_input_token_cost": 1.1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05,
+        "cache_read_input_token_cost_ultrafast": 6.6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132,
+        "input_cost_per_token_ultrafast": 6.6e-05,
         "output_cost_per_token": 5.5e-05,
         "output_cost_per_token_above_272k_tokens": 8.25e-05,
         "litellm_provider": "bedrock_mantle",
@@ -57777,6 +60581,8 @@
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495,
+        "output_cost_per_token_ultrafast": 0.00033,
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -57794,6 +60600,7 @@
         "supports_minimal_reasoning_effort": false,
         "supports_none_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57830,8 +60637,9 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57868,8 +60676,9 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57878,19 +60687,29 @@
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html"
     },
     "us.openai.gpt-6-astra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1.1e-05,
         "input_cost_per_token_above_272k_tokens": 2.2e-05,
         "cache_creation_input_token_cost": 1.375e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165,
+        "cache_creation_input_token_cost_ultrafast": 8.25e-05,
         "cache_read_input_token_cost": 1.1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05,
+        "cache_read_input_token_cost_ultrafast": 6.6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132,
+        "input_cost_per_token_ultrafast": 6.6e-05,
         "output_cost_per_token": 5.5e-05,
         "output_cost_per_token_above_272k_tokens": 8.25e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495,
+        "output_cost_per_token_ultrafast": 0.00033,
         "supported_modalities": [
             "text",
             "image"
@@ -57907,12 +60726,15 @@
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_sampling_params": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
         "cache_creation_input_token_cost": 2.75e-06,
@@ -57922,6 +60744,7 @@
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -57936,18 +60759,21 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1.1e-07,
         "input_cost_per_token_above_272k_tokens": 2.2e-07,
         "cache_creation_input_token_cost": 1.375e-07,
@@ -57957,6 +60783,7 @@
         "output_cost_per_token": 5.5e-07,
         "output_cost_per_token_above_272k_tokens": 8.25e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -57971,31 +60798,43 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-6-astra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_above_272k_tokens": 2e-05,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
+        "cache_creation_input_token_cost_ultrafast": 7.5e-05,
         "cache_read_input_token_cost": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
+        "cache_read_input_token_cost_ultrafast": 6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
+        "input_cost_per_token_ultrafast": 6e-05,
         "output_cost_per_token": 5e-05,
         "output_cost_per_token_above_272k_tokens": 7.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
+        "output_cost_per_token_ultrafast": 0.0003,
         "supported_modalities": [
             "text",
             "image"
@@ -58012,8 +60851,10 @@
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_sampling_params": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58027,6 +60868,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58041,15 +60883,17 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "global.openai.gpt-6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "cache_creation_input_token_cost": 2.5e-06,
@@ -58059,6 +60903,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58073,14 +60918,16 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58094,6 +60941,7 @@
         "output_cost_per_token": 5e-07,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58108,15 +60956,17 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "global.openai.gpt-6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_above_272k_tokens": 2e-07,
         "cache_creation_input_token_cost": 1.25e-07,
@@ -58126,6 +60976,7 @@
         "output_cost_per_token": 5e-07,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58140,14 +60991,16 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58233,12 +61086,19 @@
     },
     "bedrock_mantle/google.gemma-4-31b": {
         "input_cost_per_token": 1.4e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.45e-07,
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_flex": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58252,12 +61112,19 @@
     },
     "bedrock_mantle/google.gemma-4-26b-a4b": {
         "input_cost_per_token": 1.3e-07,
+        "input_cost_per_token_batches": 6.5e-08,
+        "input_cost_per_token_flex": 6.5e-08,
+        "input_cost_per_token_priority": 2.275e-07,
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_flex": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58271,12 +61138,19 @@
     },
     "bedrock_mantle/google.gemma-4-e2b": {
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "output_cost_per_token": 8e-08,
+        "output_cost_per_token_flex": 4e-08,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_batches": 4e-08,
+        "output_cost_per_token_priority": 1.4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58293,11 +61167,20 @@
         "input_cost_per_token": 1.25e-06,
         "output_cost_per_token": 2.5e-06,
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "input_cost_per_token_priority": 2.1875e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1048576,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -58307,18 +61190,24 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/xai.grok-4.6": {
         "use_openai_responses_path": true,
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 6.6e-06,
         "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -58359,15 +61248,108 @@
         "input_cost_per_token_batches": 5e-07,
         "output_cost_per_token_batches": 2.5e-06
     },
+    "bedrock_mantle/anthropic.claude-opus-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 5.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 8.8e-06,
+        "cache_read_input_token_cost": 2.2e-07,
+        "input_cost_per_token": 4.4e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html",
+        "thinking_always_on": true,
+        "supports_forced_tool_use": false
+    },
+    "bedrock_mantle/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
     "us.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 6.6e-06,
         "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_prompt_caching": false,
@@ -58376,14 +61358,26 @@
         "supports_vision": true
     },
     "global.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 6e-06,
         "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_flex": 2.5e-07,
+        "cache_read_input_token_cost_priority": 8.75e-07,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.5e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3e-06,
+        "output_cost_per_token_priority": 1.05e-05,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_prompt_caching": false,
@@ -58445,6 +61439,41 @@
         "supports_tool_choice": false,
         "supports_vision": true
     },
+    "volcengine/doubao-seed-2-1-pro-260915": {
+        "cache_read_input_token_cost": 1.725e-07,
+        "input_cost_per_token": 8.625e-07,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 1024000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 4.3125e-06,
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
+    "volcengine/doubao-seed-2-1-lite-260915": {
+        "cache_read_input_audio_token_cost": 3.45e-07,
+        "cache_read_input_token_cost": 2.3e-08,
+        "input_cost_per_audio_token": 1.725e-06,
+        "input_cost_per_token": 1.15e-07,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 1024000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 3.88126e-07,
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
     "volcengine/doubao-seed-2-1-turbo-260628": {
         "cache_read_input_token_cost": 8.625e-08,
         "input_cost_per_token": 4.3125e-07,
@@ -58575,6 +61604,61 @@
             }
         ]
     },
+    "volcengine/doubao-seedance-2-5-260628": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.216,
+        "output_cost_per_second_480p": 0.096075,
+        "output_cost_per_second_720p": 0.216,
+        "output_cost_per_second_1080p": 0.5346,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-260128": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.141942857,
+        "output_cost_per_second_480p": 0.066003429,
+        "output_cost_per_second_720p": 0.141942857,
+        "output_cost_per_second_1080p": 0.354085714,
+        "output_cost_per_second_4k": 0.722057143,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-fast-260128": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.114171429,
+        "output_cost_per_second_480p": 0.053089714,
+        "output_cost_per_second_720p": 0.114171429,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-mini-260615": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.070971429,
+        "output_cost_per_second_480p": 0.033001714,
+        "output_cost_per_second_720p": 0.070971429,
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
     "bedrock/us-east-1/zai.glm-5": {
         "input_cost_per_token": 1e-06,
         "output_cost_per_token": 3.2e-06,
@@ -58635,7 +61719,11 @@
         "supports_native_structured_output": true,
         "supports_pdf_input": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.5e-06,
@@ -58661,7 +61749,11 @@
         "supports_native_structured_output": true,
         "supports_pdf_input": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "snowflake/claude-sonnet-4-5": {
         "max_tokens": 16384,
@@ -59463,16 +62555,16 @@
     },
     "tencent/deepseek-v4-pro": {
         "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3.625e-09,
-        "input_cost_per_token": 4.35e-07,
-        "input_cost_per_token_cache_hit": 3.625e-09,
+        "cache_read_input_token_cost": 1.45e-07,
+        "input_cost_per_token": 1.74e-06,
+        "input_cost_per_token_cache_hit": 1.45e-07,
         "litellm_provider": "tencent",
         "max_input_tokens": 1000000,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 8.7e-07,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "output_cost_per_token": 3.48e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59498,7 +62590,7 @@
         "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 2.8e-07,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59513,6 +62605,310 @@
         "supports_reasoning": true,
         "supports_vision": false
     },
+    "tencent/deepseek-v4-pro-0813": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 4.4e-08,
+        "input_cost_per_token": 1.32e-06,
+        "input_cost_per_token_cache_hit": 4.4e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "off_peak_pricing": {
+            "cache_read_input_token_cost": 2.2e-08,
+            "input_cost_per_token": 6.6e-07,
+            "output_cost_per_token": 1.98e-06,
+            "weekday_timezone": "Asia/Shanghai",
+            "windows": [
+                {
+                    "hours_utc": [
+                        "00:00-01:00",
+                        "04:00-06:00",
+                        "10:00-00:00"
+                    ],
+                    "weekdays": [
+                        1,
+                        2,
+                        3,
+                        4,
+                        5
+                    ]
+                },
+                {
+                    "hours_utc": "00:00-00:00",
+                    "weekdays": [
+                        6,
+                        7
+                    ]
+                }
+            ]
+        },
+        "output_cost_per_token": 3.96e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_vision": false
+    },
+    "tencent/deepseek-v4.1-flash": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_cache_hit": 6e-09,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "off_peak_pricing": {
+            "cache_read_input_token_cost": 3e-09,
+            "input_cost_per_token": 1.5e-07,
+            "output_cost_per_token": 6e-07,
+            "weekday_timezone": "Asia/Shanghai",
+            "windows": [
+                {
+                    "hours_utc": [
+                        "00:00-01:00",
+                        "04:00-06:00",
+                        "10:00-00:00"
+                    ],
+                    "weekdays": [
+                        1,
+                        2,
+                        3,
+                        4,
+                        5
+                    ]
+                },
+                {
+                    "hours_utc": "00:00-00:00",
+                    "weekdays": [
+                        6,
+                        7
+                    ]
+                }
+            ]
+        },
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3-flashx": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 3.7e-07,
+        "input_cost_per_token_cache_hit": 7.5e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3-flash": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_cache_hit": 3e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_cache_hit": 2.6e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/glm-5.2": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_cache_hit": 2.6e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k3": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_cache_hit": 3e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.8-preview": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_cache_hit": 2.5e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.7-code-highspeed": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3.8e-07,
+        "input_cost_per_token": 1.9e-06,
+        "input_cost_per_token_cache_hit": 3.8e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.7-code": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_cache_hit": 1.9e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "tencent/minimax-m3": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 6e-08,
@@ -59522,7 +62918,7 @@
         "max_input_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59677,13 +63073,16 @@
     },
     "xai/grok-4.20-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -59691,20 +63090,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent-0309": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": false,
         "supports_prompt_caching": true,
@@ -59713,8 +63118,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true,
         "supported_endpoints": [
@@ -59946,6 +63354,9 @@
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 1e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "search_context_cost_per_query": {
@@ -59968,6 +63379,7 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_reasoning": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
@@ -59995,6 +63407,7 @@
         "supports_vision": true
     },
     "mistral/labs-leanstral-1-5": {
+        "deprecation_date": "2026-09-30",
         "input_cost_per_token": 0.0,
         "litellm_provider": "mistral",
         "max_input_tokens": 262144,
@@ -60140,8 +63553,8 @@
             {
                 "name": "claude-tool-search",
                 "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
-                "description": "Claude at version 4.5 or higher, in any id shape that contains claude-<family>-: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.",
+                "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
+                "description": "Claude at version 4.5 or higher, in any id shape that contains claude-<family>-: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.",
                 "model_info": {
                     "supports_tool_search": true
                 }
@@ -60215,6 +63628,9 @@
         "input_cost_per_audio_token": 2e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 98304,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
         "mode": "audio_transcription",
         "output_cost_per_token": 1.2e-05,
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
@@ -60237,6 +63653,9 @@
         "input_cost_per_audio_token": 3.5e-06,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "audio_transcription",
         "output_cost_per_token": 2.1e-05,
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
@@ -60293,7 +63712,7 @@
     },
     "vertex_ai/gemini-3.5-live-translate-preview": {
         "input_cost_per_audio_token": 3.5e-06,
-        "input_cost_per_second": 8.83333333333e-05,
+        "input_cost_per_second": 8.75e-05,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
@@ -60415,18 +63834,18 @@
         "supports_vision": false
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
-        "cache_read_input_token_cost": 7e-09,
-        "cache_read_input_token_cost_priority": 8.75e-09,
-        "input_cost_per_token": 2.2e-07,
-        "input_cost_per_token_priority": 2.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
-        "output_cost_per_token_priority": 8.25e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -60436,13 +63855,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": {
         "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -60453,13 +63875,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token_priority": 8.25e-07,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
@@ -60511,18 +63936,18 @@
         "supports_vision": false
     },
     "fireworks_ai/deepseek-v4p1-flash": {
-        "cache_read_input_token_cost": 7e-09,
-        "cache_read_input_token_cost_priority": 8.75e-09,
-        "input_cost_per_token": 2.2e-07,
-        "input_cost_per_token_priority": 2.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
-        "output_cost_per_token_priority": 8.25e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -60532,13 +63957,16 @@
     },
     "fireworks_ai/deepseek-v4p1-flash-us": {
         "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -60549,13 +63977,16 @@
     },
     "fireworks_ai/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token_priority": 8.25e-07,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
@@ -60684,14 +64115,17 @@
     },
     "fireworks_ai/muse-glimmer-30b": {
         "cache_read_input_token_cost": 4e-08,
+        "cache_read_input_token_cost_priority": 6e-08,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 3.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -60701,14 +64135,18 @@
     },
     "fireworks_ai/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 2.5e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60717,14 +64155,18 @@
     },
     "fireworks_ai/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token_priority": 3e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60733,14 +64175,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": {
         "cache_read_input_token_cost": 4e-08,
+        "cache_read_input_token_cost_priority": 6e-08,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 3.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -60748,16 +64193,31 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "fireworks_ai/accounts/fireworks/models/muse-spark-open": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://fireworks.ai/models/fireworks/muse-spark-open",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
     "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 2.5e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60766,14 +64226,18 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token_priority": 3e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -62397,6 +65861,7 @@
         "supports_tool_choice": true,
         "supports_response_schema": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "source": "https://deepinfra.com/pricing",
         "supports_audio_input": true
@@ -62881,6 +66346,40 @@
         "supports_vision": false,
         "source": "https://deepinfra.com/pricing"
     },
+    "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "max_tokens": 131072,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4.2e-07,
+        "cache_read_input_token_cost": 4.2e-09,
+        "supports_prompt_caching": true,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash"
+    },
+    "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "max_tokens": 131072,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4.2e-07,
+        "cache_read_input_token_cost": 4.2e-09,
+        "supports_prompt_caching": true,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017"
+    },
     "deepinfra/openai/gpt-oss-120b-Ultra": {
         "max_tokens": 131072,
         "max_input_tokens": 131072,
@@ -62989,13 +66488,16 @@
     },
     "xai/grok-4.20": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63003,21 +66505,27 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
     "xai/grok-4.20-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63025,21 +66533,27 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
     "xai/grok-4.20-reasoning-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63047,8 +66561,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -63203,6 +66720,23 @@
             "video"
         ]
     },
+    "xai/grok-imagine-video-1.5-lite": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.02,
+        "output_cost_per_second_1080p": 0.14,
+        "output_cost_per_second_480p": 0.02,
+        "output_cost_per_second_720p": 0.03,
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
     "xai/grok-imagine-video-1.5-2026-05-30": {
         "input_cost_per_image": 0.01,
         "litellm_provider": "xai",
@@ -63240,6 +66774,7 @@
         ]
     },
     "xai/grok-voice-transcribe-1.0": {
+        "deprecation_date": "2026-10-02",
         "input_cost_per_second": 2.778e-05,
         "litellm_provider": "xai",
         "metadata": {
@@ -63285,13 +66820,16 @@
     },
     "xai/grok-4.20-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -63299,20 +66837,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-non-reasoning-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -63320,20 +66864,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supported_endpoints": [
             "/v1/responses"
@@ -63345,20 +66895,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supported_endpoints": [
             "/v1/responses"
@@ -63370,15 +66926,18 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "groq/qwen/qwen3.8-27b": {
         "input_cost_per_token": 8e-07,
         "litellm_provider": "groq",
-        "max_input_tokens": 131042,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -63640,13 +67199,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63675,13 +67237,16 @@
     },
     "fireworks_ai/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63704,6 +67269,33 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/accounts/fireworks/routers/auto": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "fireworks_ai/accounts/fireworks/routers/auto-instant": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "fireworks_ai/accounts/fireworks/routers/firerouter": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "fireworks_ai/glm-5p3-fast": {
         "cache_read_input_token_cost": 3.9e-07,
         "input_cost_per_token": 2.1e-06,
@@ -63738,12 +67330,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -63769,12 +67365,16 @@
     },
     "fireworks_ai/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -63783,13 +67383,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/inkling": {
         "cache_read_input_token_cost": 1.7e-07,
+        "cache_read_input_token_cost_priority": 1.7e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_priority": 1e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 4.05e-06,
-        "source": "https://fireworks.ai/models/fireworks/inkling",
+        "output_cost_per_token_priority": 4.05e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -63821,12 +67425,12 @@
         "supports_tool_choice": true
     },
     "together_ai/Qwen/Qwen3.8-Flash": {
-        "input_cost_per_token": 9e-08,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 2.82e-07,
+        "output_cost_per_token": 4.7e-07,
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.5-fp4": {
@@ -63863,6 +67467,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
+        "deprecation_date": "2026-02-25",
         "input_cost_per_token": 6e-08,
         "output_cost_per_token": 2.5e-07,
         "litellm_provider": "together_ai",
@@ -63934,7 +67539,7 @@
     },
     "azure_ai/kimi-k2.7-code": {
         "cache_read_input_token_cost": 1.9e-07,
-        "deprecation_date": "2026-10-03",
+        "deprecation_date": "2027-04-16",
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 262144,
@@ -63957,52 +67562,26 @@
         "supports_vision": true
     },
     "azure_ai/deepseek-v4.1-flash": {
-        "cache_read_input_token_cost": 8e-09,
-        "input_cost_per_token": 3.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 1.2e-06,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "deprecation_date": "2026-12-15",
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
-    },
-    "azure_ai/muse-spark-1.3": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "azure_ai",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431"
     },
     "azure_ai/MAI-Image-2.6": {
         "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image_token": 3.8e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -64015,6 +67594,7 @@
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image_token": 1.9e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -64135,6 +67715,7 @@
         "supports_vision": true
     },
     "azure_ai/deepseek-r1": {
+        "deprecation_date": "2026-08-13",
         "input_cost_per_token": 1.35e-06,
         "output_cost_per_token": 5.4e-06,
         "litellm_provider": "azure_ai",
@@ -64142,6 +67723,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/deepseek-v3-0324": {
+        "deprecation_date": "2026-07-13",
         "input_cost_per_token": 1.14e-06,
         "output_cost_per_token": 4.56e-06,
         "litellm_provider": "azure_ai",
@@ -64149,6 +67731,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/deepseek-v3.1": {
+        "deprecation_date": "2026-07-13",
         "input_cost_per_token": 1.23e-06,
         "output_cost_per_token": 4.94e-06,
         "litellm_provider": "azure_ai",
@@ -64156,6 +67739,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-3": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 3e-06,
         "output_cost_per_token": 1.5e-05,
         "litellm_provider": "azure_ai",
@@ -64163,6 +67747,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-3-mini": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2.5e-07,
         "output_cost_per_token": 1.27e-06,
         "litellm_provider": "azure_ai",
@@ -64170,6 +67755,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-4-fast-non-reasoning": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
@@ -64177,6 +67763,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-4-fast-reasoning": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
@@ -64201,6 +67788,7 @@
         "supports_vision": false
     },
     "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64208,6 +67796,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -64215,6 +67804,7 @@
         "supports_response_schema": true
     },
     "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64222,6 +67812,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -64249,10 +67840,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64262,10 +67859,16 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64293,6 +67896,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64302,7 +67906,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64326,6 +67935,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64335,7 +67945,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64367,7 +67982,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64402,7 +68022,12 @@
         "supports_xhigh_reasoning_effort": true,
         "thinking_always_on": true,
         "supports_forced_tool_use": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.5e-05,
@@ -64435,7 +68060,12 @@
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 512
+        "prompt_cache_min_tokens": 512,
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5-1",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 7.2e-08,
@@ -64455,6 +68085,7 @@
         "supports_vision": false
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64462,6 +68093,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -64469,6 +68101,7 @@
         "supports_response_schema": true
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64476,6 +68109,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -64503,10 +68137,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64516,10 +68156,16 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64547,6 +68193,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64580,6 +68227,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64717,14 +68365,15 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 2.64e-06,
-        "input_cost_per_token_above_272k_tokens": 5.28e-06,
-        "cache_creation_input_token_cost": 3.3e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06,
-        "cache_read_input_token_cost": 2.64e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.28e-07,
-        "output_cost_per_token": 1.584e-05,
-        "output_cost_per_token_above_272k_tokens": 2.376e-05
+        "input_cost_per_token": 2.7e-06,
+        "input_cost_per_token_above_272k_tokens": 5.4e-06,
+        "cache_creation_input_token_cost": 3.375e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6.75e-06,
+        "cache_read_input_token_cost": 2.7e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5.4e-07,
+        "output_cost_per_token": 1.62e-05,
+        "output_cost_per_token_above_272k_tokens": 2.43e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html"
     },
     "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
         "litellm_provider": "bedrock_mantle",
@@ -64752,14 +68401,15 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 2.64e-07,
-        "input_cost_per_token_above_272k_tokens": 5.28e-07,
-        "cache_creation_input_token_cost": 3.3e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07,
-        "cache_read_input_token_cost": 2.64e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 5.28e-08,
-        "output_cost_per_token": 1.584e-06,
-        "output_cost_per_token_above_272k_tokens": 2.376e-06
+        "input_cost_per_token": 2.7e-07,
+        "input_cost_per_token_above_272k_tokens": 5.4e-07,
+        "cache_creation_input_token_cost": 3.375e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 6.75e-07,
+        "cache_read_input_token_cost": 2.7e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 5.4e-08,
+        "output_cost_per_token": 1.62e-06,
+        "output_cost_per_token_above_272k_tokens": 2.43e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html"
     },
     "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
         "litellm_provider": "bedrock_mantle",
@@ -64786,9 +68436,10 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 3.3e-06,
-        "cache_read_input_token_cost": 3.3e-07,
-        "output_cost_per_token": 1.98e-05
+        "input_cost_per_token": 3.375e-06,
+        "cache_read_input_token_cost": 3.375e-07,
+        "output_cost_per_token": 2.025e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html"
     },
     "bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
         "use_openai_responses_path": true,
@@ -64894,9 +68545,10 @@
         "output_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64912,9 +68564,10 @@
         "output_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64925,6 +68578,77 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 6e-06,
+        "cache_creation_input_token_cost_above_1hr": 9.6e-06,
+        "cache_read_input_token_cost": 2.4e-07,
+        "input_cost_per_token": 4.8e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-05,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true,
+        "supports_forced_tool_use": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html"
+    },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
     "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1050000,
@@ -64980,9 +68704,10 @@
         "output_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64998,9 +68723,10 @@
         "output_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -65012,91 +68738,131 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/deepseek.v3.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.8e-07,
+        "input_cost_per_token_batches": 2.9e-07,
+        "input_cost_per_token_flex": 2.9e-07,
+        "input_cost_per_token_priority": 1.015e-06,
         "output_cost_per_token": 1.68e-06,
+        "output_cost_per_token_flex": 8.4e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 8.4e-07,
+        "output_cost_per_token_priority": 2.94e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.38e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-235b-a22b-2507": {
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "input_cost_per_token_flex": 1.1e-07,
+        "input_cost_per_token_priority": 3.85e-07,
         "output_cost_per_token": 8.8e-07,
+        "output_cost_per_token_flex": 4.4e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 4.4e-07,
+        "output_cost_per_token_priority": 1.54e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-32b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 32000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_batches": 2.25e-07,
+        "input_cost_per_token_flex": 2.25e-07,
+        "input_cost_per_token_priority": 7.875e-07,
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_flex": 9e-07,
         "litellm_provider": "bedrock_mantle",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 9e-07,
+        "output_cost_per_token_priority": 3.15e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -65106,35 +68872,47 @@
     },
     "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": {
         "input_cost_per_token": 1.4e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": {
         "input_cost_per_token": 5.3e-07,
+        "input_cost_per_token_batches": 2.6e-07,
+        "input_cost_per_token_flex": 2.6e-07,
+        "input_cost_per_token_priority": 9.3e-07,
         "output_cost_per_token": 2.66e-06,
+        "output_cost_per_token_flex": 1.33e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.33e-06,
+        "output_cost_per_token_priority": 4.66e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "azure/us-gov/gpt-5.1": {
         "cache_read_input_token_cost": 1.71875e-07,
@@ -65277,7 +69055,7 @@
     "gemini/lyria-3.5": {
         "input_cost_per_token": 0,
         "litellm_provider": "gemini",
-        "max_input_tokens": 1048576,
+        "max_input_tokens": 131072,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -65385,12 +69163,12 @@
         "mode": "responses",
         "supports_web_search": true,
         "supports_function_calling": true,
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "input_cost_per_token": 4e-06,
+        "output_cost_per_token": 2e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "input_cost_per_token_above_272k_tokens": 8e-06,
+        "output_cost_per_token_above_272k_tokens": 3e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
     "perplexity/openai/gpt-5.6-terra": {
@@ -65473,6 +69251,22 @@
         "cache_read_input_token_cost": 1.25e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
+    "perplexity/openai/gpt-5-nano": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 5e-09,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-5.3-codex": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 3.5e-06,
+        "output_cost_per_token": 2.8e-05,
+        "cache_read_input_token_cost": 3.5e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
     "perplexity/google/gemini-3.1-pro-preview": {
         "litellm_provider": "perplexity",
         "mode": "responses",
@@ -65509,6 +69303,7 @@
     "perplexity/google/gemini-3.5-flash-lite": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 3e-07,
@@ -65519,6 +69314,7 @@
     "perplexity/google/gemini-3.6-flash": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 1.5e-06,
@@ -65529,6 +69325,7 @@
     "perplexity/google/gemini-3.7-flash": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 7.5e-07,
@@ -65652,675 +69449,6 @@
         "cache_read_input_token_cost": 2.5e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
-    "openrouter/anthropic/claude-fable-5": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "thinking_always_on": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1e-06,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "prompt_cache_min_tokens": 512,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-fable-5.1": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "thinking_always_on": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.5e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "prompt_cache_min_tokens": 512,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.8": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 2.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-5": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-2.5-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-08,
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 1e-08,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 3e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-07,
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 9e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_audio_token": 3e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-08,
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_audio_token": 3e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.6-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.7-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.8-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/openai/gpt-4o-mini": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 7.5e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1.25e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.3-codex": {
-        "input_cost_per_token": 1.75e-06,
-        "output_cost_per_token": 1.4e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1.75e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-mini": {
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 4.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 7.5e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-nano": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna": {
-        "cache_creation_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
-        "input_cost_per_token_above_272k_tokens": 4e-07,
-        "output_cost_per_token_above_272k_tokens": 1.8e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna-pro": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 2e-08,
-        "cache_creation_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 4e-07,
-        "output_cost_per_token_above_272k_tokens": 1.8e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra-pro": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o4-mini": {
-        "input_cost_per_token": 1.1e-06,
-        "output_cost_per_token": 4.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.75e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.20": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 1800000,
-        "max_tokens": 1800000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.20-multi-agent": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 1800000,
-        "max_tokens": 1800000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.3": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 900000,
-        "max_tokens": 900000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.5": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.6": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-build-0.1": {
-        "input_cost_per_token": 1e-06,
-        "output_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 230400,
-        "max_tokens": 230400,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "output_cost_per_token_above_200k_tokens": 4e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
     "baseten/zai-org/GLM-5.3": {
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.4e-06,
@@ -66369,2794 +69497,21 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
-    "openrouter/minimax/minimax-m3": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 512000,
-        "max_tokens": 512000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 6e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.7-plus": {
-        "input_cost_per_token": 3.2e-07,
-        "input_cost_per_token_above_256k_tokens": 9.6e-07,
-        "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06,
-        "cache_read_input_token_cost_above_256k_tokens": 1.92e-07,
-        "output_cost_per_token_above_256k_tokens": 3.84e-06,
-        "output_cost_per_token": 1.28e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 6.4e-08,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 4e-07,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-6-astra": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra-pro": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3.8-flash": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 4.7e-07,
-        "cache_read_input_token_cost": 1.6e-08,
-        "cache_creation_input_token_cost": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-flash": {
-        "input_cost_per_token": 4.5e-08,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 2.85e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-flash-vision-exp": {
-        "input_cost_per_token": 2.2e-07,
-        "output_cost_per_token": 6.6e-07,
-        "cache_read_input_token_cost": 7e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3": {
-        "input_cost_per_token": 1.4e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 2.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943717,
-        "max_tokens": 943717,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-27b": {
-        "input_cost_per_token": 4.2e-07,
-        "output_cost_per_token": 3e-06,
-        "cache_read_input_token_cost": 8.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-2.4t-a95b": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-lightning:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-max": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/qwen/qwen3.8-max",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/qwen/qwen3.8-max-0902": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-max-prime": {
-        "input_cost_per_token": 4e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_video_input": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/deepseek/deepseek-v4-flash-0731": {
-        "input_cost_per_token": 3e-08,
-        "output_cost_per_token": 3.2e-07,
-        "cache_read_input_token_cost": 1.6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.7-flash": {
-        "input_cost_per_token": 3e-08,
-        "input_cost_per_token_above_32k_tokens": 1e-07,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07,
-        "cache_read_input_token_cost_above_32k_tokens": 2e-08,
-        "output_cost_per_token_above_32k_tokens": 4e-07,
-        "output_cost_per_token": 1.3e-07,
-        "cache_read_input_token_cost": 6e-09,
-        "cache_creation_input_token_cost": 3.8e-08,
-        "input_cost_per_token_above_256k_tokens": 2e-07,
-        "output_cost_per_token_above_256k_tokens": 8e-07,
-        "cache_read_input_token_cost_above_256k_tokens": 4e-08,
-        "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-s-2.1": {
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 1.8e-07,
-        "cache_read_input_token_cost": 9e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-s-2.1:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k3": {
-        "input_cost_per_token": 3e-06,
-        "output_cost_per_token": 1.5e-05,
-        "cache_read_input_token_cost": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-xs-2.1": {
-        "input_cost_per_token": 6e-08,
-        "output_cost_per_token": 1.2e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-xs-2.1:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-3.1-flash-lite-image": {
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 1.5e-06,
-        "output_cost_per_image_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-flash-image": {
-        "input_cost_per_token": 5e-07,
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_image_token": 6e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3-pro-image": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "output_cost_per_image_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-5.2": {
-        "input_cost_per_token": 6.496e-07,
-        "output_cost_per_token": 2.0416e-06,
-        "cache_read_input_token_cost": 1.2064e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.2:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.7-code": {
-        "input_cost_per_token": 6.562e-07,
-        "output_cost_per_token": 3.3e-06,
-        "cache_read_input_token_cost": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-content-safety": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-content-safety:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-ultra-550b-a55b": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 182520,
-        "max_tokens": 182520,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m3:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/minimax/minimax-m3:free",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "openrouter/qwen/qwen3.7-max": {
-        "input_cost_per_token": 1.475e-06,
-        "output_cost_per_token": 4.425e-06,
-        "cache_read_input_token_cost": 2.95e-07,
-        "cache_creation_input_token_cost": 1.84375e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3-5": {
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-plus-20260420": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.8e-06,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "input_cost_per_token_above_256k_tokens": 3.75e-07,
-        "output_cost_per_token_above_256k_tokens": 2.25e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-flash": {
-        "input_cost_per_token": 1.875e-07,
-        "output_cost_per_token": 1.125e-06,
-        "cache_creation_input_token_cost": 2.34375e-07,
-        "input_cost_per_token_above_256k_tokens": 7.5e-07,
-        "output_cost_per_token_above_256k_tokens": 3e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-35b-a3b": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-max-preview": {
-        "input_cost_per_token": 1.027e-06,
-        "output_cost_per_token": 6.162e-06,
-        "cache_creation_input_token_cost": 1.28375e-06,
-        "input_cost_per_token_above_128k_tokens": 1.58e-06,
-        "output_cost_per_token_above_128k_tokens": 9.48e-06,
-        "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-27b": {
-        "input_cost_per_token": 3.2e-07,
-        "output_cost_per_token": 2.7e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 262140,
-        "max_tokens": 262140,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5.5-pro": {
-        "input_cost_per_token": 3e-05,
-        "output_cost_per_token": 0.00018,
-        "input_cost_per_token_above_272k_tokens": 6e-05,
-        "output_cost_per_token_above_272k_tokens": 0.00027,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-chat-latest": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/deepseek/deepseek-v4-flash": {
-        "input_cost_per_token": 4.9e-08,
-        "output_cost_per_token": 9.8e-08,
-        "cache_read_input_token_cost": 9.8e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.6": {
-        "input_cost_per_token": 9.5e-07,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 1.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-26b-a4b-it": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-26b-a4b-it:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-31b-it": {
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3.4e-07,
-        "cache_read_input_token_cost": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-31b-it:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5v-turbo": {
-        "input_cost_per_token": 1.2e-06,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 2.4e-07,
-        "deprecation_date": "2098-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202752,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.7": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.7:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 196608,
-        "max_output_tokens": 176947,
-        "max_tokens": 176947,
-        "mode": "chat",
-        "source": "https://openrouter.ai/minimax/minimax-m2.7:free",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false
-    },
-    "openrouter/mistralai/mistral-small-2603": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 1.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5-turbo": {
-        "input_cost_per_token": 1.2e-06,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 2.4e-07,
-        "deprecation_date": "2098-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202752,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-super-120b-a12b": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-super-120b-a12b:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-9b": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5.4-pro": {
-        "input_cost_per_token": 3e-05,
-        "output_cost_per_token": 0.00018,
-        "input_cost_per_token_above_272k_tokens": 6e-05,
-        "output_cost_per_token_above_272k_tokens": 0.00027,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-flash-image-preview": {
-        "input_cost_per_token": 5e-07,
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_image_token": 6e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-pro-preview-customtools": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/qwen/qwen3-max-thinking": {
-        "input_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_32k_tokens": 1.56e-06,
-        "output_cost_per_token_above_32k_tokens": 7.8e-06,
-        "output_cost_per_token": 3.9e-06,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-next": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 8e-07,
-        "cache_read_input_token_cost": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2-her": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-audio": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "input_cost_per_audio_token": 3.2e-05,
-        "output_cost_per_audio_token": 6.4e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-audio-mini": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "input_cost_per_audio_token": 6e-07,
-        "output_cost_per_audio_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-nano-30b-a3b": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 2e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.6v": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 9e-07,
-        "cache_read_input_token_cost": 5.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-3-pro-image-preview": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "output_cost_per_image_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex-mini": {
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/moonshotai/kimi-k2-thinking": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.5e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/voxtral-small-24b-2507": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_audio_token": 0.0001,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 26214,
-        "max_tokens": 26214,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-safeguard-20b": {
-        "input_cost_per_token": 7.5e-08,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 3.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-32b-instruct": {
-        "input_cost_per_token": 1.04e-07,
-        "output_cost_per_token": 4.16e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-8b-thinking": {
-        "input_cost_per_token": 1.8e-07,
-        "output_cost_per_token": 2.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-8b-instruct": {
-        "input_cost_per_token": 1.17e-07,
-        "output_cost_per_token": 4.55e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash-image": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 2.5e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "deprecation_date": "2027-03-15",
-        "input_cost_per_audio_token": 1e-06,
-        "output_cost_per_image_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3-vl-30b-a3b-thinking": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-30b-a3b-instruct": {
-        "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 5.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5-pro": {
-        "input_cost_per_token": 1.5e-05,
-        "output_cost_per_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3-vl-235b-a22b-thinking": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-235b-a22b-instruct": {
-        "input_cost_per_token": 2.1e-07,
-        "output_cost_per_token": 1.9e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-max": {
-        "input_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_32k_tokens": 1.56e-06,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06,
-        "cache_read_input_token_cost_above_32k_tokens": 3.12e-07,
-        "output_cost_per_token_above_32k_tokens": 7.8e-06,
-        "output_cost_per_token": 3.9e-06,
-        "cache_read_input_token_cost": 1.56e-07,
-        "cache_creation_input_token_cost": 9.75e-07,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 3.9e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.1-terminus": {
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 1.35e-07,
-        "deprecation_date": "2026-09-28",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-flash": {
-        "input_cost_per_token": 1.95e-07,
-        "input_cost_per_token_above_32k_tokens": 3.25e-07,
-        "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07,
-        "cache_read_input_token_cost_above_32k_tokens": 6.5e-08,
-        "output_cost_per_token_above_32k_tokens": 1.625e-06,
-        "output_cost_per_token": 9.75e-07,
-        "cache_read_input_token_cost": 3.9e-08,
-        "cache_creation_input_token_cost": 2.4375e-07,
-        "input_cost_per_token_above_128k_tokens": 5.2e-07,
-        "output_cost_per_token_above_128k_tokens": 2.6e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 1.04e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-next-80b-a3b-thinking": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-next-80b-a3b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 1.1e-06,
-        "cache_read_input_token_cost": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-plus-2025-07-28": {
-        "cache_creation_input_token_cost": 3.25e-07,
-        "cache_read_input_token_cost": 5.2e-08,
-        "input_cost_per_token": 2.6e-07,
-        "output_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_256k_tokens": 7.8e-07,
-        "output_cost_per_token_above_256k_tokens": 2.34e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2-0905": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b-thinking-2507": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 81920,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3.1": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5v": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 1.8e-06,
-        "cache_read_input_token_cost": 1.1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/codestral-2508": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 9e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 204800,
-        "max_tokens": 204800,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-30b-a3b-instruct": {
-        "input_cost_per_token": 7e-08,
-        "output_cost_per_token": 2.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b-instruct-2507": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.2e-06,
-        "cache_read_input_token_cost": 1.1e-07,
-        "deprecation_date": "2026-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5-air": {
-        "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 8.5e-07,
-        "cache_read_input_token_cost": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2": {
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m1": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 40000,
-        "max_tokens": 40000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o3-pro": {
-        "input_cost_per_token": 2e-05,
-        "output_cost_per_token": 8e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-2.5-pro-preview": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/mistralai/mistral-medium-3": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-pro-preview-05-06": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/meta-llama/llama-guard-4-12b": {
-        "input_cost_per_token": 1.8e-07,
-        "output_cost_per_token": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-8b": {
-        "input_cost_per_token": 1.17e-07,
-        "output_cost_per_token": 4.55e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-14b": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 2.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-32b": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 2.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b": {
-        "input_cost_per_token": 4.55e-07,
-        "output_cost_per_token": 1.82e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o4-mini-high": {
-        "input_cost_per_token": 1.1e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 2.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta-llama/llama-4-maverick": {
-        "input_cost_per_token": 1.875e-07,
-        "output_cost_per_token": 6.525e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-4-scout": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o1-pro": {
-        "input_cost_per_token": 0.00015,
-        "output_cost_per_token": 0.0006,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemma-3-4b-it": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-3-12b-it": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-3-27b-it": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 4.5e-07,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-saba": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 26214,
-        "max_tokens": 26214,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen2.5-vl-72b-instruct": {
-        "input_cost_per_token": 8e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-plus": {
-        "input_cost_per_token": 2.6e-07,
-        "output_cost_per_token": 7.8e-07,
-        "cache_read_input_token_cost": 5.2e-08,
-        "cache_creation_input_token_cost": 3.25e-07,
-        "input_cost_per_token_above_256k_tokens": 7.8e-07,
-        "output_cost_per_token_above_256k_tokens": 2.34e-06,
-        "cache_read_input_token_cost_above_256k_tokens": 1.56e-07,
-        "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-24b-instruct-2501": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1-distill-llama-70b": {
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 8e-07,
-        "output_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 7372,
-        "max_tokens": 7372,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-01": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000192,
-        "max_output_tokens": 900172,
-        "max_tokens": 900172,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.3-70b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-2024-11-20": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/mistralai/mistral-large-2407": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-2.5-7b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.2-1b-instruct": {
-        "input_cost_per_token": 2.7e-08,
-        "output_cost_per_token": 2.01e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 60000,
-        "max_output_tokens": 54000,
-        "max_tokens": 54000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.2-3b-instruct": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 3.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-2.5-72b-instruct": {
-        "input_cost_per_token": 3.6e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-2024-08-06": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/meta-llama/llama-3.1-70b-instruct": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.1-8b-instruct": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 8e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-nemo": {
-        "input_cost_per_token": 1.9e-08,
-        "output_cost_per_token": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-mini-2024-07-18": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/google/gemma-2-27b-it": {
-        "input_cost_per_token": 6.5e-07,
-        "output_cost_per_token": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4-turbo": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4-turbo-preview": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "source": "https://openrouter.ai/openai/gpt-4-turbo-preview",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-instruct": {
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 4095,
-        "max_output_tokens": 3685,
-        "max_tokens": 3685,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
     "together_ai/arcee-ai/trinity-mini": {
         "input_cost_per_token": 4.5e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000
     },
     "vertex_ai/gemini-2.5-flash-native-audio": {
         "deprecation_date": "2026-12-13",
         "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_image_token": 3e-06,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_video_token": 3e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
@@ -69191,7 +69546,7 @@
     },
     "vertex_ai/gemini-3.5-transcribe-live": {
         "input_cost_per_audio_token": 3.5e-06,
-        "input_cost_per_second": 8.33333333333e-05,
+        "input_cost_per_second": 8.75e-05,
         "litellm_provider": "vertex_ai",
         "mode": "audio_transcription",
         "output_cost_per_token": 2.1e-05,
@@ -69249,6 +69604,15 @@
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_reasoning": true
     },
+    "gpt-5.5-cyber-preview": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 1.25e-05,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_reasoning": true
+    },
     "gpt-rosalind-research": {
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 5e-06,
@@ -69262,45 +69626,75 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 3.5e-06,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 4096,
+        "max_tokens": 4096
     },
     "together_ai/meta-llama/Llama-3.2-1B-Instruct": {
         "input_cost_per_token": 6e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072
     },
     "together_ai/meta-llama/Llama-3.2-3B-Instruct": {
         "input_cost_per_token": 6e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072
     },
     "together_ai/Qwen/Qwen2-1.5B-Instruct": {
         "input_cost_per_token": 2e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 2e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
     },
     "together_ai/Qwen/Qwen2.5-14B-Instruct": {
         "input_cost_per_token": 8e-07,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 8e-07,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
     },
     "together_ai/Qwen/Qwen2.5-72B-Instruct": {
         "input_cost_per_token": 1.2e-06,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
+    },
+    "together_ai/Salesforce/Llama-Rank-V1": {
+        "deprecation_date": "2026-02-06",
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
         "source": "https://api.together.ai/v1/models"
     },
+    "together_ai/meta-llama/Meta-Llama-3.1-8B": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "completion",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.xyz/v1/models"
+    },
     "together_ai/together/Tev1-4B-experimental": {
-        "cache_read_input_token_cost": 4.2e-08,
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "together_ai",
         "max_input_tokens": 32768,
@@ -69510,7 +69904,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/google/gemma-4-31B-it": {
-        "deprecation_date": "2026-09-14",
+        "deprecation_date": "2026-09-15",
         "input_cost_per_token": 3.9e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
@@ -69643,6 +70037,7 @@
     },
     "together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2026-08-27",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 512288,
@@ -69652,7 +70047,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/openai/gpt-oss-20b": {
-        "deprecation_date": "2026-09-14",
+        "deprecation_date": "2026-09-15",
         "input_cost_per_token": 5e-08,
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
@@ -69707,7 +70102,7 @@
         "cache_read_input_token_cost": 4.13e-07,
         "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 6.6e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69762,6 +70157,9 @@
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_batches": 2.75e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_batches": 8.25e-06,
@@ -69787,7 +70185,7 @@
         "cache_read_input_token_cost": 1.38e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69823,7 +70221,7 @@
         "input_cost_per_token": 1.65e-05,
         "input_cost_per_token_batches": 8.25e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000132,
         "output_cost_per_token_batches": 6.6e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69833,7 +70231,7 @@
         "cache_read_input_token_cost": 1.375e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69857,7 +70255,7 @@
         "cache_read_input_token_cost": 1.925e-07,
         "input_cost_per_token": 1.925e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69865,7 +70263,7 @@
         "input_cost_per_token": 2.31e-05,
         "input_cost_per_token_batches": 1.155e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.0001848,
         "output_cost_per_token_batches": 9.24e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69877,7 +70275,7 @@
         "input_cost_per_token": 1.925e-06,
         "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "output_cost_per_token_priority": 3.08e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69916,7 +70314,7 @@
         "input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
         "input_cost_per_token_batches": 1.65e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000198,
         "output_cost_per_token_above_272k_tokens": 0.000297,
         "output_cost_per_token_above_272k_tokens_batches": 0.0001485,
@@ -69925,18 +70323,47 @@
     },
     "azure/eu/gpt-6-astra": {
         "deprecation_date": "2028-01-11",
-        "cache_creation_input_token_cost": 1.375e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
-        "cache_read_input_token_cost": 1.1e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token": 1.1e-05,
-        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.5e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 3e-05,
+        "cache_read_input_token_cost": 1.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-06,
+        "input_cost_per_token": 1.2e-05,
+        "input_cost_per_token_above_272k_tokens": 2.4e-05,
         "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 5.5e-05,
-        "output_cost_per_token_above_272k_tokens": 8.25e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
-        "supports_reasoning": true
+        "output_cost_per_token": 6e-05,
+        "output_cost_per_token_above_272k_tokens": 9e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": false,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
     },
     "azure/eu/gpt-6-luna": {
         "deprecation_date": "2028-03-11",
@@ -70046,12 +70473,29 @@
         "output_cost_per_token_batches": 2.42e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
+    "azure/eu/o3": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_batches": 1.1e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-06,
+        "output_cost_per_token_batches": 4.4e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
     "azure/eu/o3-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_batches": 1.1e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8.8e-06,
         "output_cost_per_token_batches": 4.4e-06,
@@ -70066,12 +70510,29 @@
         "output_cost_per_token": 4.4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
+    "azure/eu/o4-mini": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 3.03e-07,
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
     "azure/eu/o4-mini-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 3.03e-07,
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.84e-06,
         "output_cost_per_token_batches": 2.42e-06,
@@ -70117,7 +70578,8 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.8-live-extended-thinking": {
         "input_cost_per_audio_token": 3e-06,
@@ -70138,14 +70600,15 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "azure/us/codex-mini": {
         "deprecation_date": "2026-11-15",
         "cache_read_input_token_cost": 4.13e-07,
         "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 6.6e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70200,6 +70663,9 @@
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_batches": 2.75e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_batches": 8.25e-06,
@@ -70225,7 +70691,7 @@
         "cache_read_input_token_cost": 1.38e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70261,7 +70727,7 @@
         "input_cost_per_token": 1.65e-05,
         "input_cost_per_token_batches": 8.25e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000132,
         "output_cost_per_token_batches": 6.6e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70271,7 +70737,7 @@
         "cache_read_input_token_cost": 1.375e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70295,7 +70761,7 @@
         "cache_read_input_token_cost": 1.925e-07,
         "input_cost_per_token": 1.925e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70303,7 +70769,7 @@
         "input_cost_per_token": 2.31e-05,
         "input_cost_per_token_batches": 1.155e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.0001848,
         "output_cost_per_token_batches": 9.24e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70315,7 +70781,7 @@
         "input_cost_per_token": 1.925e-06,
         "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "output_cost_per_token_priority": 3.08e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70354,7 +70820,7 @@
         "input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
         "input_cost_per_token_batches": 1.65e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000198,
         "output_cost_per_token_above_272k_tokens": 0.000297,
         "output_cost_per_token_above_272k_tokens_batches": 0.0001485,
@@ -70496,7 +70962,7 @@
         "supports_audio_input": true
     },
     "azure/gpt-realtime-translate": {
-        "deprecation_date": "2027-05-06",
+        "deprecation_date": "2027-11-09",
         "input_cost_per_second": 0.000566666666667,
         "litellm_provider": "azure",
         "max_input_tokens": 32000,
@@ -70951,6 +71417,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "supports_web_search": true
     },
@@ -70968,6 +71435,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "supports_web_search": true
     },
@@ -71639,26 +72107,150 @@
         "supports_reasoning": true,
         "supports_vision": true
     },
-    "openrouter/typesafe/jev-1.13": {
-        "input_cost_per_token": 4.2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32000,
-        "max_output_tokens": 28800,
-        "max_tokens": 28800,
+    "bespoke/nimble-latest": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/typesafe/jev-1.13"
+        "source": "https://github.com/bespokelabsai/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "bespoke/nimble": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://ollama.com/library/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately"
+        }
+    },
+    "bespoke/bespokelabs/Bespoke-Nimble-9B": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/bespokelabsai/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/english": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/multilingual": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/typed-decisions": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "strands_decider/strands-decider-2B-hobson-v19": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "strands_decider",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19",
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "nace/drex-v1.0": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 32768,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-v1.5": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-v2.0": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-latest": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
     },
     "typesafe/jev-1.13.0": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://docs.typesafe.ai/models"
     },
+    "typesafe/jev-1.14.0": {
+        "input_cost_per_token": 4.2e-08,
+        "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.typesafe.ai/models",
+        "supports_box_questions": true
+    },
     "typesafe/jev-latest": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://docs.typesafe.ai/models"
@@ -71666,9 +72258,11 @@
     "typesafe/jev-preview": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
-        "source": "https://docs.typesafe.ai/models"
+        "source": "https://docs.typesafe.ai/models",
+        "supports_box_questions": true
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash": {
         "cache_read_input_token_cost": 3e-08,
@@ -71705,4109 +72299,109 @@
         "max_input_tokens": 1049000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://wandb.ai/site/pricing/tokens/",
+        "source": "https://docs.wandb.ai/inference/models.md",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/~anthropic/claude-fable-latest": {
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-haiku-latest": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-opus-latest": {
-        "cache_creation_input_token_cost": 5e-06,
-        "cache_creation_input_token_cost_above_1hr": 8e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-sonnet-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~deepseek/deepseek-flash-latest": {
-        "cache_read_input_token_cost": 6e-09,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~deepseek/deepseek-pro-latest": {
-        "cache_read_input_token_cost": 4.4e-08,
-        "input_cost_per_token": 1.32e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8},
-        "output_cost_per_token": 3.96e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/~deepseek/deepseek-v4-flash-latest": {
-        "cache_read_input_token_cost": 1.6e-08,
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 6.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/~google/gemini-flash-latest": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~google/gemini-pro-latest": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~moonshotai/kimi-latest": {
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~openai/gpt-astra-latest": {
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "input_cost_per_token": 1e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-luna-latest": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-mini-latest": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-sol-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-terra-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~x-ai/grok-latest": {
-        "cache_read_input_token_cost": 4e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 8e-07,
-        "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_above_200k_tokens": 3.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "output_cost_per_token": 4.8e-06,
-        "output_cost_per_token_above_200k_tokens": 9.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~z-ai/glm-flash-latest": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~z-ai/glm-latest": {
-        "cache_read_input_token_cost": 1.2142e-07,
-        "input_cost_per_token": 6.538e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2.0548e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-2.0": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.0": {
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.0-mini": {
-        "cache_read_input_token_cost": 1.8e-07,
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.5": {
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.5-mini": {
-        "cache_read_input_token_cost": 1.8e-07,
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-rp-llama-3.1-8b": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-2-lite-v1": {
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-lite-v1": {
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 300000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 2.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-micro-v1": {
-        "input_cost_per_token": 3.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-premier-v1": {
-        "cache_read_input_token_cost": 6.25e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-pro-v1": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 300000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 3.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/anthracite-org/magnum-v4-72b": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/anthropic/claude-fable-5:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-fable-5.1:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-haiku-4.5:batch": {
-        "cache_creation_input_token_cost": 6.25e-07,
-        "cache_creation_input_token_cost_above_1hr": 1e-06,
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.1:batch": {
-        "cache_creation_input_token_cost": 9.375e-06,
-        "cache_creation_input_token_cost_above_1hr": 1.5e-05,
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.5:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.6:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.7:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.8:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-5:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.5:batch": {
-        "cache_creation_input_token_cost": 1.875e-06,
-        "cache_creation_input_token_cost_above_1hr": 3e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 3e-07,
-        "input_cost_per_token": 1.5e-06,
-        "input_cost_per_token_above_200k_tokens": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.125e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.6:batch": {
-        "cache_creation_input_token_cost": 1.875e-06,
-        "cache_creation_input_token_cost_above_1hr": 3e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-5:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/arcee-ai/trinity-large-thinking": {
-        "cache_read_input_token_cost": 6e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 80000,
-        "max_tokens": 80000,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/baidu/ernie-4.5-vl-424b-a47b": {
-        "deprecation_date": "2026-10-08",
-        "input_cost_per_token": 4.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 123000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-1.6": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_above_128k_tokens": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_128k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-1.6-flash": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 7.5e-08,
-        "input_cost_per_token_above_128k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "output_cost_per_token_above_128k_tokens": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2-1-turbo": {
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-code": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 5e-07,
-        "input_cost_per_token_above_128k_tokens": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_token_above_128k_tokens": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-lite": {
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_above_128k_tokens": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_128k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-mini": {
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_128k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "output_cost_per_token_above_128k_tokens": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": {
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-a": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r-08-2024": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r-plus-08-2024": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r7b-12-2024": {
-        "input_cost_per_token": 3.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/north-mini-code:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/dots-studio/dots-3-note-preview:free": {
-        "deprecation_date": "2026-12-31",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 512000,
-        "max_output_tokens": 460800,
-        "max_tokens": 460800,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 3e-08,
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_audio_token": 1.5e-07,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-flash:batch": {
-        "cache_read_input_audio_token_cost": 1e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-pro:batch": {
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 6.25e-07,
-        "input_cost_per_token": 6.25e-07,
-        "input_cost_per_token_above_200k_tokens": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_200k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3-flash-preview:batch": {
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 2.5e-08,
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_audio_token": 2.5e-07,
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-pro-preview:batch": {
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 1.5e-08,
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_audio_token": 1.5e-07,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash:batch": {
-        "cache_read_input_audio_token_cost": 1.5e-07,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 1.5e-06,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.6-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.7-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.8-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/ibm-granite/granite-4.0-h-micro": {
-        "input_cost_per_token": 1.7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131000,
-        "max_output_tokens": 117900,
-        "max_tokens": 117900,
-        "mode": "chat",
-        "output_cost_per_token": 1.12e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/ibm-granite/granite-4.2-8b": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inception/mercury-2": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 50000,
-        "max_tokens": 50000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inception/mercury-2.5": {
-        "cache_read_input_token_cost": 4e-09,
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 260000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash": {
-        "cache_read_input_token_cost": 4.2e-09,
-        "input_cost_per_token": 2.1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6.3e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-fin": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 1.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-fin:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-sante:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-vl": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-vl:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/inference-net/schematron-v2-small": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inference-net/schematron-v2-turbo": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/kwaipilot/kat-coder-pro-v2.5": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 7.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.96e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/liquid/lfm-2.5-2.6b:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meituan/longcat-2.0": {
-        "cache_read_input_token_cost": 6e-09,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048756,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta/muse-glimmer-30b": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta/muse-spark-1.1": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.2": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.2-contributor": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.3": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.3-contributor": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/microsoft/phi-4": {
-        "input_cost_per_token": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16384,
-        "max_output_tokens": 14745,
-        "max_tokens": 14745,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/microsoft/wizardlm-2-8x22b": {
-        "input_cost_per_token": 6.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65535,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 6.2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/codestral-2508:batch": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 204800,
-        "max_tokens": 204800,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-8b-2512:batch": {
-        "cache_read_input_token_cost": 7.5e-09,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-large-2512": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-large-2512:batch": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3-5:batch": {
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3.1:batch": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-2603:batch": {
-        "cache_read_input_token_cost": 7.5e-09,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k3:batch": {
-        "cache_read_input_token_cost": 2.28e-07,
-        "input_cost_per_token": 2.28e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.14e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/morph/morph-v3-fast": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 81920,
-        "max_output_tokens": 38000,
-        "max_tokens": 38000,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/morph/morph-v3-large": {
-        "input_cost_per_token": 9e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-mini:free": {
-        "deprecation_date": "2026-09-25",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-pro:free": {
-        "deprecation_date": "2026-09-25",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-3-llama-3.1-405b": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-3-llama-3.1-70b": {
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-4-405b": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-0613": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 4095,
-        "max_output_tokens": 3685,
-        "max_tokens": 3685,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo:batch": {
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4-turbo:batch": {
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-mini:batch": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-nano:batch": {
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o-mini:batch": {
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o:batch": {
-        "cache_read_input_token_cost": 6.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-image": {
-        "cache_read_input_token_cost": 1.25e-06,
-        "input_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-image-mini": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-mini:batch": {
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-nano:batch": {
-        "cache_read_input_token_cost": 2.5e-09,
-        "input_cost_per_token": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-pro:batch": {
-        "input_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5:batch": {
-        "cache_read_input_token_cost": 6.25e-08,
-        "input_cost_per_token": 6.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1:batch": {
-        "cache_read_input_token_cost": 6.25e-08,
-        "input_cost_per_token": 6.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-pro:batch": {
-        "input_cost_per_token": 1.05e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 8.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2:batch": {
-        "cache_read_input_token_cost": 8.75e-08,
-        "input_cost_per_token": 8.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-image-2": {
-        "cache_read_input_token_cost": 2e-06,
-        "input_cost_per_token": 8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-mini:batch": {
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-nano:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6.25e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-pro:batch": {
-        "input_cost_per_token": 1.5e-05,
-        "input_cost_per_token_above_272k_tokens": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 9e-05,
-        "output_cost_per_token_above_272k_tokens": 0.000135,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4:batch": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "input_cost_per_token_above_272k_tokens": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "output_cost_per_token_above_272k_tokens": 1.125e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5-pro:batch": {
-        "input_cost_per_token": 1.5e-05,
-        "input_cost_per_token_above_272k_tokens": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 9e-05,
-        "output_cost_per_token_above_272k_tokens": 0.000135,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna-pro:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_token_above_272k_tokens": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_token_above_272k_tokens": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol-pro:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra-pro:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra-pro:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "output_cost_per_token_above_272k_tokens": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "output_cost_per_token_above_272k_tokens": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna-pro": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol-pro": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini:batch": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o4-mini:batch": {
-        "cache_read_input_token_cost": 1.375e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perceptron/perceptron-mk1": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/perplexity/sonar": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 127072,
-        "max_output_tokens": 114364,
-        "max_tokens": 114364,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-deep-research": {
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-pro": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-pro-search": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-reasoning-pro": {
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3.8-27b:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/rekaai/reka-edge": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16384,
-        "max_output_tokens": 14745,
-        "max_tokens": 14745,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/rekaai/reka-flash-3": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/relace/relace-apply-3": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/relace/relace-search": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sakana/fugu-max": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/fugu-ultra": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/fugu-ultra-v2": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/sakana-namazu": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 9.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sao10k/l3-lunaris-8b": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 7372,
-        "max_tokens": 7372,
-        "mode": "chat",
-        "output_cost_per_token": 5e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sao10k/l3.1-euryale-70b": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 8.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sao10k/l3.3-euryale-70b": {
-        "input_cost_per_token": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/stealth/space-bunny-alpha": {
-        "deprecation_date": "2098-12-31",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_video_input": true,
         "supports_vision": true
     },
-    "openrouter/stepfun/step-3.5-flash": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/stepfun/step-3.7-flash": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 230400,
-        "max_tokens": 230400,
-        "mode": "chat",
-        "output_cost_per_token": 1.15e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hunyuan-a13b-instruct": {
-        "input_cost_per_token": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 5.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-1.8b": {
-        "input_cost_per_token": 4.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.77e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-30b-a3b": {
-        "input_cost_per_token": 7.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.95e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-7b": {
-        "input_cost_per_token": 7.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.95e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy3": {
-        "cache_read_input_token_cost": 3.3e-08,
-        "input_cost_per_token": 1.32e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8},
-        "output_cost_per_token": 5.28e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy3-preview": {
-        "cache_read_input_token_cost": 6e-08,
-        "input_cost_per_token": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy4-preview": {
-        "cache_read_input_token_cost": 4.2e-08,
-        "input_cost_per_token": 8.34e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.501e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/cydonia-24b-v4.1": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/skyfall-36b-v2": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/unslopnemo-12b": {
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1024000,
-        "max_output_tokens": 819200,
-        "max_tokens": 819200,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling": {
-        "cache_read_input_token_cost": 1.7e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 471859,
-        "max_tokens": 471859,
-        "mode": "chat",
-        "output_cost_per_token": 4.05e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling-small": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling-small:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/unbiased/pareto": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-pro-3": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-pro4": {
-        "cache_read_input_token_cost": 1.8e-08,
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 524288,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-mini4": {
-        "cache_read_input_token_cost": 5e-09,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 524288,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/writer/palmyra-x5": {
-        "input_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1040000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4.3:batch": {
-        "cache_read_input_token_cost": 1.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 3.2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 900000,
-        "max_tokens": 900000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_200k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-5.3-flash:batch": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/prism-ml/ternary-bonsai-2-27b": {
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-prime": {
-        "cache_read_input_token_cost": 5.6e-07,
-        "input_cost_per_token": 2.8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 8.8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-flashx": {
-        "cache_read_input_token_cost": 9e-08,
-        "deprecation_date": "2098-12-31",
-        "input_cost_per_token": 3.7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4.7": {
-        "cache_read_input_token_cost": 4e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 8e-07,
-        "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_above_200k_tokens": 3.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "output_cost_per_token": 4.8e-06,
-        "output_cost_per_token_above_200k_tokens": 9.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
     "moonshotai.kimi-k3": {
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "global.moonshotai.kimi-k3": {
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "us.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
         "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
         "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
         "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
         "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
         "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
+        "supports_vision": true
+    },
+    "global.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_flex": 1.875e-06,
+        "cache_creation_input_token_cost_priority": 6.5625e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_flex": 1.5e-07,
+        "cache_read_input_token_cost_priority": 5.25e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_flex": 1.5e-06,
+        "input_cost_per_token_priority": 5.25e-06,
+        "litellm_provider": "bedrock_converse",
         "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "openrouter/xiaomi/mimo-v2.6-flash": {
-        "cache_read_input_token_cost": 2.8e-09,
-        "input_cost_per_token": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 2.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_flex": 7.5e-06,
+        "output_cost_per_token_priority": 2.625e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
         "supports_function_calling": true,
-        "supports_pdf_input": false,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
+        "supports_vision": true
     },
-    "openrouter/xiaomi/mimo-v2.6-pro": {
-        "cache_read_input_token_cost": 3.6e-09,
-        "input_cost_per_token": 4.35e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
+    "us.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 8.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
+        "output_cost_per_token": 1.65e-05,
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
         "supports_function_calling": true,
-        "supports_pdf_input": false,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": {
-        "cache_read_input_token_cost": 3.6e-08,
-        "input_cost_per_token": 4.35e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 8.7e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
+        "supports_vision": true
     },
     "xiaomi_mimo/mimo-v2.6-pro": {
         "cache_read_input_token_cost": 3.6e-09,
@@ -75857,13 +72451,16 @@
     },
     "xai/grok-4.20-0309": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -75871,8 +72468,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -76277,53 +72877,13 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
-    "openrouter/nex-agi/nex-n2.5-mini": {
-        "cache_read_input_token_cost": 2.5e-09,
-        "input_cost_per_token": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-pro": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
     "baseten/deepseek-ai/DeepSeek-V4.1-Flash": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "max_input_tokens": 1048576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://inference.baseten.co/v1/models",
@@ -76335,6 +72895,7 @@
         "supports_vision": true
     },
     "baseten/moonshotai/Kimi-K2.6": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.6e-07,
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
@@ -76352,6 +72913,7 @@
         "supports_vision": true
     },
     "baseten/moonshotai/Kimi-K2.7-Code": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.6e-07,
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
@@ -76403,6 +72965,7 @@
         "supports_vision": false
     },
     "baseten/thinkingmachines/inkling": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.7e-07,
         "input_cost_per_token": 1e-06,
         "litellm_provider": "baseten",
@@ -76420,6 +72983,7 @@
         "supports_vision": true
     },
     "baseten/thinkingmachines/inkling-small": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "baseten",
@@ -76488,6 +73052,7 @@
         "supports_vision": false
     },
     "baseten/deepseek-ai/DeepSeek-V4-Pro": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.45e-07,
         "input_cost_per_token": 1.74e-06,
         "litellm_provider": "baseten",
@@ -76636,13 +73201,25 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "fireworks_ai/accounts/fireworks/routers/rune": {
+        "cache_read_input_token_cost": 8.4e-09,
+        "input_cost_per_token": 4.2e-08,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.fireworks.ai"
+    },
     "fireworks_ai/accounts/fireworks/models/ember-1": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -76650,224 +73227,6 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
-    "openrouter/anthropic/claude-opus-5.5:batch": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/cohere/command-a-plus": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 192000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4.1-flash:batch": {
-        "cache_read_input_token_cost": 3.36e-09,
-        "input_cost_per_token": 1.12e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.36e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-6-luna-pro:batch": {
-        "cache_creation_input_token_cost": 6.25e-08,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07,
-        "cache_read_input_token_cost": 5e-09,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-08,
-        "input_cost_per_token": 5e-08,
-        "input_cost_per_token_above_272k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "output_cost_per_token_above_272k_tokens": 3.75e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna:batch": {
-        "cache_creation_input_token_cost": 6.25e-08,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07,
-        "cache_read_input_token_cost": 5e-09,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-08,
-        "input_cost_per_token": 5e-08,
-        "input_cost_per_token_above_272k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "output_cost_per_token_above_272k_tokens": 3.75e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol-pro:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-oss-20b:batch": {
-        "input_cost_per_token": 2.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 1.12e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-omni-flash": {
-        "cache_read_input_token_cost": 1.6e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/perceptron/perceptron-mk1.5": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 36864,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true
-    },
     "vertex_ai/gemini-2.0-flash": {
         "deprecation_date": "2026-06-01",
         "input_cost_per_audio_token": 1e-06,
@@ -77142,7 +73501,12 @@
         "cache_read_input_token_cost": 1.1e-06,
         "output_cost_per_token": 5.5e-05,
         "cache_creation_input_token_cost_above_1hr": 2.2e-05,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-mythos-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "apac.anthropic.claude-fable-5": {
         "litellm_provider": "bedrock_converse",
@@ -77164,7 +73528,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77197,7 +73561,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77241,7 +73605,12 @@
         "input_cost_per_token": 5.5e-06,
         "cache_creation_input_token_cost_above_1hr": 1.1e-05,
         "cache_read_input_token_cost": 5.5e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "apac.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77265,6 +73634,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77275,7 +73645,12 @@
         "output_cost_per_token": 2.75e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_creation_input_token_cost": 6.875e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "apac.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77308,7 +73683,12 @@
         "input_cost_per_token": 5.5e-06,
         "cache_read_input_token_cost": 5.5e-07,
         "output_cost_per_token": 2.75e-05,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "apac.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77343,7 +73723,12 @@
         "input_cost_per_token": 4.4e-06,
         "output_cost_per_token": 2.2e-05,
         "cache_read_input_token_cost": 2.2e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "apac.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -77354,7 +73739,7 @@
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -77373,7 +73758,11 @@
         "cache_read_input_token_cost": 3.3e-07,
         "cache_creation_input_token_cost": 4.125e-06,
         "input_cost_per_token": 3.3e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "apac.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77397,6 +73786,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77407,7 +73797,12 @@
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 1.1e-05,
         "cache_read_input_token_cost": 2.2e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "us.anthropic.claude-mythos-preview": {
         "litellm_provider": "bedrock_converse",
@@ -77470,6 +73865,7 @@
         "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
     "deepseek.r1-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -77477,7 +73873,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
         "supports_function_calling": false,
         "supports_reasoning": true,
         "supports_tool_choice": false
@@ -77494,61 +73890,3103 @@
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
-    "cloudflare/clef": {
-        "input_cost_per_token": 2.4e-07,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/MAI-Cyber-1-Flash": {
+        "cache_read_input_token_cost": 6e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
     },
-    "cloudflare/clef-flash": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/mistral-ocr-2505": {
+        "litellm_provider": "azure_ai",
+        "mode": "ocr",
+        "ocr_cost_per_page": 0.001,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/"
     },
-    "cloudflare/@cf/cloudflare/clef": {
-        "input_cost_per_token": 2.4e-07,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/mistral-ocr-2512": {
+        "litellm_provider": "azure_ai",
+        "mode": "ocr",
+        "ocr_cost_per_page": 0.002,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/"
     },
-    "cloudflare/@cf/cloudflare/clef-flash": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
-    "perplexity/pplx-decider-v1-27b": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "perplexity",
-        "max_input_tokens": 262144,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://docs.perplexity.ai/api-reference/decisions-post"
+    "apac.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "input_cost_per_token": 2.2e-06,
+        "output_cost_per_token": 1.1e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
-    "strands_decider/strands-decider-2B-hobson-v19": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "strands_decider",
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19",
-        "metadata": {
-            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+    "au.anthropic.claude-sonnet-5-5": {
+        "token_count_model": {
+            "model": "au.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        },
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "azure_ai/claude-sonnet-5-5": {
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-09-29",
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
+    },
+    "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
         }
     },
+    "eu.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "global.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "jp.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "perplexity/anthropic/claude-sonnet-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_adaptive_thinking": true,
+        "supports_web_search": true,
+        "supports_function_calling": true,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/anthropic/claude-fable-5-1": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-05,
+        "output_cost_per_token": 5e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/anthropic/claude-opus-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 4e-06,
+        "output_cost_per_token": 2e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6.1-sol": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-sol": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-astra": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-05,
+        "output_cost_per_token": 5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_creation_input_token_cost": 1.25e-05,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-luna": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token_above_272k_tokens": 2e-07,
+        "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/google/gemini-3.8-flash": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_sampling_params": false,
+        "input_cost_per_token": 7.5e-07,
+        "output_cost_per_token": 3.75e-06,
+        "cache_read_input_token_cost": 7.5e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/xai/grok-4.7": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 6e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "us-gov.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "us.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "us.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "vertex_ai/claude-sonnet-5-5": {
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/claude-sonnet-5-5@default": {
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "prism/deepseek-v4.1-flash": {
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token": 1.7e-07,
+        "litellm_provider": "prism",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "output_cost_per_token": 6.3e-07,
+        "source": "https://prisminference.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "prism/deepseek-v4-flash": {
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token": 1.7e-07,
+        "litellm_provider": "prism",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "output_cost_per_token": 2.1e-07,
+        "source": "https://prisminference.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "global.xai.grok-4.7": {
+        "supports_regex_lookaround": false,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_flex": 2.5e-07,
+        "cache_read_input_token_cost_priority": 8.75e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.5e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_flex": 3e-06,
+        "output_cost_per_token_priority": 1.05e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html",
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "us.xai.grok-4.7": {
+        "supports_regex_lookaround": false,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html",
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
+        "cache_read_input_token_cost": 1.4e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_creation_input_token_cost_flex": 1.25e-06,
+        "cache_creation_input_token_cost_priority": 5e-06,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 2e-07,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_flex": 2e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 4e-06,
+        "input_cost_per_token_ultrafast": 1.2e-05,
+        "litellm_provider": "openai",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_flex": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 2e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
+        "regional_processing_uplift_multiplier_eu": 1.1,
+        "regional_processing_uplift_multiplier_us": 1.1,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_tool_search": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "global.openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_ultrafast": 1.2e-05,
+        "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_sampling_params": false,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock_mantle/openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "responses",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "use_openai_responses_path": true
+    },
+    "us.openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
+        "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_sampling_params": false,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "vertex_ai/gemini-3.8-flash-tts": {
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 9e-06,
+        "output_cost_per_token": 9e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ]
+    },
+    "vertex_ai/gemini-3.8-flash-lite-tts": {
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 6e-06,
+        "output_cost_per_token": 6e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ]
+    },
+    "vertex_ai/xai/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure_ai/kimi-k2-thinking": {
+        "deprecation_date": "2026-03-29",
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_video_input": false,
+        "supports_vision": false
+    },
+    "global.zai.glm-5.3": {
+        "cache_creation_input_token_cost": 2.1e-06,
+        "cache_creation_input_token_cost_batches": 1.05e-06,
+        "cache_creation_input_token_cost_flex": 1.05e-06,
+        "cache_creation_input_token_cost_priority": 3.675e-06,
+        "cache_read_input_token_cost": 3.12e-07,
+        "cache_read_input_token_cost_batches": 1.56e-07,
+        "cache_read_input_token_cost_flex": 1.56e-07,
+        "cache_read_input_token_cost_priority": 5.46e-07,
+        "input_cost_per_token": 1.68e-06,
+        "input_cost_per_token_batches": 8.4e-07,
+        "input_cost_per_token_flex": 8.4e-07,
+        "input_cost_per_token_priority": 2.94e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.28e-06,
+        "output_cost_per_token_batches": 2.64e-06,
+        "output_cost_per_token_flex": 2.64e-06,
+        "output_cost_per_token_priority": 9.24e-06,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "us.zai.glm-5.3": {
+        "cache_creation_input_token_cost": 2.31e-06,
+        "cache_creation_input_token_cost_batches": 1.155e-06,
+        "cache_creation_input_token_cost_flex": 1.155e-06,
+        "cache_creation_input_token_cost_priority": 4.0425e-06,
+        "cache_read_input_token_cost": 3.432e-07,
+        "cache_read_input_token_cost_batches": 1.716e-07,
+        "cache_read_input_token_cost_flex": 1.716e-07,
+        "cache_read_input_token_cost_priority": 6.006e-07,
+        "input_cost_per_token": 1.848e-06,
+        "input_cost_per_token_batches": 9.24e-07,
+        "input_cost_per_token_flex": 9.24e-07,
+        "input_cost_per_token_priority": 3.234e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.808e-06,
+        "output_cost_per_token_batches": 2.904e-06,
+        "output_cost_per_token_flex": 2.904e-06,
+        "output_cost_per_token_priority": 1.0164e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "amazon.nova-2-5-sonic": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 3.3e-07,
+        "litellm_provider": "bedrock",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2.75e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
+    "azure/model-router": {
+        "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it",
+        "deprecation_date": "2027-05-20",
+        "input_cost_per_token": 1.4e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/",
+        "supports_vision": true
+    },
+    "azure/whisper": {
+        "deprecation_date": "2026-12-15",
+        "input_cost_per_second": 0.0001,
+        "litellm_provider": "azure",
+        "mode": "audio_transcription",
+        "output_cost_per_second": 0.0001,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
+    "gemini/gemini-nano-banana-2.1": {
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 4000000.0,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini-nano-banana-2.1": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "cache_read_input_token_cost_batches": 7.5e-08,
+        "cache_read_input_token_cost_priority": 2.7e-07,
+        "input_cost_per_image": 0.00168,
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "input_cost_per_token_priority": 2.7e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "output_cost_per_token_priority": 1.35e-05,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-nano-banana-2.1": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "cache_read_input_token_cost_batches": 7.5e-08,
+        "cache_read_input_token_cost_priority": 2.7e-07,
+        "input_cost_per_image": 0.00168,
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "input_cost_per_token_priority": 2.7e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "output_cost_per_token_priority": 1.35e-05,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "azure_ai/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "deprecation_date": "2027-10-05",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://docs.x.ai/developers/models/grok-4.7",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "in.moonshotai.kimi-k3": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_prompt_cache_breakpoint": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_regex_lookaround": false,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+"claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens_batches": 2.5e-07,
+        "output_cost_per_token_above_100k_tokens_batches": 1.25e-06,
+        "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07,
+        "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08,
+        "supports_anthropic_compaction": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "provider_specific_entry": {
+            "us": 1.1
+        },
+        "supports_output_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview",
+        "supports_web_search": true,
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08
+    },
+    "bedrock_mantle/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
+    },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
+    },
+    "anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "apac.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "input_cost_per_token": 1.1e-07,
+        "output_cost_per_token": 5.5e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "au.anthropic.claude-haiku-5-5": {
+        "token_count_model": {
+            "model": "au.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        },
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "azure_ai/claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2027-09-29",
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide"
+    },
+    "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "eu.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "global.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "jp.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "perplexity/anthropic/claude-haiku-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_adaptive_thinking": true,
+        "supports_web_search": true,
+        "supports_function_calling": true,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "us-gov.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "us.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "us.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "vertex_ai/claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
+    "vertex_ai/claude-haiku-5-5@default": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
+    "microsoft_365_copilot/chat": {
+        "litellm_provider": "microsoft_365_copilot",
+        "mode": "chat",
+        "supports_mid_conversation_system": true,
+        "input_cost_per_token": 0.0,
+        "output_cost_per_token": 0.0
+    },
+    "us.twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
+    "global.twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
+    "twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
     "azure_ai/Microsoft-Decision-1": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "azure_ai",
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'"
+    },
+    "gpt-rosalind-discovery": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "chatgpt/gpt-rosalind-discovery": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/responses"
+        ]
+    },
+    "azure_ai/Cohere-Embed-V5-Fast": {
+        "deprecation_date": "2027-01-23",
+        "input_cost_per_image_token": 4e-07,
+        "input_cost_per_token": 8e-08,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048.0,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/embeddings"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_embedding_image_input": true
+    },
+    "azure_ai/Cohere-Embed-V5-Pro": {
+        "deprecation_date": "2027-01-23",
+        "input_cost_per_image_token": 4e-07,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048.0,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/embeddings"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_embedding_image_input": true
+    },
+    "scaledown/extract": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_response_schema": false,
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/summarize": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/compress": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_function_calling": false,
+        "supports_vision": false
+    },
+    "scaledown/classify": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/decisions": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "vertex_ai/gemini-robotics-er-2-preview": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 5e-06,
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini-robotics-er-2-preview": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 5e-06,
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "rpm": 2000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 800000.0,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_audio_token_batches": 1e-06,
+        "input_cost_per_audio_token_priority": 3.6e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05,
+        "prompt_cache_min_tokens": 6144.0,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-4-argon-cyber-permissive": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_audio_token": 4e-06,
+        "input_cost_per_audio_token_batches": 2e-06,
+        "input_cost_per_audio_token_priority": 7.2e-06,
+        "input_cost_per_token": 4e-06,
+        "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_flex": 2e-06,
+        "input_cost_per_token_priority": 7.2e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2e-05,
+        "output_cost_per_token": 2e-05,
+        "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_flex": 1e-05,
+        "output_cost_per_token_priority": 3.6e-05,
+        "prompt_cache_min_tokens": 6144.0,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "github_copilot/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "openinfer/@oi/GLM-5.3-Flash": {
+        "max_tokens": 393216,
+        "max_input_tokens": 393216,
+        "max_output_tokens": 393216,
+        "input_cost_per_token": 1.95e-07,
+        "output_cost_per_token": 1.56e-06,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "openinfer/@oi/Qwen3.5-27B": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 1.95e-07,
+        "output_cost_per_token": 1.56e-06,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "openinfer/@oi/Qwen3.5-9B": {
+        "max_tokens": 100000,
+        "max_input_tokens": 100000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 5e-06,
+        "output_cost_per_token": 1.5e-07,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "xai/grok-voice-3.0": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "xai/grok-voice-latest": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "xai/grok-voice-2.0": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "jp.amazon.nova-2-lite-v1:0": {
+        "cache_read_input_token_cost": 9.9e-08,
+        "cache_read_input_token_cost_flex": 4.95e-08,
+        "cache_read_input_token_cost_priority": 1.7325e-07,
+        "input_cost_per_token": 3.96e-07,
+        "input_cost_per_token_batches": 1.98e-07,
+        "input_cost_per_token_flex": 1.98e-07,
+        "input_cost_per_token_priority": 6.93e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.311e-06,
+        "output_cost_per_token_batches": 1.6555e-06,
+        "output_cost_per_token_flex": 1.6555e-06,
+        "output_cost_per_token_priority": 5.79425e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json",
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-deepseek_models",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_regions": [
+            "global"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure_ai/claude-opus-5-5-fast": {
+        "cache_creation_input_token_cost": 1e-05,
+        "cache_creation_input_token_cost_above_1hr": 1.6e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-10-01",
+        "input_cost_per_token": 8e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-05,
+        "prompt_cache_min_tokens": 512.0,
+        "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02},
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_forced_tool_use": false,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true
+    },
+    "baseten/meta-models/muse-spark-open": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "wandb",
+        "max_input_tokens": 1049000,
+        "max_tokens": 943718,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-07,
+        "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "together_ai/reflection/Beam-1.0-501B-A23B": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "baseten/reflection/Beam-1.0": {
+        "cache_read_input_token_cost": 1.3e-07,
+        "input_cost_per_token": 1.3e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 4.3e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "nebius/reflection/beam": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "nebius",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1e-06,
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": {
+        "cache_read_input_token_cost": 1.4e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": {
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-sonnet-4.6": {
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2026-09-01",
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_legacy_thinking": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4-nano": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.25e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.6": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "meta/muse-image-1.0": {
+        "litellm_provider": "meta",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.01,
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits",
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "image"
+        ]
+    },
+    "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": {
+        "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 2.25e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 2.25e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_priority": 9e-07,
+        "source": "https://platform.minimax.io/docs/guides/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "meta/sam-3.1": {
+        "input_cost_per_image": 0.0025,
+        "litellm_provider": "meta",
+        "mode": "responses",
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits.md",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ]
+    },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": {
+        "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
+        "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
+        "source": "https://docs.fireworks.ai/serverless/us-only-serverless",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
     }
 }
diff --git a/litellm/proxy/guardrails/guardrail_hooks/presidio.py b/litellm/proxy/guardrails/guardrail_hooks/presidio.py
index f5e24c501f1..7eb4eadda4c 100644
--- a/litellm/proxy/guardrails/guardrail_hooks/presidio.py
+++ b/litellm/proxy/guardrails/guardrail_hooks/presidio.py
@@ -1538,7 +1538,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail):
 
     def _unmask_responses_api_completed_chunk(self, chunk: object, pii_tokens: dict[str, str]) -> None:
         """
-        Unmask PII tokens in-place for a ``response.completed`` Responses API event.
+        Unmask PII tokens in-place for a ``response.completed`` / ``response.incomplete`` Responses API event.
 
         The chunk carries a ``response`` attribute (ResponsesAPIResponse) whose
         ``output`` list holds message items.  Each item has a ``content`` list of
@@ -1598,7 +1598,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail):
                             yield buffered_chunk
                         remaining_chunks = []
                     chunk_type = getattr(chunk, "type", None)
-                    if chunk_type == "response.completed" and pii_tokens:
+                    if chunk_type in ("response.completed", "response.incomplete") and pii_tokens:
                         self._unmask_responses_api_completed_chunk(chunk, pii_tokens)
                     saw_non_chat_chunk = True
                     yield chunk
diff --git a/litellm/proxy/hooks/model_max_budget_limiter.py b/litellm/proxy/hooks/model_max_budget_limiter.py
index 7ce50bf5ead..20f7c0f3a02 100644
--- a/litellm/proxy/hooks/model_max_budget_limiter.py
+++ b/litellm/proxy/hooks/model_max_budget_limiter.py
@@ -6,8 +6,6 @@ from dataclasses import dataclass
 from types import MappingProxyType
 from typing import Final
 
-from openai.types import Batch
-
 import litellm
 from litellm._logging import verbose_proxy_logger
 from litellm.caching.caching import DualCache
@@ -16,7 +14,7 @@ from litellm.litellm_core_utils.duration_parser import duration_in_seconds
 from litellm.llms.bedrock.common_utils import get_bedrock_base_model
 from litellm.proxy._types import Litellm_EntityType, UserAPIKeyAuth
 from litellm.router_strategy.budget_limiter import RouterBudgetLimiting
-from litellm.router_utils.batch_utils import is_batch_retrieve_call_type
+from litellm.router_utils.batch_utils import batch_charged_once_marker_key, batch_id_to_charge_once
 from litellm.types.llms.openai import AllMessageValues
 from litellm.types.utils import BudgetConfig, StandardLoggingPayload
 
@@ -121,17 +119,6 @@ def model_budget_start_time_cache_key(
     return f"{_BUDGET_START_TIME_KEY_PREFIXES[entity_type]}:{entity_id}:{budget_model}:{budget_duration}"
 
 
-def batch_charged_once_marker_key(spend_key: str, batch_id: str) -> str:
-    return f"{spend_key}:batch:{batch_id}"
-
-
-def batch_id_to_charge_once(call_type: object, response_obj: object, response_cost: float) -> str | None:
-    """A finished batch reports its whole cost on every poll, so its id is charged once per counter."""
-    if response_cost <= 0 or not is_batch_retrieve_call_type(call_type):
-        return None
-    return response_obj.id if isinstance(response_obj, Batch) else None
-
-
 def resolve_model_budget(model: str, model_max_budget: Mapping[str, object]) -> ResolvedModelBudget | None:
     """Find the `model_max_budget` entry that governs `model`, or None."""
     for candidate in _budget_model_candidates(model):
diff --git a/litellm/proxy/hooks/proxy_track_cost_callback.py b/litellm/proxy/hooks/proxy_track_cost_callback.py
index 48eb8b9cf73..a1cf81e4540 100644
--- a/litellm/proxy/hooks/proxy_track_cost_callback.py
+++ b/litellm/proxy/hooks/proxy_track_cost_callback.py
@@ -1,6 +1,8 @@
 import asyncio
 import traceback
-from collections.abc import Callable, Mapping, Sequence
+from collections.abc import Callable, Generator, Mapping, Sequence
+from contextlib import contextmanager
+from contextvars import ContextVar
 from datetime import datetime, timezone
 from types import MappingProxyType
 from typing import TYPE_CHECKING, Any, Final, Protocol, cast
@@ -65,6 +67,37 @@ from litellm.utils import get_end_user_id_for_cost_tracking
 if TYPE_CHECKING:
     from litellm.proxy.utils import ProxyLogging
 
+
+class BatchAccountingOutcome:
+    def __init__(self, call_id: str) -> None:
+        self.call_id: Final = call_id
+        self.write_started = False
+        self.failed = False
+
+    @property
+    def retryable_failure(self) -> bool:
+        return self.failed and not self.write_started
+
+
+_BATCH_ACCOUNTING: Final[ContextVar[BatchAccountingOutcome | None]] = ContextVar("batch_accounting", default=None)
+_BATCH_CALLBACK_FIELDS: Final = TypeAdapter(dict[str, object])
+
+
+@contextmanager
+def track_batch_accounting(call_id: str) -> Generator[BatchAccountingOutcome, None, None]:
+    outcome: Final = BatchAccountingOutcome(call_id)
+    token: Final = _BATCH_ACCOUNTING.set(outcome)
+    try:
+        yield outcome
+    finally:
+        _BATCH_ACCOUNTING.reset(token)
+
+
+def _batch_accounting_for(call_id: object) -> BatchAccountingOutcome | None:
+    outcome: Final = _BATCH_ACCOUNTING.get()
+    return outcome if outcome is not None and call_id == outcome.call_id else None
+
+
 _UNATTRIBUTED_TRACKABLE_CALL_TYPES: Final[frozenset[str]] = frozenset(
     {
         CallTypes.pass_through.value,
@@ -383,6 +416,11 @@ class _ProxyDBLogger(CustomLogger):
             update_cache,
         )
 
+        accounting: Final = (
+            _batch_accounting_for(_BATCH_CALLBACK_FIELDS.validate_python(kwargs).get("litellm_call_id"))
+            if _BATCH_ACCOUNTING.get() is not None
+            else None
+        )
         verbose_proxy_logger.debug("INSIDE _PROXY_track_cost_callback")
         try:
             verbose_proxy_logger.debug(
@@ -403,6 +441,8 @@ class _ProxyDBLogger(CustomLogger):
                 )
                 _write_spend_metadata_to_kwargs(kwargs=kwargs, metadata=metadata)
             budget_reservation: Final = _get_budget_reservation_from_metadata(metadata=metadata)
+            if accounting is not None and budget_reservation is not None:
+                accounting.write_started = True
             if (
                 isinstance(completion_response, LiteLLMBatch)
                 and kwargs.get("call_type") == CallTypes.aretrieve_batch.value
@@ -558,6 +598,8 @@ class _ProxyDBLogger(CustomLogger):
                         f"Cost tracking failed for model={model}.\nDebug info - {cost_tracking_failure_debug_info}\nAdd custom pricing - https://docs.litellm.ai/docs/proxy/custom_pricing"
                     )
         except Exception as e:
+            if accounting is not None:
+                accounting.failed = True
             failing_model: Final = kwargs.get("model", "")
             failing_call_type: Final = kwargs.get("call_type", "")
             error_msg: Final = (
@@ -808,7 +850,15 @@ async def _update_database_and_spend_counters(
             budget_reservation=budget_reservation, response_cost=response_cost
         )
     try:
-        charged: Final = await proxy_logging_obj.db_spend_update_writer.update_database(
+        writer: Final = proxy_logging_obj.db_spend_update_writer
+        accounting: Final = (
+            _batch_accounting_for(_BATCH_CALLBACK_FIELDS.validate_python(kwargs).get("litellm_call_id"))
+            if _BATCH_ACCOUNTING.get() is not None
+            else None
+        )
+        if accounting is not None:
+            accounting.write_started = True
+        charged: Final = await writer.update_database(
             token=user_api_key,
             response_cost=response_cost,
             user_id=user_id,
diff --git a/litellm/responses/litellm_completion_transformation/streaming_iterator.py b/litellm/responses/litellm_completion_transformation/streaming_iterator.py
index 4f291165012..9f89c811467 100644
--- a/litellm/responses/litellm_completion_transformation/streaming_iterator.py
+++ b/litellm/responses/litellm_completion_transformation/streaming_iterator.py
@@ -17,7 +17,6 @@ from litellm.responses.litellm_completion_transformation.transformation import (
 from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator, stamp_responses_usage_cost
 from litellm.responses.utils import ResponsesAPIRequestUtils
 from litellm.types.llms.openai import (
-    ResponseIncompleteEvent,
     PART_UNION_TYPES,
     BaseLiteLLMOpenAIResponseObject,
     ContentPartAddedEvent,
@@ -35,6 +34,7 @@ from litellm.types.llms.openai import (
     ReasoningSummaryTextDoneEvent,
     ResponseCompletedEvent,
     ResponseCreatedEvent,
+    ResponseIncompleteEvent,
     ResponseInProgressEvent,
     ResponseInputParam,
     ResponsesAPIOptionalRequestParams,
@@ -913,7 +913,7 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
                 raise StopAsyncIteration
 
         self.finished = self.is_stream_finished()
-        response_completed_event: Final = self._emit_response_completed_event(self.litellm_model_response)
+        response_completed_event: Final = self._emit_terminal_response_event(self.litellm_model_response)
         if response_completed_event:
             # Latch so wrappers (FallbackResponsesStreamWrapper) + proxy
             # container-ownership hook can read completed_response.
@@ -1296,7 +1296,9 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
         stamp_responses_usage_cost(partial, self.litellm_logging_obj)
         return ResponseIncompleteEvent(type=ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE, response=partial)
 
-    def _emit_response_completed_event(self, litellm_model_response: ModelResponse) -> ResponseCompletedEvent | None:
+    def _emit_terminal_response_event(
+        self, litellm_model_response: ModelResponse
+    ) -> ResponseCompletedEvent | ResponseIncompleteEvent | None:
         if litellm_model_response:
             # Transform the response
             responses_api_response: Final = (
@@ -1316,6 +1318,11 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
             # Encode the response ID to match non-streaming behavior
             encoded_response: Final = self._with_encoded_response_id(responses_api_response)
 
+            if responses_api_response.status == "incomplete":
+                return ResponseIncompleteEvent(
+                    type=ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE,
+                    response=encoded_response,
+                )
             return ResponseCompletedEvent(
                 type=ResponsesAPIStreamEvents.RESPONSE_COMPLETED,
                 response=encoded_response,
diff --git a/litellm/responses/litellm_completion_transformation/transformation.py b/litellm/responses/litellm_completion_transformation/transformation.py
index bd239922fd3..484f465c954 100644
--- a/litellm/responses/litellm_completion_transformation/transformation.py
+++ b/litellm/responses/litellm_completion_transformation/transformation.py
@@ -117,6 +117,44 @@ _INCOMPLETE_REASON_BY_FINISH_REASON: Final[Mapping[str, Literal["max_output_toke
 )
 
 
+class _EchoedResponsesRequestParams(TypedDict, total=False):
+    """Responses API request fields that the response object echoes back."""
+
+    instructions: ReadOnly[str]
+    metadata: ReadOnly[dict[str, object]]
+    parallel_tool_calls: ReadOnly[bool]
+    temperature: ReadOnly[float]
+    tools: ReadOnly[list[dict[str, object]]]
+    top_p: ReadOnly[float]
+    max_output_tokens: ReadOnly[int]
+    previous_response_id: ReadOnly[str]
+    reasoning: ReadOnly[dict[str, object]]
+    text: ReadOnly[dict[str, object]]
+    truncation: ReadOnly[Literal["auto", "disabled"]]
+    user: ReadOnly[str]
+    store: ReadOnly[bool]
+
+
+_ECHOED_PARAMS_ADAPTER: Final = TypeAdapter(_EchoedResponsesRequestParams)
+
+
+def _is_echoable(name: str, value: object) -> bool:
+    try:
+        _ = _ECHOED_PARAMS_ADAPTER.validate_python({name: value})
+    except ValidationError:
+        return False
+    return True
+
+
+def _echoable_request_params(request: Mapping[str, object]) -> _EchoedResponsesRequestParams:
+    echoable: Final = {
+        name: request[name]
+        for name in _EchoedResponsesRequestParams.__optional_keys__
+        if name in request and _is_echoable(name, request[name])
+    }
+    return _ECHOED_PARAMS_ADAPTER.validate_python(echoable)
+
+
 @dataclass(frozen=True, slots=True)
 class ResponsesToolChatForm:
     chat_tools: tuple[ChatToolParam, ...]
@@ -2294,7 +2332,7 @@ class LiteLLMCompletionResponsesConfig:
             The corresponding responses API status value (one of ResponsesAPIStatus)
         """
         if finish_reason is None:
-            return "completed"
+            return "incomplete"
 
         # Map finish reasons to status
         if finish_reason in ["stop", "tool_calls", "function_call"]:
@@ -2309,11 +2347,18 @@ class LiteLLMCompletionResponsesConfig:
     def _incomplete_details_for_finish_reason(
         finish_reason: str | None,
         existing: IncompleteDetails | None,
+        completion_tokens: int | None = None,
+        max_output_tokens: int | None = None,
     ) -> IncompleteDetails | None:
         if existing is not None:
             return existing
         if finish_reason is None:
-            return None
+            hit_cap: Final = (
+                completion_tokens is not None
+                and max_output_tokens is not None
+                and completion_tokens >= max_output_tokens
+            )
+            return IncompleteDetails(reason="max_output_tokens") if hit_cap else None
         reason: Final = _INCOMPLETE_REASON_BY_FINISH_REASON.get(finish_reason)
         return IncompleteDetails(reason=reason) if reason is not None else None
 
@@ -2433,9 +2478,13 @@ class LiteLLMCompletionResponsesConfig:
         if choices and len(choices) > 0:
             finish_reason = choices[0].finish_reason
 
+        echoed: Final = _echoable_request_params(responses_api_request)
+        chat_usage: Final = getattr(chat_completion_response, "usage", None)
         incomplete_details: Final = LiteLLMCompletionResponsesConfig._incomplete_details_for_finish_reason(
             finish_reason=finish_reason,
             existing=getattr(chat_completion_response, "incomplete_details", None),
+            completion_tokens=getattr(chat_usage, "completion_tokens", None),
+            max_output_tokens=echoed.get("max_output_tokens"),
         )
 
         responses_api_response: Final[ResponsesAPIResponse] = ResponsesAPIResponse(
@@ -2445,32 +2494,33 @@ class LiteLLMCompletionResponsesConfig:
             object="response",
             error=getattr(chat_completion_response, "error", None),
             incomplete_details=incomplete_details,
-            instructions=getattr(chat_completion_response, "instructions", None),
-            metadata=getattr(chat_completion_response, "metadata", {}),
+            instructions=echoed.get("instructions"),
+            metadata=echoed.get("metadata") or {},
             output=LiteLLMCompletionResponsesConfig._transform_chat_completion_choices_to_responses_output(
                 chat_completion_response=chat_completion_response,
                 choices=getattr(chat_completion_response, "choices", []),
                 responses_api_request=responses_api_request,
             ),
-            parallel_tool_calls=getattr(chat_completion_response, "parallel_tool_calls", False),
-            temperature=getattr(chat_completion_response, "temperature", 0),
+            parallel_tool_calls=echoed.get("parallel_tool_calls", False),
+            temperature=echoed.get("temperature"),
             tool_choice=LiteLLMCompletionResponsesConfig._transform_tool_choice_for_responses_api_response(
                 responses_api_request.get("tool_choice")
             ),
-            tools=getattr(chat_completion_response, "tools", []),
-            top_p=getattr(chat_completion_response, "top_p", None),
-            max_output_tokens=getattr(chat_completion_response, "max_output_tokens", None),
-            previous_response_id=getattr(chat_completion_response, "previous_response_id", None),
-            reasoning=None,
+            tools=echoed.get("tools") or [],
+            top_p=echoed.get("top_p"),
+            max_output_tokens=echoed.get("max_output_tokens"),
+            previous_response_id=echoed.get("previous_response_id"),
+            reasoning=echoed.get("reasoning"),
             status=LiteLLMCompletionResponsesConfig._map_chat_completion_finish_reason_to_responses_status(
                 finish_reason
             ),
-            text={},
-            truncation=getattr(chat_completion_response, "truncation", None),
+            text=echoed.get("text") or {},
+            truncation=echoed.get("truncation"),
             usage=LiteLLMCompletionResponsesConfig._transform_chat_completion_usage_to_responses_usage(
                 chat_completion_response=chat_completion_response
             ),
-            user=getattr(chat_completion_response, "user", None),
+            user=echoed.get("user"),
+            store=echoed.get("store"),
         )
         responses_api_response._hidden_params = getattr(chat_completion_response, "_hidden_params", {})
 
diff --git a/litellm/responses/streaming_iterator.py b/litellm/responses/streaming_iterator.py
index c691a0118d1..0c167488318 100644
--- a/litellm/responses/streaming_iterator.py
+++ b/litellm/responses/streaming_iterator.py
@@ -1762,6 +1762,8 @@ RESPONSES_WS_LOGGED_EVENT_TYPES: Final = [
     "error",
 ]
 
+_HISTORY_TERMINAL_EVENT_TYPES: Final = frozenset({"response.completed", "response.incomplete"})
+
 RESPONSES_WS_MASKABLE_TEXT_BLOCK_TYPES: Final = frozenset({"input_text", "output_text", "text"})
 
 _RESPONSES_WS_FAILURE_EVENT_TYPES: Final = frozenset({"error", "response.failed"})
@@ -2545,7 +2547,7 @@ class ManagedResponsesWebSocketHandler:
     @staticmethod
     def _extract_response_id(completed_event: _MutableJsonObject) -> str | None:
         """
-        Pull the raw (decoded) response ID out of a ``response.completed`` event.
+        Pull the raw (decoded) response ID out of a terminal (``response.completed`` or ``response.incomplete``) event.
         Returns *None* if the event doesn't contain a usable ID.
         """
         resp_obj: Final = completed_event.get("response", {})
@@ -2561,8 +2563,8 @@ class ManagedResponsesWebSocketHandler:
         completed_event: _MutableJsonObject,
     ) -> list[dict[str, object]]:
         """
-        Convert the output items in a ``response.completed`` event into
-        Responses API message dicts suitable for the next turn's ``input``.
+        Convert output items in a terminal (``response.completed`` or ``response.incomplete``) event into Responses
+        API message dicts suitable for the next turn's ``input``.
         """
         resp_obj: Final = completed_event.get("response", {})
         if not isinstance(resp_obj, dict):
@@ -2803,11 +2805,11 @@ class ManagedResponsesWebSocketHandler:
         """
         Stream ``litellm.aresponses`` and forward every chunk over the WebSocket.
 
-        Captures the ``response.completed`` event type from the chunk object
-        directly (before serialization) to avoid a redundant JSON round-trip on
-        every chunk.  Returns the completed event dict, or ``None``.
+        Captures the first terminal (``response.completed`` or ``response.incomplete``) event from the chunk object
+        directly (before serialization) to avoid a redundant JSON round-trip on every chunk. Returns the terminal
+        event dict, or ``None``.
         """
-        completed_event: _MutableJsonObject | None = None
+        terminal_event: _MutableJsonObject | None = None
         stream_response: Final = await litellm.aresponses(model=model, **call_kwargs)
         async for chunk in stream_response:
             if chunk is None:
@@ -2817,31 +2819,31 @@ class ManagedResponsesWebSocketHandler:
             serialized = self._serialize_chunk(chunk)
             if serialized is None:
                 continue
-            if chunk_type == "response.completed" and completed_event is None:
+            if chunk_type in _HISTORY_TERMINAL_EVENT_TYPES and terminal_event is None:
                 try:
-                    completed_event = _load_json_object(serialized)
+                    terminal_event = _load_json_object(serialized)
                 except Exception:
                     pass
             try:
                 await self.websocket.send_text(serialized)
             except Exception as send_exc:
                 verbose_logger.debug("ManagedResponsesWS: error sending chunk to client: %s", send_exc)
-                return completed_event  # Client disconnected
-        return completed_event
+                return terminal_event  # Client disconnected
+        return terminal_event
 
     def _save_turn_history(
         self,
-        completed_event: _MutableJsonObject | None,
+        terminal_event: _MutableJsonObject | None,
         prior_history: list[dict[str, object]],
         current_messages: list[dict[str, object]],
     ) -> None:
-        """Store this turn in in-memory history for future previous_response_id lookups."""
-        if completed_event is None:
+        """Store this terminal (``response.completed`` or ``response.incomplete``) event for future history lookups."""
+        if terminal_event is None:
             return
-        new_response_id: Final = self._extract_response_id(completed_event)
+        new_response_id: Final = self._extract_response_id(terminal_event)
         if not new_response_id:
             return
-        output_msgs: Final = self._extract_output_messages(completed_event)
+        output_msgs: Final = self._extract_output_messages(terminal_event)
         all_messages: Final = prior_history + current_messages + output_msgs
         self._store_history(new_response_id, all_messages)
         verbose_logger.debug(
@@ -2867,7 +2869,8 @@ class ManagedResponsesWebSocketHandler:
         2. Prepend those messages to the current ``input`` so the model has full
            conversation context.
         3. After the stream completes, extract the new response ID and output
-           messages from ``response.completed`` and store them in
+           messages from the terminal (``response.completed`` or
+           ``response.incomplete``) event and store them in
            ``self._session_history`` for the next turn.
 
         This in-memory approach avoids the async DB-write race condition that
@@ -2921,13 +2924,13 @@ class ManagedResponsesWebSocketHandler:
         call_kwargs.update(self.extra_kwargs)
 
         try:
-            completed_event: Final = await self._stream_and_forward(model, call_kwargs)
+            terminal_event: Final = await self._stream_and_forward(model, call_kwargs)
         except Exception as exc:
             verbose_logger.exception("ManagedResponsesWS: error processing response.create: %s", exc)
             await self._send_error(str(exc))
             return
 
-        self._save_turn_history(completed_event, prior_history, current_messages)
+        self._save_turn_history(terminal_event, prior_history, current_messages)
 
     # ------------------------------------------------------------------
     # Main entry point
diff --git a/litellm/router.py b/litellm/router.py
index a164db71c97..d863d3fdb21 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -86,6 +86,7 @@ from litellm.litellm_core_utils.get_llm_provider_logic import (
     is_registered_custom_provider,
 )
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
+from litellm.litellm_core_utils.llm_cost_calc.utils import SERVICE_TIER_COST_KEY_SUFFIXES
 from litellm.litellm_core_utils.ptu_pricing import (
     PTU_COST_ATTRIBUTION_ENV_VAR,
     declares_ptu,
@@ -319,12 +320,14 @@ from litellm.types.utils import (
     StandardLoggingRoutingDecision,
     Usage,
     all_litellm_params,
+    is_server_derived_pricing_key,
     shared_backend_model_info,
 )
 from litellm.types.utils import ModelInfo as ModelMapInfo
 from litellm.utils import (
     CustomStreamWrapper,
     EmbeddingResponse,
+    ModelInfoLookupMiss,
     ModelResponse,
     Rules,
     function_setup,
@@ -333,6 +336,8 @@ from litellm.utils import (
     get_secret,
     get_utc_datetime,
     is_region_allowed,
+    lookup_model_info_for_registration,
+    model_info_with_pricing_overrides,
     provider_rejectable_params,
     set_live_deployment_replay,
 )
@@ -473,6 +478,8 @@ def _stream_chunks_have_generated_content(chunks: Sequence[ModelResponseStream])
 _NO_SESSION_KWARGS: Final[Mapping[str, Mapping[str, object]]] = MappingProxyType({})
 _SESSION_ADAPTER: Final = TypeAdapter(Mapping[str, object])
 _SILENT_MODEL_ADAPTER: Final = TypeAdapter(str | list[str])
+_MODEL_INFO_ADAPTER: Final = TypeAdapter(Mapping[str, object])
+_LITELLM_PARAMS_ADAPTER: Final = TypeAdapter(Mapping[str, object])
 
 
 def _as_retry_skipped_deployment_ids(value: object) -> tuple[str, ...]:
@@ -8872,34 +8879,7 @@ class Router:
                 litellm_params=litellm_params,
                 model_info=_model_info,
             )
-            for field in CustomPricingLiteLLMParams.model_fields:
-                if deployment.litellm_params.get(field) is not None:
-                    _model_info[field] = deployment.litellm_params[field]
-
-            Router._inherit_builtin_base_rates_for_off_peak(
-                model_info=_model_info,
-                backend_model=deployment.litellm_params.model,
-                custom_llm_provider=deployment.litellm_params.custom_llm_provider,
-            )
-            if _model_info.get("input_cost_per_token") is not None:
-                Router._inherit_builtin_cache_pricing(
-                    model_info=_model_info,
-                    backend_model=deployment.litellm_params.model,
-                    custom_llm_provider=deployment.litellm_params.custom_llm_provider,
-                )
-            Router._inherit_builtin_tiered_output_rate(
-                model_info=_model_info,
-                backend_model=deployment.litellm_params.model,
-                custom_llm_provider=deployment.litellm_params.custom_llm_provider,
-            )
-
-            ## REGISTER MODEL INFO IN LITELLM MODEL COST MAP
-            Router._register_deployment_in_model_cost(
-                model_id=deployment.model_info.id,
-                model_info=_model_info,
-                model=deployment.litellm_params.model,
-                custom_llm_provider=deployment.litellm_params.custom_llm_provider,
-            )
+            Router._register_deployment_pricing(deployment)
 
             ## Check if LLM Deployment is allowed for this deployment
             if self.deployment_is_active_for_environment(deployment=deployment) is not True:
@@ -9903,7 +9883,56 @@ class Router:
         return (backend_key,)
 
     @staticmethod
-    def _deployment_model_cost_payload(deployment: Deployment) -> dict:  # mutable-ok: cost-map entry
+    def _inherit_builtin_service_tier_pricing(
+        model_info: dict,  # mutable-ok: deployment cost-map entry filled in place
+        backend_model: str,
+        custom_llm_provider: str | None,
+    ) -> None:
+        """Inherit missing tier rates so a standalone entry does not fall back to custom standard rates."""
+        if ptu_terms(model_info) is not None and is_ptu_cost_attribution_enabled():
+            return
+        if all(model_info.get(field) is None for field in ("input_cost_per_token", "output_cost_per_token")):
+            return
+        try:
+            backend_info: Final = litellm.get_model_info(model=backend_model, custom_llm_provider=custom_llm_provider)
+        except Exception:  # noqa: BLE001  # get_model_info raises plain Exception for an unmapped backend model
+            return
+        backend_entry: Final = litellm.model_cost.get(backend_info.get("key") or "")
+        if not isinstance(backend_entry, dict):
+            return
+        for field, backend_value in backend_entry.items():
+            if not field.endswith(SERVICE_TIER_COST_KEY_SUFFIXES):
+                continue
+            if model_info.get(field) is not None or backend_value is None:
+                continue
+            model_info[field] = copy.deepcopy(backend_value)
+
+    @staticmethod
+    def _cost_map_backend_model(deployment: Deployment) -> str:
+        model_info_base_model: Final = deployment.model_info.base_model
+        if isinstance(model_info_base_model, str) and model_info_base_model:
+            return model_info_base_model
+        params_base_model: Final = deployment.litellm_params.get("base_model")
+        if isinstance(params_base_model, str) and params_base_model:
+            return params_base_model
+        params: Final = _LITELLM_PARAMS_ADAPTER.validate_python(deployment.litellm_params.model_dump(exclude_none=True))
+        invoked_model: Final = params.get("model_id")
+        if (
+            isinstance(invoked_model, str)
+            and invoked_model
+            and (
+                deployment.litellm_params.custom_llm_provider == "bedrock"
+                or deployment.litellm_params.model.startswith("bedrock/")
+            )
+        ):
+            profile_model: Final = invoked_model if invoked_model.startswith("bedrock/") else f"bedrock/{invoked_model}"
+            profile_info: Final = lookup_model_info_for_registration(model=profile_model, custom_llm_provider="bedrock")
+            if not isinstance(profile_info, ModelInfoLookupMiss):
+                return profile_model
+        return deployment.litellm_params.model
+
+    @staticmethod
+    def _deployment_model_cost_payload(deployment: Deployment) -> dict[str, object]:  # mutable-ok: cost-map entry
         """The ``model_info`` a deployment contributes to ``litellm.model_cost``.
 
         Custom pricing lives on ``litellm_params`` rather than ``model_info``, and
@@ -9911,25 +9940,49 @@ class Router:
         both are folded back in here. That keeps this reproducible from a
         deployment alone, which is what lets a refresh rebuild the same entries.
         """
-        model_info: Final[dict] = deployment.model_info.model_dump(exclude_none=True)  # mutable-ok: built in place
+        model_info: Final = dict(
+            _MODEL_INFO_ADAPTER.validate_python(deployment.model_info.model_dump(exclude_none=True))
+        )
         for field in CustomPricingLiteLLMParams.model_fields:
             field_value = deployment.litellm_params.get(field)
             if field_value is not None:
                 model_info[field] = field_value
+        backend_model: Final = Router._cost_map_backend_model(deployment)
+        params: Final = _LITELLM_PARAMS_ADAPTER.validate_python(deployment.litellm_params.model_dump(exclude_none=True))
+        if (
+            params.get("model_id")
+            and backend_model != deployment.litellm_params.model
+            and (
+                deployment.litellm_params.custom_llm_provider == "bedrock"
+                or deployment.litellm_params.model.startswith("bedrock/")
+            )
+        ):
+            profile_info: Final = lookup_model_info_for_registration(model=backend_model, custom_llm_provider="bedrock")
+            if not isinstance(profile_info, ModelInfoLookupMiss):
+                explicit_info: Final = _MODEL_INFO_ADAPTER.validate_python(model_info)
+                priced_info: Final = model_info_with_pricing_overrides(profile_info, explicit_info)
+                model_info.update(
+                    {key: value for key, value in priced_info.items() if is_server_derived_pricing_key(key)}
+                )
         Router._inherit_builtin_base_rates_for_off_peak(
             model_info=model_info,
-            backend_model=deployment.litellm_params.model,
+            backend_model=backend_model,
             custom_llm_provider=deployment.litellm_params.custom_llm_provider,
         )
         if model_info.get("input_cost_per_token") is not None:
             Router._inherit_builtin_cache_pricing(
                 model_info=model_info,
-                backend_model=deployment.litellm_params.model,
+                backend_model=backend_model,
                 custom_llm_provider=deployment.litellm_params.custom_llm_provider,
             )
+        Router._inherit_builtin_service_tier_pricing(
+            model_info=model_info,
+            backend_model=backend_model,
+            custom_llm_provider=deployment.litellm_params.custom_llm_provider,
+        )
         Router._inherit_builtin_tiered_output_rate(
             model_info=model_info,
-            backend_model=deployment.litellm_params.model,
+            backend_model=backend_model,
             custom_llm_provider=deployment.litellm_params.custom_llm_provider,
         )
         return model_info
diff --git a/litellm/router_strategy/budget_limiter.py b/litellm/router_strategy/budget_limiter.py
index 4e84bded9de..f68af6b21b7 100644
--- a/litellm/router_strategy/budget_limiter.py
+++ b/litellm/router_strategy/budget_limiter.py
@@ -27,6 +27,8 @@ from itertools import groupby
 from types import MappingProxyType
 from typing import Any, Final
 
+from pydantic import TypeAdapter
+
 import litellm
 from litellm._logging import verbose_router_logger
 from litellm.caching.caching import DualCache
@@ -37,6 +39,7 @@ from litellm.litellm_core_utils.core_helpers import (
 )
 from litellm.litellm_core_utils.duration_parser import duration_in_seconds
 from litellm.router_strategy.tag_based_routing import _get_tags_from_request_kwargs
+from litellm.router_utils.batch_utils import batch_charged_once_marker_key, batch_id_to_charge_once
 from litellm.router_utils.cooldown_callbacks import (
     _get_prometheus_logger_from_callbacks,
 )
@@ -46,6 +49,8 @@ from litellm.types.utils import BudgetConfig, GenericBudgetConfigType, StandardL
 from litellm.types.utils import BudgetConfig as GenericBudgetInfo
 
 DEFAULT_REDIS_SYNC_INTERVAL: Final = 1
+_CALLBACK_FIELDS: Final = TypeAdapter(dict[str, object])
+_BATCH_CHARGE_VALUES: Final = TypeAdapter(tuple[object, float])
 
 
 class _LiteLLMParamsDictView:
@@ -500,14 +505,18 @@ class RouterBudgetLimiting(CustomLogger):
         if standard_logging_payload is None:
             raise ValueError("standard_logging_payload is required")
 
-        response_cost: Final[float] = standard_logging_payload.get("response_cost", 0)
+        batch_response, response_cost = _BATCH_CHARGE_VALUES.validate_python(
+            (response_obj, _CALLBACK_FIELDS.validate_python(standard_logging_payload).get("response_cost", 0))
+        )
         model_id: Final[str] = str(standard_logging_payload.get("model_id", ""))
-        custom_llm_provider: Final[str] = kwargs.get("litellm_params", {}).get("custom_llm_provider", None)
-        if custom_llm_provider is None:
-            raise ValueError("custom_llm_provider is required")
+        custom_llm_provider: Final[str | None] = standard_logging_payload.get("custom_llm_provider")
 
-        budget_config: Final = self._get_budget_config_for_provider(custom_llm_provider)
-        if budget_config:
+        batch_id: Final = batch_id_to_charge_once(kwargs.get("call_type"), batch_response, response_cost)
+
+        budget_config: Final = (
+            self._get_budget_config_for_provider(custom_llm_provider) if custom_llm_provider is not None else None
+        )
+        if custom_llm_provider is not None and budget_config is not None:
             # increment spend for provider
             spend_key: Final = f"provider_spend:{custom_llm_provider}:{budget_config.budget_duration}"
             start_time_key: Final = f"provider_budget_start_time:{custom_llm_provider}"
@@ -516,6 +525,7 @@ class RouterBudgetLimiting(CustomLogger):
                 spend_key=spend_key,
                 start_time_key=start_time_key,
                 response_cost=response_cost,
+                batch_id=batch_id,
             )
 
         deployment_budget_config: Final = self._get_budget_config_for_deployment(model_id)
@@ -528,6 +538,7 @@ class RouterBudgetLimiting(CustomLogger):
                 spend_key=deployment_spend_key,
                 start_time_key=deployment_start_time_key,
                 response_cost=response_cost,
+                batch_id=batch_id,
             )
 
         request_tags: Final = _get_tags_from_request_kwargs(
@@ -545,6 +556,7 @@ class RouterBudgetLimiting(CustomLogger):
                         spend_key=_tag_spend_key,
                         start_time_key=_tag_start_time_key,
                         response_cost=response_cost,
+                        batch_id=batch_id,
                     )
 
     async def _increment_spend_for_key(
@@ -553,12 +565,15 @@ class RouterBudgetLimiting(CustomLogger):
         spend_key: str,
         start_time_key: str,
         response_cost: float,
+        batch_id: str | None = None,
     ):
         if budget_config.budget_duration is None:
             return
 
         current_time: Final = datetime.now(timezone.utc).timestamp()
         ttl_seconds: Final = duration_in_seconds(budget_config.budget_duration)
+        if batch_id is not None and not await self._claim_batch_charge(spend_key, batch_id, ttl_seconds):
+            return
 
         budget_start = await self._get_or_set_budget_start_time(
             start_time_key=start_time_key,
@@ -596,6 +611,17 @@ class RouterBudgetLimiting(CustomLogger):
 
         verbose_router_logger.debug("Incremented spend for %s by %s", spend_key, response_cost)
 
+    async def _claim_batch_charge(self, spend_key: str, batch_id: str, ttl_seconds: int) -> bool:
+        marker_key: Final = batch_charged_once_marker_key(spend_key=spend_key, batch_id=batch_id)
+        redis_cache: Final = self.dual_cache.redis_cache
+        if redis_cache is not None:
+            polls: Final = await redis_cache.async_increment(key=marker_key, value=1, ttl=ttl_seconds, refresh_ttl=True)
+            return polls == 1
+        local_polls: Final = await self.dual_cache.in_memory_cache.async_increment(
+            key=marker_key, value=1, ttl=ttl_seconds, refresh_ttl=True
+        )
+        return local_polls == 1
+
     async def periodic_sync_in_memory_spend_with_redis(self):
         """
         Handler that triggers sync_in_memory_spend_with_redis every DEFAULT_REDIS_SYNC_INTERVAL seconds
diff --git a/litellm/router_utils/batch_utils.py b/litellm/router_utils/batch_utils.py
index 386a2135239..50085a055b2 100644
--- a/litellm/router_utils/batch_utils.py
+++ b/litellm/router_utils/batch_utils.py
@@ -3,6 +3,8 @@ import json
 from os import PathLike
 from typing import Final
 
+from openai.types import Batch
+
 from litellm._logging import verbose_logger
 from litellm.types.llms.openai import FileTypes, OpenAIFilesPurpose
 from litellm.types.utils import CallTypes
@@ -189,3 +191,14 @@ def is_batch_retrieve_call_type(call_type: object) -> bool:
     routing strategies' own state, must not be fed from it.
     """
     return isinstance(call_type, str) and call_type in BATCH_RETRIEVE_CALL_TYPES
+
+
+def batch_charged_once_marker_key(spend_key: str, batch_id: str) -> str:
+    return f"{spend_key}:batch:{batch_id}"
+
+
+def batch_id_to_charge_once(call_type: object, response_obj: object, response_cost: float) -> str | None:
+    """A finished batch reports its whole cost on every poll, so its id is charged once per counter."""
+    if response_cost <= 0 or not is_batch_retrieve_call_type(call_type):
+        return None
+    return response_obj.id if isinstance(response_obj, Batch) else None
diff --git a/litellm/router_utils/reasoning_effort_capability.py b/litellm/router_utils/reasoning_effort_capability.py
index 1d7656f253e..c24536cd6fa 100644
--- a/litellm/router_utils/reasoning_effort_capability.py
+++ b/litellm/router_utils/reasoning_effort_capability.py
@@ -1,20 +1,17 @@
 """Resolve which reasoning_effort values a deployment, and by intersection a model group, accepts.
 
-An entry that states its levels outright in reasoning_effort_levels is read first and wins
-whole, for a model whose set the per-level flags cannot express: Kimi K3 takes low, high and max,
-and no flag can drop medium because medium has none. Every other entry answers through the
-supports_*_reasoning_effort flags below, whose polarity mirrors how a request path reads that same
-flag. medium and high are unconditional for a reasoning model. minimal and low are opt-out:
-openai/chat/gpt_5_transformation.py refuses them only when the map says false. xhigh and max are
-opt-in. none is opt-out everywhere except the azure gpt-5 family, whose config raises
-UnsupportedParamsError without an explicit true.
+An entry that states its levels outright in reasoning_effort_levels wins whole, for a model whose set
+the per-level flags cannot express (Kimi K3 takes low, high and max, and no flag can drop medium).
+Every other entry answers through its supports_*_reasoning_effort flags, read with the polarity the
+chat gate uses: medium and high are unconditional, minimal and low are opt-out (refused only on an
+explicit false), xhigh is opt-in, and none is opt-out except on the azure gpt-5 family, whose chat
+config refuses it without an explicit true.
 
-xhigh is gated on the request path by the openai and azure gpt-5 configs. max is not gated there at
-all: outside the gpt-6-astra rows every entry carrying supports_max_reasoning_effort is Claude-family,
-and anthropic/chat/transformation.py gates max on the output_config path while its reasoning_effort
-path maps any level to a thinking budget. Making max opt-in is a deliberate trade, then, since an
-explicit flag is the only signal that the tier is a real one rather than litellm rounding the level
-to a budget, and a missing flag costs advisory metadata rather than a rejected request.
+The Responses gate reads none, minimal, low and xhigh as opt-out. Neither gate judges max, which
+Chat Completions refuses and Responses honors on the gpt-6 family, so its flag is advisory and
+advertised opt-in: outside the gpt-6 rows every entry carrying supports_max_reasoning_effort is
+Claude-family, where anthropic/chat/transformation.py gates max on the output_config path, so an
+explicit flag is the only signal that the tier is real.
 
 A deployment the map describes with no effort flags at all resolves to None rather than to the
 opt-out defaults. 689 of the map's 854 reasoning entries carry no flag, and the o-series, xai and
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index c3b4ebdf58f..6671d0b65aa 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -290,6 +290,8 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     input_cost_per_token_ultrafast: ReadOnly[float | None]  # OpenAI ultrafast service tier pricing
     cache_creation_input_token_cost: float | None
     cache_creation_input_token_cost_above_200k_tokens: float | None
+    cache_creation_input_token_cost_above_100k_tokens: ReadOnly[float | None]
+    cache_creation_input_token_cost_above_1hr_above_100k_tokens: ReadOnly[float | None]
     cache_creation_input_token_cost_above_272k_tokens: float | None
     cache_creation_input_token_cost_above_272k_tokens_priority: float | None
     cache_creation_input_token_cost_above_272k_tokens_flex: float | None
@@ -304,15 +306,18 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     cache_read_input_token_cost_priority: float | None  # OpenAI priority service tier pricing
     cache_read_input_token_cost_ultrafast: ReadOnly[float | None]  # OpenAI ultrafast service tier pricing
     cache_read_input_token_cost_above_200k_tokens: float | None
+    cache_read_input_token_cost_above_100k_tokens: ReadOnly[float | None]
     cache_read_input_token_cost_above_200k_tokens_priority: float | None
     cache_read_input_token_cost_above_272k_tokens: float | None
     cache_read_input_token_cost_above_272k_tokens_priority: float | None
     cache_read_input_token_cost_above_272k_tokens_flex: float | None
     cache_read_input_token_cost_above_512k_tokens: float | None
     cache_read_input_token_cost_batches: ReadOnly[float | None]
+    cache_read_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
     cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
     cache_creation_input_token_cost_batches: ReadOnly[float | None]
     cache_creation_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None]
+    cache_creation_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
     cache_creation_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
     # Smallest prefix this model will actually cache, whatever caching mechanism its provider uses.
     # Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT.
@@ -322,6 +327,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     input_cost_per_audio_token: float | None
     input_cost_per_token_above_128k_tokens: float | None  # only for vertex ai models
     input_cost_per_token_above_200k_tokens: float | None  # only for vertex ai gemini-2.5-pro models
+    input_cost_per_token_above_100k_tokens: ReadOnly[float | None]
     input_cost_per_token_above_200k_tokens_priority: float | None
     input_cost_per_token_above_272k_tokens: float | None  # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
     input_cost_per_token_above_272k_tokens_priority: float | None
@@ -339,8 +345,10 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     input_cost_per_second: float | None  # for OpenAI Speech models
     input_cost_per_token_batches: float | None
     input_cost_per_video_token_batches: ReadOnly[float | None]
+    input_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
     input_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
     output_cost_per_token_batches: float | None
+    output_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
     output_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
     output_cost_per_token: Required[float | None]
     output_cost_per_token_flex: float | None  # OpenAI flex service tier pricing
@@ -359,6 +367,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     output_cost_per_audio_token: float | None
     output_cost_per_token_above_128k_tokens: float | None  # only for vertex ai models
     output_cost_per_token_above_200k_tokens: float | None  # only for vertex ai gemini-2.5-pro models
+    output_cost_per_token_above_100k_tokens: ReadOnly[float | None]
     output_cost_per_token_above_200k_tokens_priority: float | None
     output_cost_per_token_above_272k_tokens: float | None  # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
     output_cost_per_token_above_272k_tokens_priority: float | None
@@ -3738,6 +3747,8 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     input_cost_per_token_priority: float | None = None
     input_cost_per_token_ultrafast: float | None = None
     cache_creation_input_token_cost_above_1hr: float | None = None
+    cache_creation_input_token_cost_above_100k_tokens: float | None = None
+    cache_creation_input_token_cost_above_1hr_above_100k_tokens: float | None = None
     cache_creation_input_token_cost_above_200k_tokens: float | None = None
     cache_creation_input_token_cost_above_272k_tokens: float | None = None
     cache_creation_input_token_cost_above_272k_tokens_priority: float | None = None
@@ -3749,13 +3760,16 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     cache_read_input_token_cost_flex: float | None = None
     cache_read_input_token_cost_priority: float | None = None
     cache_read_input_token_cost_ultrafast: float | None = None
+    cache_read_input_token_cost_above_100k_tokens: float | None = None
     cache_read_input_token_cost_above_200k_tokens: float | None = None
     cache_read_input_token_cost_above_200k_tokens_priority: float | None = None
     cache_read_input_token_cost_above_272k_tokens_priority: float | None = None
     cache_read_input_token_cost_above_272k_tokens_flex: float | None = None
     cache_read_input_token_cost_batches: float | None = None
+    cache_read_input_token_cost_above_100k_tokens_batches: float | None = None
     cache_read_input_token_cost_above_272k_tokens_batches: float | None = None
     cache_creation_input_token_cost_batches: float | None = None
+    cache_creation_input_token_cost_above_100k_tokens_batches: float | None = None
     cache_creation_input_token_cost_above_200k_tokens_batches: float | None = None
     cache_creation_input_token_cost_above_272k_tokens_batches: float | None = None
     cache_read_input_audio_token_cost: float | None = None
@@ -3764,10 +3778,12 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     input_cost_per_audio_token: float | None = None
     input_cost_per_token_cache_hit: float | None = None
     input_cost_per_token_above_128k_tokens: float | None = None
+    input_cost_per_token_above_100k_tokens: float | None = None
     input_cost_per_token_above_200k_tokens: float | None = None
     input_cost_per_token_above_200k_tokens_priority: float | None = None
     input_cost_per_token_above_272k_tokens_priority: float | None = None
     input_cost_per_token_above_272k_tokens_flex: float | None = None
+    input_cost_per_token_above_100k_tokens_batches: float | None = None
     input_cost_per_token_above_272k_tokens_batches: float | None = None
     input_cost_per_query: float | None = None
     input_cost_per_image: float | None = None
@@ -3788,10 +3804,12 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     output_cost_per_token_ultrafast: float | None = None
     output_cost_per_audio_token: float | None = None
     output_cost_per_token_above_128k_tokens: float | None = None
+    output_cost_per_token_above_100k_tokens: float | None = None
     output_cost_per_token_above_200k_tokens: float | None = None
     output_cost_per_token_above_200k_tokens_priority: float | None = None
     output_cost_per_token_above_272k_tokens_priority: float | None = None
     output_cost_per_token_above_272k_tokens_flex: float | None = None
+    output_cost_per_token_above_100k_tokens_batches: float | None = None
     output_cost_per_token_above_272k_tokens_batches: float | None = None
     output_cost_per_character_above_128k_tokens: float | None = None
     output_cost_per_image: float | None = None
@@ -3858,7 +3876,7 @@ def shared_backend_model_info(model_info: dict[str, Any]) -> dict[str, Any]:
     return {k: v for k, v in model_info.items() if k in SHARED_BACKEND_MODEL_INFO_FIELDS}
 
 
-ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens$")
+ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens(?:_batches)?$")
 
 _PRICING_FIELD_EXEMPTIONS: Final[frozenset[str]] = frozenset({"output_vector_size"})
 
diff --git a/litellm/utils.py b/litellm/utils.py
index 9e93497f559..59a93965993 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -45,7 +45,7 @@ from httpx import Proxy
 from httpx._utils import get_environment_proxies
 from openai.lib import _parsing, _pydantic
 from openai.types.chat.completion_create_params import ResponseFormat
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict, TypeAdapter, ValidationError, with_config
 
 import litellm
 import litellm.litellm_core_utils
@@ -3234,6 +3234,129 @@ def _get_builtin_model_info_for_registration(model: str) -> ModelInfo | None:
 
 
 _runtime_registered_model_cost: Final[dict[str, dict[str, object]]] = {}  # mutable-ok: replayed on reload
+_runtime_registered_fields: Final[dict[str, frozenset[str]]] = {}  # mutable-ok: fields each registration set
+_runtime_registered_fields_owner: list[int] = [0]  # mutable-ok: id of the model_cost map the fields describe
+
+
+def _registered_fields_for_current_map() -> dict[str, frozenset[str]]:
+    if _runtime_registered_fields_owner[0] != id(litellm.model_cost):
+        _runtime_registered_fields.clear()
+        _runtime_registered_fields_owner[0] = id(litellm.model_cost)
+    return _runtime_registered_fields
+
+
+_RATE_TABLE: Final = TypeAdapter(Mapping[str, object])
+_RATE_TIERS: Final = TypeAdapter(tuple[Mapping[str, object], ...])
+_TOKEN_COST_FIELDS: Final = ("input_cost_per_token", "output_cost_per_token")
+_DIRECTION_RATE_FIELDS: Final = MappingProxyType(
+    {
+        "input_cost_per_token": ("input_cost_per_token",),
+        "output_cost_per_token": ("output_cost_per_token", "output_cost_per_reasoning_token"),
+    }
+)
+
+
+def _is_overridden_rate(name: str, overridden_fields: tuple[str, ...]) -> bool:
+    is_variant: Final = name.startswith(tuple(f"{rate_field}_" for rate_field in overridden_fields))
+    return name in overridden_fields or (is_variant and "_cache_" not in name)
+
+
+def _without_overridden_rates(rates: Mapping[str, object], overridden_fields: tuple[str, ...]) -> Mapping[str, object]:
+    return MappingProxyType(
+        {name: rate for name, rate in rates.items() if not _is_overridden_rate(name, overridden_fields)}
+    )
+
+
+def _rate_table_with_flat_prices(
+    name: str, table: object, overridden_fields: tuple[str, ...], flat_prices: Mapping[str, object]
+) -> object:
+    try:
+        if name == "tiered_pricing":
+            return [
+                {**_without_overridden_rates(tier, overridden_fields), **flat_prices}
+                for tier in _RATE_TIERS.validate_python(table)
+            ]
+        if name == "off_peak_pricing":
+            return dict(_without_overridden_rates(_RATE_TABLE.validate_python(table), overridden_fields))
+    except ValidationError:
+        return table
+    return table
+
+
+def _without_overridden_price_variants(
+    entry: Mapping[str, object], value: Mapping[str, object]
+) -> Mapping[str, object]:
+    flat_prices: Final = MappingProxyType(
+        {cost_field: value[cost_field] for cost_field in _TOKEN_COST_FIELDS if value.get(cost_field) is not None}
+    )
+    overridden_fields: Final = tuple(
+        itertools.chain.from_iterable(_DIRECTION_RATE_FIELDS[cost_field] for cost_field in flat_prices)
+    )
+    if not overridden_fields:
+        return entry
+    return MappingProxyType(
+        {
+            name: _rate_table_with_flat_prices(name, field_value, overridden_fields, flat_prices)
+            for name, field_value in entry.items()
+            if not _is_overridden_rate(name, overridden_fields)
+        }
+    )
+
+
+@with_config(ConfigDict(extra="allow"))
+class _PricingModelInfo(ModelInfo):
+    pass
+
+
+_PRICING_MODEL_INFO: Final = TypeAdapter(_PricingModelInfo)
+
+
+def model_info_with_pricing_overrides(model_info: ModelInfo, registration: Mapping[str, object]) -> ModelInfo:
+    from litellm.types.utils import is_server_derived_pricing_key
+
+    overrides: Final = {
+        name: value for name, value in registration.items() if value is not None and is_server_derived_pricing_key(name)
+    }
+    return _PRICING_MODEL_INFO.validate_python(
+        _update_dictionary(dict(_without_overridden_price_variants(model_info, overrides)), overrides)
+    )
+
+
+def runtime_model_cost_registrations(
+    model: str, custom_llm_provider: str
+) -> tuple[tuple[str, Mapping[str, object]], ...]:
+    names: Final = _get_potential_model_names(model, custom_llm_provider)
+    candidates: Final = (
+        model,
+        names["combined_model_name"],
+        f"{custom_llm_provider}/{names['split_model']}",
+        names["split_model"],
+        names["stripped_model_name"],
+    )
+    registered: Final = (
+        (key, litellm.model_cost.get(key), _registered_fields_for_current_map().get(key, frozenset()))
+        for key in dict.fromkeys(candidates)
+    )
+    return tuple(
+        (key, MappingProxyType({name: value for name, value in entry.items() if name in fields}))
+        for key, entry, fields in registered
+        if isinstance(entry, Mapping) and fields
+    )
+
+
+@dataclass(frozen=True, slots=True)
+class ModelInfoLookupMiss:
+    tripped: bool
+
+
+def lookup_model_info_for_registration(model: str, custom_llm_provider: str | None) -> ModelInfo | ModelInfoLookupMiss:
+    try:
+        info: Final = get_model_info(model=model, custom_llm_provider=custom_llm_provider)
+    except ModelNotMappedError:
+        return ModelInfoLookupMiss(tripped=False)
+    except Exception:
+        return ModelInfoLookupMiss(tripped=True)
+    return ModelInfoLookupMiss(tripped=False) if is_generalized_model_info(info) else info
 
 
 class _LiveDeploymentReplay:
@@ -3275,6 +3398,7 @@ def reapply_runtime_model_cost_registrations() -> None:
     have no such owner are recorded and replayed, and a registration describing
     a single request opts out of even that.
     """
+    _runtime_registered_fields.clear()
     if _LiveDeploymentReplay.callback is not None:
         _LiveDeploymentReplay.callback()
     if _runtime_registered_model_cost:
@@ -3338,7 +3462,10 @@ def register_model(
     if persist_across_reloads:
         _registrations: Final[Mapping[str, Mapping[str, object]]] = loaded_model_cost
         for _registered_key, _registered_value in _registrations.items():
-            _runtime_registered_model_cost[_registered_key] = dict(_registered_value)  # mutable-ok: caller-owned
+            _runtime_registered_model_cost[_registered_key] = _update_dictionary(
+                dict(_runtime_registered_model_cost.get(_registered_key, {})),
+                dict(_RATE_TABLE.validate_python(_registered_value)),
+            )
 
     _skip_get_model_info_providers: Final = PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO
 
@@ -3404,6 +3531,10 @@ def register_model(
         ## override / add new keys to the existing model cost dictionary
         updated_dictionary = _update_dictionary(existing_model, value)
         litellm.model_cost.setdefault(model_cost_key, {}).update(updated_dictionary)
+        registered_fields = _registered_fields_for_current_map()
+        registered_fields[str(model_cost_key)] = registered_fields.get(str(model_cost_key), frozenset()) | frozenset(
+            name for name, field_value in value.items() if field_value is not None
+        )
 
         # Invalidate case-insensitive lookup map since model_cost was modified
         _invalidate_model_cost_lowercase_map()
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index d0020004e19..98fee42de3c 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -99,22 +99,22 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md"
     },
     "ai21.jamba-1-5-mini-v1:0": {
         "deprecation_date": "2026-11-26",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md"
     },
     "ai21.jamba-instruct-v1:0": {
         "input_cost_per_token": 5e-07,
@@ -293,6 +293,7 @@
         "supports_nova_canvas_image_edit": true
     },
     "us.writer.palmyra-x4-v1:0": {
+        "deprecation_date": "2027-03-09",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -300,23 +301,25 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "us.writer.palmyra-x5-v1:0": {
+        "deprecation_date": "2027-03-21",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-x4-v1:0": {
+        "deprecation_date": "2027-03-09",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -324,42 +327,52 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-x5-v1:0": {
+        "deprecation_date": "2027-03-21",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md",
         "supports_function_calling": true,
         "supports_pdf_input": true
     },
     "writer.palmyra-vision-7b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_vision": true
     },
     "amazon.nova-lite-v1:0": {
         "cache_read_input_token_cost": 1.5e-08,
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -369,13 +382,19 @@
     },
     "amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_priority": 1.3125e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -386,16 +405,21 @@
         "supports_vision": true
     },
     "amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.125e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_image_token": 1.25e-06,
+        "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_priority": 2.1875e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_priority": 1.75e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -406,14 +430,14 @@
         "supports_vision": true
     },
     "apac.amazon.nova-2-lite-v1:0": {
-        "cache_read_input_token_cost": 8.25e-08,
-        "input_cost_per_token": 3.3e-07,
+        "cache_read_input_token_cost": 9.9e-08,
+        "input_cost_per_token": 3.96e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token": 3.311e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -424,16 +448,17 @@
         "supports_vision": true
     },
     "apac.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "source": "https://aws.amazon.com/nova/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -444,14 +469,14 @@
         "supports_vision": true
     },
     "eu.amazon.nova-2-lite-v1:0": {
-        "cache_read_input_token_cost": 8.25e-08,
-        "input_cost_per_token": 3.3e-07,
+        "cache_read_input_token_cost": 1.0725e-07,
+        "input_cost_per_token": 4.29e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token": 3.597e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -462,16 +487,17 @@
         "supports_vision": true
     },
     "eu.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "source": "https://aws.amazon.com/nova/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -483,13 +509,22 @@
     },
     "us.amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 8.25e-08,
+        "cache_read_input_token_cost_flex": 4.125e-08,
+        "cache_read_input_token_cost_priority": 1.44375e-07,
         "input_cost_per_token": 3.3e-07,
+        "input_cost_per_token_batches": 1.65e-07,
+        "input_cost_per_token_flex": 1.65e-07,
+        "input_cost_per_token_priority": 5.775e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.75e-06,
+        "output_cost_per_token_batches": 1.375e-06,
+        "output_cost_per_token_flex": 1.375e-06,
+        "output_cost_per_token_priority": 4.8125e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -500,16 +535,21 @@
         "supports_vision": true
     },
     "us.amazon.nova-2-pro-preview-20251202-v1:0": {
-        "cache_read_input_token_cost": 5.46875e-07,
-        "input_cost_per_token": 2.1875e-06,
-        "input_cost_per_image_token": 2.1875e-06,
-        "input_cost_per_audio_token": 2.1875e-06,
+        "cache_read_input_token_cost": 3.4375e-07,
+        "input_cost_per_token": 1.375e-06,
+        "input_cost_per_image_token": 1.375e-06,
+        "input_cost_per_audio_token": 1.375e-06,
+        "input_cost_per_token_batches": 6.875e-07,
+        "input_cost_per_token_priority": 2.40625e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "output_cost_per_token_priority": 1.925e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -539,26 +579,60 @@
     "amazon.nova-micro-v1:0": {
         "cache_read_input_token_cost": 8.75e-09,
         "input_cost_per_token": 3.5e-08,
+        "input_cost_per_token_batches": 1.75e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 1.4e-07,
+        "output_cost_per_token_batches": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "amazon.nova-premier-v1:0": {
+        "cache_read_input_token_cost": 6.25e-07,
+        "cache_read_input_token_cost_priority": 1.09375e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_priority": 4.375e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 10000,
+        "max_tokens": 10000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-05,
+        "output_cost_per_token_batches": 6.25e-06,
+        "output_cost_per_token_priority": 2.1875e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 8e-07,
+        "input_cost_per_token_batches": 4e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "input_cost_per_token_priority": 1.4e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_flex": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -639,16 +713,20 @@
         "mode": "image_generation"
     },
     "amazon.titan-image-generator-v2": {
+        "deprecation_date": "2026-06-30",
         "input_cost_per_image": 0.0,
         "output_cost_per_image": 0.008,
         "litellm_provider": "bedrock",
-        "mode": "image_generation"
+        "mode": "image_generation",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html"
     },
     "amazon.titan-image-generator-v2:0": {
+        "deprecation_date": "2026-06-30",
         "input_cost_per_image": 0.0,
         "output_cost_per_image": 0.008,
         "litellm_provider": "bedrock",
-        "mode": "image_generation"
+        "mode": "image_generation",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html"
     },
     "twelvelabs.marengo-embed-2-7-v1:0": {
         "deprecation_date": "2026-11-30",
@@ -738,51 +816,58 @@
         "supports_image_input": true
     },
     "twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "us.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "eu.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md",
         "supports_video_input": true
     },
     "global.twelvelabs.pegasus-1-2-v1:0": {
+        "deprecation_date": "2027-03-22",
         "input_cost_per_video_per_second": 0.00049,
         "output_cost_per_token": 7.5e-06,
         "litellm_provider": "bedrock",
         "mode": "chat",
         "supports_video_input": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md"
     },
     "amazon.titan-text-express-v1": {
-        "input_cost_per_token": 1.3e-06,
+        "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
-        "output_cost_per_token": 1.7e-06
+        "output_cost_per_token": 6e-07
     },
     "amazon.titan-text-lite-v1": {
-        "input_cost_per_token": 3e-07,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 4000,
         "max_tokens": 4000,
         "mode": "chat",
-        "output_cost_per_token": 4e-07
+        "output_cost_per_token": 2e-07
     },
     "amazon.titan-text-premier-v1:0": {
         "input_cost_per_token": 5e-07,
@@ -837,7 +922,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5e-07,
-        "output_cost_per_token_batches": 2.5e-06
+        "output_cost_per_token_batches": 2.5e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-haiku-4-5@20251001": {
         "cache_creation_input_token_cost": 1.25e-06,
@@ -869,7 +958,7 @@
     "anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
@@ -879,10 +968,6 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 3e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07
     },
@@ -891,7 +976,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -903,11 +988,7 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 3e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07
+        "supports_vision": true
     },
     "anthropic.claude-3-7-sonnet-20240620-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -999,7 +1080,11 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -1058,7 +1143,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1094,7 +1183,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1130,7 +1223,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1166,7 +1263,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1202,7 +1303,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "au.anthropic.claude-opus-4-6-v1": {
         "supports_adaptive_thinking": true,
@@ -1238,7 +1343,11 @@
         "bedrock_output_config_effort_ceiling": "max",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-6-v1",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1276,7 +1385,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-mythos-preview": {
         "cache_creation_input_token_cost": 3.4375e-05,
@@ -1334,7 +1448,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1372,7 +1491,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1410,7 +1534,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1448,7 +1577,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "anthropic.claude-fable-5": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1480,13 +1614,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1557,13 +1696,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -1634,13 +1778,18 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.375e-05,
@@ -1711,7 +1860,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -1793,7 +1942,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1833,7 +1987,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1871,7 +2030,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1911,7 +2075,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1949,7 +2118,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -1989,7 +2163,12 @@
         "prompt_cache_min_tokens": 512,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2027,7 +2206,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "eu.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2105,7 +2289,12 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "au.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2145,7 +2334,12 @@
         "prompt_cache_min_tokens": 512,
         "thinking_always_on": true,
         "supports_forced_tool_use": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2257,12 +2451,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2296,12 +2496,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2335,12 +2541,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2374,12 +2586,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2413,12 +2631,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2452,12 +2676,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "jp.anthropic.claude-opus-4-7": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2494,7 +2724,12 @@
         "supports_minimal_reasoning_effort": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 2048,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2528,12 +2763,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "global.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2567,12 +2808,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "global.anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "us.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2606,12 +2853,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "eu.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2645,12 +2898,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "eu-west-1"
+        }
     },
     "au.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2684,12 +2943,18 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "jp.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -2723,6 +2988,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -2749,7 +3015,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2763,7 +3029,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2784,7 +3054,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2798,7 +3068,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2819,7 +3093,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2833,7 +3107,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2854,7 +3132,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2868,7 +3146,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "au.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2889,7 +3171,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2903,7 +3185,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "jp.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -2924,7 +3210,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -2938,7 +3224,11 @@
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -2950,7 +3240,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -2971,18 +3261,23 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
+        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -3009,7 +3304,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "anthropic.claude-v1": {
         "input_cost_per_token": 8e-06,
@@ -3180,13 +3479,16 @@
     },
     "apac.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.1e-07,
+        "cache_read_input_token_cost_flex": 1.05e-07,
         "input_cost_per_token": 8.4e-07,
+        "input_cost_per_token_flex": 4.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.36e-06,
+        "output_cost_per_token_flex": 1.68e-06,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -3219,7 +3521,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -3231,7 +3537,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -3252,7 +3558,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "assemblyai/best": {
         "input_cost_per_second": 3.333e-05,
@@ -3276,6 +3586,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -3302,17 +3613,21 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "azure/ada": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
         "max_tokens": 8191,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/codex-mini": {
         "cache_read_input_token_cost": 3.75e-07,
@@ -3358,7 +3673,7 @@
         "supports_function_calling": true
     },
     "azure_ai/claude-haiku-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-15",
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
@@ -3378,10 +3693,11 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-opus-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-24",
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
@@ -3402,7 +3718,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-opus-4-6": {
         "deprecation_date": "2027-02-02",
@@ -3588,6 +3905,7 @@
         "cache_creation_input_token_cost": 5e-06,
         "cache_creation_input_token_cost_above_1hr": 8e-06,
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-09-18",
         "supports_adaptive_thinking": true,
         "thinking_always_on": true,
         "supports_assistant_prefill": false,
@@ -3604,7 +3922,8 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_max_reasoning_effort": true,
-        "prompt_cache_min_tokens": 512
+        "prompt_cache_min_tokens": 512,
+        "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
     },
     "azure_ai/claude-opus-4-8": {
         "deprecation_date": "2027-09-01",
@@ -3640,7 +3959,7 @@
         "prompt_cache_min_tokens": 1024
     },
     "azure_ai/claude-sonnet-4-5": {
-        "deprecation_date": "2026-10-19",
+        "deprecation_date": "2026-11-30",
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -3660,7 +3979,8 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
     },
     "azure_ai/claude-sonnet-5": {
         "deprecation_date": "2027-06-30",
@@ -3705,11 +4025,11 @@
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -3720,7 +4040,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models"
     },
     "azure/computer-use-preview": {
         "input_cost_per_token": 3e-06,
@@ -3751,9 +4072,10 @@
         "supports_vision": true
     },
     "azure/container": {
-        "code_interpreter_cost_per_session": 0.03,
+        "code_interpreter_cost_per_session": 0.033,
         "litellm_provider": "azure",
-        "mode": "chat"
+        "mode": "chat",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/"
     },
     "azure_ai/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
@@ -3805,7 +4127,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_cache_breakpoint": true,
@@ -3916,6 +4238,55 @@
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
+    "azure_ai/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "azure_ai/gpt-5.5": {
         "deprecation_date": "2027-10-26",
         "cache_read_input_token_cost": 5e-07,
@@ -3927,7 +4298,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -3965,7 +4336,7 @@
     },
     "azure_ai/gpt-chat-latest": {
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 272000,
@@ -4062,7 +4433,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4109,7 +4480,7 @@
         "input_cost_per_token_priority": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4156,7 +4527,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4204,7 +4575,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -4252,7 +4623,7 @@
         "input_cost_per_token_priority": 6e-05,
         "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -4298,7 +4669,7 @@
         "input_cost_per_token_priority": 6e-05,
         "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -4545,6 +4916,26 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/eu/gpt-4o": {
+        "deprecation_date": "2027-04-14",
+        "cache_creation_input_token_cost": 1.38e-06,
+        "cache_read_input_token_cost": 1.375e-06,
+        "input_cost_per_token": 2.75e-06,
+        "input_cost_per_token_batches": 1.375e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/gpt-4o-2024-11-20": {
         "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
@@ -4565,6 +4956,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/eu/gpt-4o-mini": {
+        "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
+        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token_batches": 8.3e-08,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
         "deprecation_date": "2027-04-14",
@@ -4606,6 +5016,7 @@
     "azure/eu/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2.2e-05,
         "cache_read_input_token_cost": 2.75e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.00011,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
@@ -4615,6 +5026,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.00022,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -4628,12 +5040,13 @@
         "input_cost_per_audio_token": 4.4e-05,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 8.8e-05,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_modalities": [
             "text",
             "audio"
@@ -4873,6 +5286,25 @@
         "supports_vision": true,
         "cache_read_input_token_cost_batches": 2.75e-09
     },
+    "azure/eu/o1": {
+        "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.65e-05,
+        "input_cost_per_token_batches": 8.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-05,
+        "output_cost_per_token_batches": 3.3e-05,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/eu/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
         "deprecation_date": "2026-11-19",
@@ -4909,6 +5341,24 @@
         "supports_prompt_caching": true,
         "supports_vision": false
     },
+    "azure/eu/o3-mini": {
+        "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/eu/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
         "deprecation_date": "2026-11-19",
@@ -5140,12 +5590,13 @@
         "supports_tool_choice": true
     },
     "azure/gpt-3.5-turbo-instruct-0914": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-35-turbo": {
         "input_cost_per_token": 5e-07,
@@ -5184,20 +5635,22 @@
         "supports_tool_choice": true
     },
     "azure/gpt-35-turbo-instruct": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-35-turbo-instruct-0914": {
-        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure_text",
         "max_input_tokens": 4097,
         "max_tokens": 4097,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-4": {
         "deprecation_date": "2025-06-06",
@@ -5274,38 +5727,41 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4-turbo": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_tool_choice": true
     },
     "azure/gpt-4-turbo-2024-04-09": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
     },
     "azure/gpt-4-turbo-vision-preview": {
-        "input_cost_per_token": 1e-05,
+        "input_cost_per_token": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3e-05,
+        "output_cost_per_token": 3.3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -5692,14 +6148,14 @@
     },
     "azure/gpt-audio-1.5": {
         "deprecation_date": "2027-08-24",
-        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
             "/v1/chat/completions"
@@ -5721,19 +6177,20 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/gpt-audio-1.5-2026-02-23": {
         "deprecation_date": "2027-08-24",
-        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -5853,13 +6310,13 @@
     "azure/gpt-4o-mini": {
         "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -5888,15 +6345,16 @@
         "supports_vision": true
     },
     "azure/gpt-4o-mini-audio-preview-2024-12-17": {
-        "input_cost_per_audio_token": 4e-05,
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
-        "output_cost_per_audio_token": 8e-05,
-        "output_cost_per_token": 1e-05,
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 6e-07,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -6079,7 +6537,7 @@
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
-        "deprecation_date": "2027-07-31",
+        "deprecation_date": "2027-06-25",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image_token": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -6090,7 +6548,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 2.4e-05,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -6114,7 +6572,7 @@
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 6e-08,
-        "deprecation_date": "2027-07-31",
+        "deprecation_date": "2027-06-25",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_image_token": 8e-07,
         "input_cost_per_token": 6e-07,
@@ -6125,7 +6583,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
-        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -6215,7 +6673,7 @@
     },
     "azure/gpt-4o-mini-transcribe": {
         "deprecation_date": "2027-06-15",
-        "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
@@ -6228,7 +6686,7 @@
     },
     "azure/gpt-4o-mini-tts": {
         "deprecation_date": "2027-06-15",
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "azure",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
@@ -6248,6 +6706,7 @@
     "azure/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2e-05,
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.0001,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
@@ -6257,6 +6716,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.0002,
         "output_cost_per_token": 2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -6269,12 +6729,13 @@
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
         "output_cost_per_audio_token": 8e-05,
         "output_cost_per_token": 2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supported_modalities": [
             "text",
             "audio"
@@ -6291,27 +6752,29 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4o-transcribe": {
-        "deprecation_date": "2026-12-31",
-        "input_cost_per_audio_token": 2.5e-06,
+        "deprecation_date": "2026-10-15",
+        "input_cost_per_audio_token": 6e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
     },
     "azure/gpt-4o-transcribe-diarize": {
         "deprecation_date": "2027-04-15",
-        "input_cost_per_audio_token": 2.5e-06,
+        "input_cost_per_audio_token": 6e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
@@ -6320,6 +6783,9 @@
         "deprecation_date": "2027-05-06",
         "input_cost_per_second": 0.0002833333333333333,
         "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "audio_transcription",
         "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper",
         "supported_endpoints": [
@@ -7374,7 +7840,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7430,7 +7896,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7480,7 +7946,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7530,7 +7996,7 @@
         "input_cost_per_token_priority": 5e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7586,7 +8052,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7636,7 +8102,7 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_priority": 3.3e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -7687,7 +8153,7 @@
         "input_cost_per_token_batches": 1.5e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -7736,7 +8202,7 @@
         "input_cost_per_token_batches": 1.5e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -8251,7 +8717,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8300,7 +8766,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8413,11 +8879,17 @@
     "azure/gpt-6-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8425,11 +8897,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8462,11 +8932,17 @@
     "azure/gpt-6-sol-2026-09-22": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8474,11 +8950,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8508,9 +8982,254 @@
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
+    "azure/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/gpt-6.1-sol-2026-09-29": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/us/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/eu/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.4e-06,
+        "input_cost_per_token_above_272k_tokens": 4.8e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "azure/apac/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-07,
+        "deprecation_date": "2028-03-11",
+        "input_cost_per_token": 2.4e-06,
+        "input_cost_per_token_above_272k_tokens": 4.8e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "azure/gpt-chat-latest": {
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8841,7 +9560,7 @@
         "supports_max_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false,
         "supports_native_streaming": true,
-        "supports_none_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -8906,10 +9625,16 @@
         "deprecation_date": "2028-03-11",
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8917,11 +9642,9 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
+        "output_cost_per_token_priority": 2.2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8953,7 +9676,7 @@
     },
     "azure/us/gpt-chat-latest": {
         "cache_read_input_token_cost": 5.5e-07,
-        "deprecation_date": "2026-12-02",
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -9228,7 +9951,7 @@
         "input_cost_per_token_batches": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9287,7 +10010,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9342,7 +10065,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9394,7 +10117,7 @@
         "input_cost_per_token_priority": 1.25e-05,
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9454,7 +10177,7 @@
         "input_cost_per_token_above_272k_tokens_priority": 2e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9513,7 +10236,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9566,7 +10289,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9620,7 +10343,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -9673,7 +10396,7 @@
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "output_cost_per_token_priority": 8.25e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 1050000,
+        "max_input_tokens": 922000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -10001,6 +10724,7 @@
         "cache_read_input_token_cost_batches": 1e-08
     },
     "azure/gpt-image-1": {
+        "cache_read_input_image_token_cost": 2.5e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
@@ -10008,28 +10732,32 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 4e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/hd/1024-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 7.629e-08,
+        "input_cost_per_pixel": 8.39233e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/hd/1024-x-1792/dall-e-3": {
-        "input_cost_per_pixel": 6.539e-08,
+        "input_cost_per_pixel": 7.19343e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/hd/1792-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 6.539e-08,
+        "input_cost_per_pixel": 7.19343e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/high/1024-x-1024/gpt-image-1": {
         "deprecation_date": "2026-10-23",
@@ -10122,6 +10850,7 @@
         ]
     },
     "azure/gpt-image-1-mini": {
+        "cache_read_input_image_token_cost": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "deprecation_date": "2027-04-07",
         "input_cost_per_image_token": 2.5e-06,
@@ -10129,12 +10858,14 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 8e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-1.5": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2026-12-16",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10142,12 +10873,15 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-1.5-2025-12-16": {
+        "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-12-16",
         "input_cost_per_token": 5e-06,
@@ -10155,12 +10889,15 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ]
     },
     "azure/gpt-image-2": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-10-21",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10168,6 +10905,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10176,6 +10914,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2.5-flare": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-09-09",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10183,6 +10922,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10191,6 +10931,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2.5-sunburst": {
+        "cache_read_input_image_token_cost": 2e-06,
         "deprecation_date": "2027-09-09",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
@@ -10198,6 +10939,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10206,6 +10948,7 @@
         "supports_pdf_input": true
     },
     "azure/gpt-image-2-2026-04-21": {
+        "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2027-10-21",
         "input_cost_per_token": 5e-06,
@@ -10213,6 +10956,7 @@
         "litellm_provider": "azure",
         "mode": "image_generation",
         "output_cost_per_image_token": 3e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -10481,7 +11225,6 @@
         },
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10550,7 +11293,6 @@
         "output_cost_per_token_batches": 4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10582,7 +11324,6 @@
         "output_cost_per_token_batches": 4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/batch",
             "/v1/responses"
         ],
@@ -10659,52 +11400,55 @@
         "output_cost_per_token": 0.0
     },
     "azure/standard/1024-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 3.81469e-08,
+        "input_cost_per_pixel": 4.19617e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/standard/1024-x-1792/dall-e-3": {
-        "input_cost_per_pixel": 4.359e-08,
+        "input_cost_per_pixel": 4.79562e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/standard/1792-x-1024/dall-e-3": {
-        "input_cost_per_pixel": 4.359e-08,
+        "input_cost_per_pixel": 4.79562e-08,
         "litellm_provider": "azure",
         "mode": "image_generation",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-3-large": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1.3e-07,
+        "input_cost_per_token": 1.43e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-3-small": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 2e-08,
+        "input_cost_per_token": 2.2e-08,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/text-embedding-ada-002": {
         "deprecation_date": "2028-02-09",
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 8191,
-        "max_tokens": 8191,
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/speech/azure-tts": {
         "input_cost_per_character": 1.5e-05,
@@ -10737,9 +11481,10 @@
     },
     "azure/tts-1-hd": {
         "deprecation_date": "2026-12-15",
-        "input_cost_per_character": 3e-05,
+        "input_cost_per_character": 3.3e-05,
         "litellm_provider": "azure",
-        "mode": "audio_speech"
+        "mode": "audio_speech",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
     },
     "azure/us/gpt-4.1-2025-04-14": {
         "deprecation_date": "2027-04-14",
@@ -10871,6 +11616,26 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/gpt-4o": {
+        "deprecation_date": "2027-04-14",
+        "cache_creation_input_token_cost": 1.38e-06,
+        "cache_read_input_token_cost": 1.375e-06,
+        "input_cost_per_token": 2.75e-06,
+        "input_cost_per_token_batches": 1.375e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_batches": 5.5e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/gpt-4o-2024-11-20": {
         "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
@@ -10891,6 +11656,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/gpt-4o-mini": {
+        "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
+        "input_cost_per_token": 1.65e-07,
+        "input_cost_per_token_batches": 8.3e-08,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
         "deprecation_date": "2027-04-14",
@@ -10932,6 +11716,7 @@
     "azure/us/gpt-4o-realtime-preview-2024-10-01": {
         "cache_creation_input_audio_token_cost": 2.2e-05,
         "cache_read_input_token_cost": 2.75e-06,
+        "deprecation_date": "2025-03-26",
         "input_cost_per_audio_token": 0.00011,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
@@ -10941,6 +11726,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 0.00022,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_audio_input": true,
         "supports_audio_output": true,
         "supports_function_calling": true,
@@ -10954,12 +11740,13 @@
         "input_cost_per_audio_token": 4.4e-05,
         "input_cost_per_token": 5.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 16000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "realtime",
-        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_audio_token": 8.8e-05,
         "output_cost_per_token": 2.2e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
         "supported_modalities": [
             "text",
             "audio"
@@ -11199,6 +11986,25 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/o1": {
+        "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.65e-05,
+        "input_cost_per_token_batches": 8.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-05,
+        "output_cost_per_token_batches": 3.3e-05,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
         "deprecation_date": "2026-11-19",
@@ -11235,6 +12041,39 @@
         "supports_prompt_caching": true,
         "supports_vision": false
     },
+    "azure/us/o3": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_batches": 1.1e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-06,
+        "output_cost_per_token_batches": 4.4e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o3-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 5.5e-07,
@@ -11268,6 +12107,24 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/us/o3-mini": {
+        "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/us/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
         "deprecation_date": "2026-11-19",
@@ -11286,6 +12143,27 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "azure/us/o4-mini": {
+        "cache_read_input_token_cost": 3.03e-07,
+        "deprecation_date": "2026-11-19",
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/us/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 3.03e-07,
         "deprecation_date": "2026-11-19",
@@ -11358,6 +12236,8 @@
     },
     "azure_ai/FLUX-1.1-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 5000,
+        "max_tokens": 5000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
         "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659",
@@ -11367,18 +12247,22 @@
     },
     "azure_ai/FLUX.1-Kontext-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 5000,
+        "max_tokens": 5000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
-        "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/",
         "supported_endpoints": [
             "/v1/images/generations"
         ]
     },
     "azure_ai/flux.2-pro": {
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
+        "max_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
-        "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supported_endpoints": [
             "/v1/images/generations"
         ]
@@ -11699,34 +12583,37 @@
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
         "mode": "image_generation",
-        "output_cost_per_image": 0.05,
+        "output_cost_per_image": 0.048,
         "output_cost_per_image_token": 4.7e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ],
-        "deprecation_date": "2026-10-01"
+        "deprecation_date": "2026-10-01",
+        "max_input_tokens": 32000
     },
     "azure_ai/MAI-Image-2.5-Flash": {
         "input_cost_per_image_token": 1.75e-06,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure_ai",
         "mode": "image_generation",
-        "output_cost_per_image": 0.0338,
-        "output_cost_per_image_token": 3.3e-05,
+        "output_cost_per_image": 0.02,
+        "output_cost_per_image_token": 1.95e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
         ],
-        "deprecation_date": "2026-10-01"
+        "deprecation_date": "2026-10-01",
+        "max_input_tokens": 32000
     },
     "azure_ai/MAI-Image-2.5-Pro": {
         "deprecation_date": "2026-10-01",
         "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image": 0.1085,
         "output_cost_per_image_token": 0.000106,
@@ -11764,11 +12651,11 @@
         "input_cost_per_token": 7.1e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.1e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
@@ -11776,8 +12663,8 @@
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -11799,6 +12686,7 @@
         "supports_vision": true
     },
     "azure_ai/Meta-Llama-3-70B-Instruct": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -11806,9 +12694,11 @@
         "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 3.7e-07,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/Meta-Llama-3.1-70B-Instruct": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_token": 2.68e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11816,10 +12706,11 @@
         "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 3.54e-06,
-        "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/Phi-3-medium-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.7e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11827,11 +12718,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.8e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-medium-4k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.7e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 4096,
@@ -11839,11 +12731,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.8e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-mini-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11851,11 +12744,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-mini-4k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 4096,
@@ -11863,11 +12757,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-small-128k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11875,11 +12770,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3-small-8k-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -11887,11 +12783,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-MoE-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.6e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11899,11 +12796,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6.4e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-mini-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11911,11 +12809,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": false
     },
     "azure_ai/Phi-3.5-vision-instruct": {
+        "deprecation_date": "2025-08-30",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -11923,7 +12822,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 5.2e-07,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -12058,6 +12957,7 @@
         "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/"
     },
     "azure_ai/MAI-DS-R1": {
+        "deprecation_date": "2026-02-27",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12065,11 +12965,12 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
     "azure_ai/cohere-rerank-v3-english": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "azure_ai",
@@ -12077,9 +12978,11 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/cohere-rerank-v3-multilingual": {
+        "deprecation_date": "2025-06-30",
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "azure_ai",
@@ -12087,7 +12990,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/cohere-rerank-v4.0-pro": {
         "input_cost_per_query": 0.0025,
@@ -12114,12 +13018,12 @@
     "azure_ai/deepseek-v3.2": {
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -12129,12 +13033,12 @@
     "azure_ai/deepseek-v3.2-speciale": {
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -12142,6 +13046,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/deepseek-v3": {
+        "deprecation_date": "2025-08-31",
         "input_cost_per_token": 1.14e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12149,7 +13054,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 4.56e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/deepseek-v4-pro": {
@@ -12190,11 +13095,11 @@
         "input_cost_per_token": 4.4e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12216,17 +13121,18 @@
             "text",
             "image"
         ],
-        "supports_embedding_image_input": true
+        "supports_embedding_image_input": true,
+        "input_cost_per_image_token": 4.7e-07
     },
     "azure_ai/grok-4": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 262000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -12239,12 +13145,12 @@
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
-        "max_output_tokens": 200000,
-        "max_tokens": 200000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12265,7 +13171,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -12315,9 +13221,9 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supports_function_calling": true,
@@ -12329,9 +13235,9 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
         "supports_function_calling": true,
@@ -12343,18 +13249,19 @@
     "azure_ai/grok-code-fast-1": {
         "input_cost_per_token": 2e-07,
         "litellm_provider": "azure_ai",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "azure_ai/jais-30b-chat": {
+        "deprecation_date": "2026-01-30",
         "input_cost_per_token": 0.0032,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 8192,
@@ -12362,9 +13269,10 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.00971,
-        "source": "https://ai.azure.com/catalog/models/jais-30b-chat"
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
     },
     "azure_ai/jamba-instruct": {
+        "deprecation_date": "2025-03-01",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 70000,
@@ -12372,6 +13280,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_tool_choice": true
     },
     "azure_ai/kimi-k2.5": {
@@ -12416,6 +13325,7 @@
         "supports_prompt_caching": true
     },
     "azure_ai/ministral-3b": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 4e-08,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12428,6 +13338,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/mistral-large": {
+        "deprecation_date": "2025-04-15",
         "input_cost_per_token": 4e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 32000,
@@ -12435,10 +13346,12 @@
         "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "azure_ai/mistral-large-2407": {
+        "deprecation_date": "2025-05-13",
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12446,7 +13359,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
@@ -12476,6 +13389,7 @@
         "supports_vision": true
     },
     "azure_ai/mistral-medium-2505": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 4e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
@@ -12488,6 +13402,7 @@
         "supports_tool_choice": true
     },
     "azure_ai/mistral-nemo": {
+        "deprecation_date": "2026-01-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
@@ -12495,10 +13410,11 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true
     },
     "azure_ai/mistral-small": {
+        "deprecation_date": "2025-07-31",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 32000,
@@ -12506,10 +13422,12 @@
         "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "azure_ai/mistral-small-2503": {
+        "deprecation_date": "2026-12-09",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 128000,
@@ -12535,43 +13453,43 @@
         "source": "https://developers.openai.com/api/docs/pricing"
     },
     "bedrock/*/1-month-commitment/cohere.command-light-text-v14": {
+        "cost_per_second": 0.001902,
         "input_cost_per_second": 0.001902,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.001902,
         "supports_tool_choice": true
     },
     "bedrock/*/1-month-commitment/cohere.command-text-v14": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/*/6-month-commitment/cohere.command-light-text-v14": {
+        "cost_per_second": 0.0011416,
         "input_cost_per_second": 0.0011416,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.0011416,
         "supports_tool_choice": true
     },
     "bedrock/*/6-month-commitment/cohere.command-text-v14": {
+        "cost_per_second": 0.0066027,
         "input_cost_per_second": 0.0066027,
         "litellm_provider": "bedrock",
         "max_input_tokens": 4096,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_second": 0.0066027,
         "supports_tool_choice": true
     },
     "bedrock/guardrails": {
@@ -12590,61 +13508,61 @@
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.01475,
         "input_cost_per_second": 0.01475,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.01475,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0455,
         "input_cost_per_second": 0.0455,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0455
+        "mode": "chat"
     },
     "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0455,
         "input_cost_per_second": 0.0455,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0455,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.008194,
         "input_cost_per_second": 0.008194,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.008194,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.02527,
         "input_cost_per_second": 0.02527,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.02527
+        "mode": "chat"
     },
     "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.02527,
         "input_cost_per_second": 0.02527,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.02527,
         "supports_tool_choice": true
     },
     "bedrock/ap-northeast-1/anthropic.claude-instant-v1": {
@@ -12679,12 +13597,14 @@
     },
     "bedrock/ap-northeast-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12692,32 +13612,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-northeast-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-northeast-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12725,71 +13649,86 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.3e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token_flex": 1.52e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-northeast-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/moonshotai.kimi-k2-thinking": {
-        "input_cost_per_token": 7.3e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
-        "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
-        "output_cost_per_token": 3.03e-06,
-        "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart",
+        "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12800,31 +13739,37 @@
         "supports_response_schema": true
     },
     "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.18e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.2e-06
+        "output_cost_per_token": 4.2e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 7.2e-07
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/ap-south-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12832,32 +13777,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-south-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-south-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12865,59 +13814,69 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.1e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.94e-06,
+        "output_cost_per_token_flex": 1.47e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/ap-south-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-south-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/ap-southeast-2/minimax.minimax-m2.5": {
-        "input_cost_per_token": 3.09e-07,
+        "input_cost_per_token": 3.1e-07,
+        "input_cost_per_token_flex": 1.55e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12925,16 +13884,19 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.236e-06
+        "output_cost_per_token": 1.24e-06,
+        "output_cost_per_token_flex": 6.2e-07
     },
     "bedrock/ap-southeast-3/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -12942,32 +13904,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/ap-southeast-3/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/ap-southeast-3/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -12975,66 +13941,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/ap-southeast-3/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.05e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.03e-06
+        "output_cost_per_token": 4.03e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6.9e-07
+        "output_cost_per_token": 6.9e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-north-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13042,32 +14019,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/eu-north-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-north-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13075,80 +14056,83 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-north-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.01635,
         "input_cost_per_second": 0.01635,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.01635,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0415,
         "input_cost_per_second": 0.0415,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0415
+        "mode": "chat"
     },
     "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0415,
         "input_cost_per_second": 0.0415,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0415,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.009083,
         "input_cost_per_second": 0.009083,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.009083,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.02305,
         "input_cost_per_second": 0.02305,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.02305
+        "mode": "chat"
     },
     "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.02305,
         "input_cost_per_second": 0.02305,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.02305,
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/anthropic.claude-instant-v1": {
@@ -13181,29 +14165,33 @@
         "supports_tool_choice": true
     },
     "bedrock/eu-central-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-central-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13211,66 +14199,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-central-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.86e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.78e-06
+        "output_cost_per_token": 3.78e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6.5e-07
+        "output_cost_per_token": 6.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-west-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-west-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13278,66 +14277,77 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-west-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.45e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4.55e-06
+        "output_cost_per_token": 4.55e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 7.8e-07
+        "output_cost_per_token": 7.8e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/eu-west-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.7e-07,
+        "input_cost_per_token_flex": 2.35e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-west-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 4.7e-07,
+        "input_cost_per_token_flex": 2.35e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13345,16 +14355,19 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.86e-06
+        "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07
     },
     "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": {
         "input_cost_per_token": 2.3e-07,
+        "input_cost_per_token_flex": 1.15e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 1.01e-06,
+        "output_cost_per_token_flex": 5.05e-07,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -13366,75 +14379,85 @@
     },
     "bedrock/eu-west-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 7.8e-07,
+        "input_cost_per_token_flex": 3.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
+        "output_cost_per_token_flex": 9.3e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 5.2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.56e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 9.1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/eu-south-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/eu-south-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13442,23 +14465,26 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/eu-south-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -13479,31 +14505,37 @@
         "cache_creation_input_token_cost": 3.75e-06
     },
     "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.45e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 5.88e-06
+        "output_cost_per_token": 5.88e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.01e-06
+        "output_cost_per_token": 1.01e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/sa-east-1/deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13511,32 +14543,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/sa-east-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/sa-east-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3.6e-07,
+        "input_cost_per_token_flex": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13544,107 +14580,116 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.44e-06
+        "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07
     },
     "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.3e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.03e-06,
+        "output_cost_per_token_flex": 1.52e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/sa-east-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_flex": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
+        "output_cost_per_token_flex": 1.8e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/sa-east-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.44e-06,
+        "output_cost_per_token_flex": 7.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0175
+        "mode": "chat"
     },
     "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0175,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.00611,
         "input_cost_per_second": 0.00611,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00611,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.00972
+        "mode": "chat"
     },
     "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00972,
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/anthropic.claude-instant-v1": {
@@ -13678,62 +14723,72 @@
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-east-1/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13741,29 +14796,34 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-east-1/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-east-1/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -13773,59 +14833,69 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html"
     },
     "bedrock/us-east-1/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-east-1/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-east-1/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-east-2/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -13833,32 +14903,36 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-east-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-east-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
@@ -13866,50 +14940,59 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "output_cost_per_token": 1.2e-06
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07
     },
     "bedrock/us-east-2/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-east-2/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-east-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.4e-07,
@@ -13995,7 +15078,11 @@
         "supports_vision": true,
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -14114,7 +15201,7 @@
         "output_vector_size": 1536
     },
     "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": {
-        "input_cost_per_token": 2e-07,
+        "input_cost_per_token": 1.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_tokens": 8192,
@@ -14123,13 +15210,13 @@
         "output_vector_size": 1024
     },
     "bedrock/us-gov-west-1/amazon.titan-text-express-v1": {
-        "input_cost_per_token": 1.3e-06,
+        "input_cost_per_token": 8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 42000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
-        "output_cost_per_token": 1.7e-06
+        "output_cost_per_token": 1.6e-06
     },
     "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": {
         "input_cost_per_token": 3e-07,
@@ -14172,7 +15259,11 @@
         "supports_vision": true,
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -14220,79 +15311,83 @@
         "supports_pdf_input": true
     },
     "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.011,
         "input_cost_per_second": 0.011,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.011,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.0175
+        "mode": "chat"
     },
     "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.0175,
         "input_cost_per_second": 0.0175,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.0175,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": {
+        "cost_per_second": 0.00611,
         "input_cost_per_second": 0.00611,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00611,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_second": 0.00972
+        "mode": "chat"
     },
     "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": {
+        "cost_per_second": 0.00972,
         "input_cost_per_second": 0.00972,
         "litellm_provider": "bedrock",
         "max_input_tokens": 100000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_second": 0.00972,
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/anthropic.claude-instant-v1": {
@@ -14326,44 +15421,50 @@
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "bedrock/us-west-2/deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_flex": 3.1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 163840,
-        "max_output_tokens": 163840,
-        "max_tokens": 163840,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_flex": 9.25e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -14371,29 +15472,34 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html"
     },
     "bedrock/us-west-2/minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html"
     },
     "bedrock/us-west-2/minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_flex": 1.5e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 196000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -14403,50 +15509,58 @@
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html"
     },
     "bedrock/us-west-2/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html",
         "supports_function_calling": true,
         "supports_reasoning": true
     },
     "bedrock/us-west-2/moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html"
     },
     "bedrock/us-west-2/qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 262144,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html"
     },
     "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "cache_creation_input_token_cost": 1e-06,
@@ -14642,6 +15756,7 @@
         "source": "https://developers.openai.com/api/docs/pricing"
     },
     "claude-haiku-4-5-20251001": {
+        "supports_web_search": true,
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_creation_input_token_cost_batches": 6.25e-07,
@@ -14699,18 +15814,14 @@
     "claude-sonnet-4-5": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_batches": 1.875e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_read_input_token_cost_batches": 1.5e-07,
+        "deprecation_date": "2026-11-30",
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "anthropic",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -14737,18 +15848,14 @@
     "claude-sonnet-4-5-20250929": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_batches": 1.875e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "cache_read_input_token_cost_batches": 1.5e-07,
+        "deprecation_date": "2026-11-30",
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "anthropic",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -14774,6 +15881,7 @@
         "source": "https://docs.anthropic.com/en/docs/about-claude/pricing"
     },
     "claude-sonnet-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_1hr": 4e-06,
@@ -14817,7 +15925,54 @@
         "prompt_cache_min_tokens": 1024,
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
+    "claude-sonnet-5-5": {
+        "supports_anthropic_compaction": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "provider_specific_entry": {
+            "us": 1.1
+        },
+        "supports_output_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing",
+        "supports_web_search": true
+    },
     "claude-sonnet-4-6": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
@@ -14840,7 +15995,7 @@
         },
         "supports_adaptive_thinking": true,
         "supports_legacy_thinking": true,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -14891,6 +16046,7 @@
         "output_cost_per_token_batches": 7.5e-06
     },
     "claude-opus-4-5-20251101": {
+        "supports_web_search": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_creation_input_token_cost_batches": 3.125e-06,
@@ -14960,6 +16116,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15045,6 +16202,7 @@
         "prompt_cache_min_tokens": 4096
     },
     "claude-opus-4-7": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15132,6 +16290,7 @@
         "prompt_cache_min_tokens": 2048
     },
     "claude-fable-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_1hr": 2e-05,
@@ -15176,6 +16335,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-fable-5-1": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_1hr": 2e-05,
@@ -15221,6 +16381,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 5e-06,
         "cache_creation_input_token_cost_above_1hr": 8e-06,
@@ -15258,9 +16419,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_max_reasoning_effort": true,
-        "provider_specific_entry": {
-            "fast": 2.0
-        },
+        "provider_specific_entry": {"us":1.1,"fast":2},
         "supports_output_config": true,
         "supports_speed": true,
         "supports_fast_mode": true,
@@ -15268,6 +16427,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15315,6 +16475,7 @@
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-8": {
+        "supports_web_search": true,
         "supports_anthropic_compaction": true,
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
@@ -15361,6 +16522,82 @@
         "prompt_cache_min_tokens": 1024,
         "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
+    "cloudflare/clef-omni": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 64000,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/",
+        "supports_audio_input": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef-omni": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 64000,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/",
+        "supports_audio_input": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "cloudflare/clef": {
+        "input_cost_per_token": 2.4e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/clef-flash": {
+        "input_cost_per_token": 9e-08,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef": {
+        "input_cost_per_token": 2.4e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clef-flash": {
+        "input_cost_per_token": 9e-08,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
+        "supports_vision": true
+    },
+    "cloudflare/clairic": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "extraction",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clairic/",
+        "supports_vision": true
+    },
+    "cloudflare/@cf/cloudflare/clairic": {
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "cloudflare",
+        "max_input_tokens": 65536,
+        "mode": "extraction",
+        "output_cost_per_token": 0.0,
+        "source": "https://developers.cloudflare.com/workers-ai/models/clairic/",
+        "supports_vision": true
+    },
     "cloudflare/@cf/meta/llama-2-7b-chat-fp16": {
         "input_cost_per_token": 1.923e-06,
         "litellm_provider": "cloudflare",
@@ -15796,7 +17033,31 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_vector_size": 1536,
-        "supports_embedding_image_input": true
+        "supports_embedding_image_input": true,
+        "input_cost_per_image_token": 4.7e-07,
+        "source": "https://cohere.com/pricing"
+    },
+    "cohere/embed-v5.0-pro": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048,
+        "supports_embedding_image_input": true,
+        "source": "https://cohere.com/pricing"
+    },
+    "cohere/embed-v5.0-fast": {
+        "input_cost_per_token": 8e-08,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048,
+        "supports_embedding_image_input": true,
+        "source": "https://cohere.com/pricing"
     },
     "cohere/parse-v5.0": {
         "litellm_provider": "cohere",
@@ -15811,11 +17072,12 @@
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 32000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
+        "max_input_tokens": 4096,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "rerank",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md"
     },
     "command-a-03-2025": {
         "input_cost_per_token": 2.5e-06,
@@ -15896,6 +17158,144 @@
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
+    "coralbricks/glm-5.3-fast": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/glm-5.3-fp4": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/glm-5.3": {
+        "cache_creation_input_token_cost": 1.68e-06,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1.12e-06,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "coralbricks/deepseek-v4.1-flash-fast": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "coralbricks/deepseek-v4.1-flash-fast-fp4": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "coralbricks/deepseek-v4.1-flash": {
+        "cache_creation_input_token_cost": 9e-08,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "coralbricks",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.coralbricks.ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "computer-use-preview": {
         "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
@@ -15926,8 +17326,39 @@
         "supports_vision": true,
         "source": "https://platform.openai.com/docs/models/computer-use-preview"
     },
+    "computer-use-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 1024,
+        "max_tokens": 1024,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://developers.openai.com/api/docs/models/computer-use-preview"
+    },
     "deepseek-chat": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "litellm_provider": "deepseek",
         "max_input_tokens": 131072,
@@ -15949,6 +17380,7 @@
     },
     "deepseek-reasoner": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "litellm_provider": "deepseek",
         "max_input_tokens": 131072,
@@ -16810,7 +18242,9 @@
         ]
     },
     "dashscope/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "dashscope",
         "max_input_tokens": 991808,
@@ -16961,6 +18395,281 @@
             "/v1/images/generations"
         ]
     },
+    "dashscope/wan3.0-video": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.165025,
+        "output_cost_per_second_480p": 0.041256,
+        "output_cost_per_second_720p": 0.082513,
+        "output_cost_per_second_1080p": 0.165025,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan3.0-video-prime": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.254399,
+        "output_cost_per_second_480p": 0.0636,
+        "output_cost_per_second_720p": 0.127199,
+        "output_cost_per_second_1080p": 0.254399,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.1-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/happyhorse-1.0-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-t2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-i2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "dashscope/wan2.7-r2v": {
+        "litellm_provider": "dashscope",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "qwencloud/deepseek-v4-flash": {
         "cache_read_input_token_cost": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -17802,7 +19511,9 @@
         ]
     },
     "qwencloud/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "qwencloud",
         "max_input_tokens": 991808,
@@ -17913,6 +19624,281 @@
             "/v1/images/generations"
         ]
     },
+    "qwencloud/wan3.0-video": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.2,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.2,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan3.0-video-prime": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.28,
+        "output_cost_per_second_480p": 0.068,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.28,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.1-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.18,
+        "output_cost_per_second_480p": 0.07,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.18,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/happyhorse-1.0-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.24,
+        "output_cost_per_second_720p": 0.14,
+        "output_cost_per_second_1080p": 0.24,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-t2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-i2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwencloud/wan2.7-r2v": {
+        "litellm_provider": "qwencloud",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.15,
+        "output_cost_per_second_720p": 0.1,
+        "output_cost_per_second_1080p": 0.15,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "qwen_ai_platform/deepseek-v4-flash": {
         "cache_read_input_token_cost": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -18754,7 +20740,9 @@
         ]
     },
     "qwen_ai_platform/qwen3.7-max": {
+        "cache_creation_input_token_cost": 3.125e-06,
         "cache_read_input_token_cost": 5e-07,
+        "explicit_cache_read_input_token_cost": 2.5e-07,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "qwen_ai_platform",
         "max_input_tokens": 991808,
@@ -18905,6 +20893,281 @@
             "/v1/images/generations"
         ]
     },
+    "qwen_ai_platform/wan3.0-video": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
+        "output_cost_per_second": 0.165025,
+        "output_cost_per_second_480p": 0.041256,
+        "output_cost_per_second_720p": 0.082513,
+        "output_cost_per_second_1080p": 0.165025,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan3.0-video-prime": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime",
+        "output_cost_per_second": 0.254399,
+        "output_cost_per_second_480p": 0.0636,
+        "output_cost_per_second_720p": 0.127199,
+        "output_cost_per_second_1080p": 0.254399,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.1-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v",
+        "output_cost_per_second": 0.165026,
+        "output_cost_per_second_480p": 0.0618845,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.165026,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/happyhorse-1.0-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v",
+        "output_cost_per_second": 0.220034,
+        "output_cost_per_second_720p": 0.123769,
+        "output_cost_per_second_1080p": 0.220034,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-t2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-i2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "first_frame"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
+    "qwen_ai_platform/wan2.7-r2v": {
+        "litellm_provider": "qwen_ai_platform",
+        "mode": "video_generation",
+        "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v",
+        "output_cost_per_second": 0.143353,
+        "output_cost_per_second_720p": 0.086012,
+        "output_cost_per_second_1080p": 0.143353,
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "provider_specific_entry": {
+            "dashscope_video_reference_input": "reference_image"
+        },
+        "metadata": {
+            "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
+        }
+    },
     "databricks/databricks-bge-large-en": {
         "cache_creation_input_token_cost": 1.0003e-07,
         "cache_read_input_token_cost": 1.0003e-07,
@@ -19094,7 +21357,7 @@
         "output_cost_per_token": 2.5000010000000002e-05,
         "output_dbu_cost_per_token": 0.000357143,
         "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_legacy_thinking": true,
         "supports_prompt_caching": true,
@@ -19186,6 +21449,41 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "databricks/databricks-claude-opus-5-5": {
+        "cache_creation_input_token_cost": 5.00003e-06,
+        "cache_creation_input_token_cost_above_1hr": 8.00002e-06,
+        "cache_read_input_token_cost": 1.9999e-07,
+        "input_cost_per_token": 4.00001e-06,
+        "input_dbu_cost_per_token": 5.7143e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "metadata": {
+            "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.999998e-05,
+        "output_dbu_cost_per_token": 0.000285714,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_adaptive_thinking": true,
+        "supports_anthropic_thinking_payload": true,
+        "supports_assistant_prefill": false,
+        "supports_forced_tool_use": false,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_output_config": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true
+    },
     "databricks/databricks-claude-sonnet-4": {
         "cache_creation_input_token_cost": 3.74997e-06,
         "cache_read_input_token_cost": 3.0002e-07,
@@ -19274,7 +21572,7 @@
         "output_cost_per_token": 1.5000020000000002e-05,
         "output_dbu_cost_per_token": 0.000214286,
         "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_legacy_thinking": true,
         "supports_prompt_caching": true,
@@ -19317,6 +21615,7 @@
         "input_cost_per_token": 1.4e-07,
         "input_dbu_cost_per_token": 2e-06,
         "litellm_provider": "databricks",
+        "token_count_framing": 97,
         "max_input_tokens": 1000000,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
@@ -19337,8 +21636,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_vision": false,
-        "token_count_framing": 97
+        "supports_vision": false
     },
     "databricks/system.ai.deepseek-v4-flash-0731": {
         "litellm_provider": "databricks",
@@ -19623,6 +21921,7 @@
         ],
         "supports_function_calling": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19647,6 +21946,7 @@
         ],
         "supports_function_calling": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19678,6 +21978,7 @@
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -19741,6 +22042,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true
     },
@@ -20313,6 +22615,7 @@
         "input_cost_per_token": 2.99999e-06,
         "input_dbu_cost_per_token": 4.2857e-05,
         "litellm_provider": "databricks",
+        "token_count_framing": 100,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1048576,
         "max_tokens": 1048576,
@@ -20334,8 +22637,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 100
+        "supports_vision": true
     },
     "databricks/system.ai.kimi-k3": {
         "litellm_provider": "databricks",
@@ -20463,6 +22765,30 @@
         "output_vector_size": 1024,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
     },
+    "databricks/databricks-openjev-qwen35-4b": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "databricks",
+        "metadata": {
+            "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost."
+        },
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
+    },
+    "databricks/ai_decide": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "databricks",
+        "metadata": {
+            "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it."
+        },
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide"
+    },
     "dataforseo/search": {
         "input_cost_per_query": 0.003,
         "litellm_provider": "dataforseo",
@@ -21844,6 +24170,7 @@
     "deepseek/deepseek-chat": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "input_cost_per_token_cache_hit": 2.8e-08,
         "litellm_provider": "deepseek",
@@ -21898,6 +24225,7 @@
     },
     "deepseek/deepseek-reasoner": {
         "cache_read_input_token_cost": 2.8e-08,
+        "deprecation_date": "2026-07-24",
         "input_cost_per_token": 2.8e-07,
         "input_cost_per_token_cache_hit": 2.8e-08,
         "litellm_provider": "deepseek",
@@ -21953,14 +24281,15 @@
         "supports_tool_choice": true
     },
     "deepseek.v3-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.8e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 81920,
-        "max_tokens": 81920,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -21968,17 +24297,23 @@
     },
     "deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_batches": 3.1e-07,
+        "input_cost_per_token_flex": 3.1e-07,
+        "input_cost_per_token_priority": 1.085e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 164000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_batches": 9.25e-07,
+        "output_cost_per_token_flex": 9.25e-07,
+        "output_cost_per_token_priority": 3.2375e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -22198,6 +24533,265 @@
         "litellm_provider": "perplexity",
         "mode": "search"
     },
+    "sail/moonshotai/Kimi-K3": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 2.5e-06,
+        "output_cost_per_token": 1.25e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token_balanced": 2e-06,
+        "output_cost_per_token_balanced": 1e-05,
+        "cache_read_input_token_cost_balanced": 2e-07,
+        "input_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_flex": 6.25e-06,
+        "cache_read_input_token_cost_flex": 1.5e-07,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/zai-org/GLM-5.3": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9.8e-07,
+        "output_cost_per_token": 3.08e-06,
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token_balanced": 5e-07,
+        "output_cost_per_token_balanced": 2.5e-06,
+        "cache_read_input_token_cost_balanced": 1.2e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "output_cost_per_token_flex": 1.8e-06,
+        "cache_read_input_token_cost_flex": 8e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/zai-org/GLM-5.3-Flash": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 1.1e-07,
+        "output_cost_per_token": 3.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_balanced": 8e-08,
+        "output_cost_per_token_balanced": 2.8e-07,
+        "cache_read_input_token_cost_balanced": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1.8e-07,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4-Pro-0813": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9.2e-07,
+        "output_cost_per_token": 2.77e-06,
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token_balanced": 7.4e-07,
+        "output_cost_per_token_balanced": 2.22e-06,
+        "cache_read_input_token_cost_balanced": 3e-08,
+        "input_cost_per_token_flex": 4.6e-07,
+        "output_cost_per_token_flex": 1.39e-06,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4-Flash-0731": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 1.8e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_balanced": 7e-08,
+        "output_cost_per_token_balanced": 1.4e-07,
+        "cache_read_input_token_cost_balanced": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 9e-08,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "max_tokens": 1048576,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 3e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token_balanced": 7e-08,
+        "output_cost_per_token_balanced": 2.2e-07,
+        "cache_read_input_token_cost_balanced": 5e-09,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1.5e-07,
+        "cache_read_input_token_cost_flex": 4e-09,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/moonshotai/Kimi-K2.6": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1e-06,
+        "output_cost_per_token": 4e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_balanced": 4.5e-07,
+        "output_cost_per_token_balanced": 3e-06,
+        "cache_read_input_token_cost_balanced": 2e-07,
+        "input_cost_per_token_flex": 3.5e-07,
+        "output_cost_per_token_flex": 2e-06,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/google/gemma-4-31B-it": {
+        "max_tokens": 256000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "input_cost_per_token": 4e-07,
+        "output_cost_per_token": 6e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_balanced": 1.2e-07,
+        "output_cost_per_token_balanced": 6e-07,
+        "cache_read_input_token_cost_balanced": 8e-08,
+        "input_cost_per_token_flex": 6e-08,
+        "output_cost_per_token_flex": 3e-07,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/nvidia/Gemma-4-31B-IT-NVFP4": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token_balanced": 1.1e-07,
+        "output_cost_per_token_balanced": 3.2e-07,
+        "cache_read_input_token_cost_balanced": 6e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "output_cost_per_token_flex": 2e-07,
+        "cache_read_input_token_cost_flex": 4e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/google/gemma-4-12B-it": {
+        "max_tokens": 16384,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2e-06,
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token_balanced": 1e-07,
+        "output_cost_per_token_balanced": 2e-06,
+        "cache_read_input_token_cost_balanced": 7e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 1e-06,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/openai/gpt-oss-120b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 6e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 3e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
+    "sail/Qwen/Qwen3.6-35B-A3B": {
+        "max_tokens": 262144,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_flex": 4e-07,
+        "cache_read_input_token_cost_flex": 2e-08,
+        "litellm_provider": "sail",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.sailresearch.com/models"
+    },
     "searxng/search": {
         "litellm_provider": "searxng",
         "mode": "search",
@@ -22231,7 +24825,7 @@
         }
     },
     "agentcore/search": {
-        "input_cost_per_query": 0.0,
+        "input_cost_per_query": 0.007,
         "litellm_provider": "agentcore",
         "mode": "search",
         "metadata": {
@@ -22246,6 +24840,11 @@
             "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment."
         }
     },
+    "deepseek/search": {
+        "input_cost_per_query": 0.00075,
+        "litellm_provider": "deepseek",
+        "mode": "search"
+    },
     "tinyfish/search": {
         "input_cost_per_query": 0.0,
         "litellm_provider": "tinyfish",
@@ -22390,13 +24989,16 @@
     },
     "eu.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2.625e-07,
+        "cache_read_input_token_cost_flex": 1.3125e-07,
         "input_cost_per_token": 1.05e-06,
+        "input_cost_per_token_flex": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 4.2e-06,
+        "output_cost_per_token_flex": 2.1e-06,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -22450,7 +25052,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -22547,7 +25153,11 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "deprecation_date": "2027-01-08"
+        "deprecation_date": "2027-01-08",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -22585,7 +25195,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -22606,7 +25216,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.125e-06,
@@ -22618,6 +25232,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -22644,9 +25259,14 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -22654,10 +25274,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "eu.meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.9e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -22665,6 +25287,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.9e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -22672,10 +25295,11 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -24984,9 +27608,10 @@
         "output_cost_per_token": 5e-07
     },
     "fireworks-ai-up-to-4b": {
-        "input_cost_per_token": 2e-07,
+        "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "output_cost_per_token": 2e-07
+        "output_cost_per_token": 1e-07,
+        "source": "https://docs.fireworks.ai/serverless/pricing"
     },
     "fireworks_ai/WhereIsAI/UAE-Large-V1": {
         "input_cost_per_token": 1.6e-08,
@@ -25013,7 +27638,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 20480,
         "max_tokens": 20480,
         "mode": "chat",
@@ -25025,7 +27650,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 160000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 160000,
         "max_tokens": 160000,
         "mode": "chat",
@@ -25037,7 +27662,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": {
         "input_cost_per_token": 5.5e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 163840,
         "max_output_tokens": 20480,
         "max_tokens": 20480,
         "mode": "chat",
@@ -25049,7 +27674,7 @@
     "fireworks_ai/accounts/fireworks/models/deepseek-v3": {
         "input_cost_per_token": 9e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
@@ -25182,7 +27807,7 @@
     "fireworks_ai/accounts/fireworks/models/glm-4p5": {
         "input_cost_per_token": 5.5e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 96000,
         "max_tokens": 96000,
         "mode": "chat",
@@ -25196,7 +27821,7 @@
     "fireworks_ai/accounts/fireworks/models/glm-4p5-air": {
         "input_cost_per_token": 2.2e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 96000,
         "max_tokens": 96000,
         "mode": "chat",
@@ -25211,7 +27836,7 @@
         "input_cost_per_token": 5.5e-07,
         "output_cost_per_token": 2.19e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25225,7 +27850,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25240,7 +27865,7 @@
         "cache_read_input_token_cost": 2.6e-07,
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
@@ -25275,6 +27900,7 @@
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
         "cache_read_input_token_cost_priority": 1.8e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
@@ -25284,7 +27910,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_priority": 7.2e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -25404,7 +28030,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
         "input_cost_per_token": 3e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25417,7 +28043,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25430,7 +28056,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
         "input_cost_per_token": 2e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25444,7 +28070,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25457,7 +28083,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25470,7 +28096,7 @@
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
         "input_cost_per_token": 9e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 16384,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -25508,7 +28134,7 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 204800,
         "max_tokens": 204800,
         "mode": "chat",
@@ -25609,7 +28235,7 @@
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 202800,
         "max_tokens": 202800,
         "mode": "chat",
@@ -25624,7 +28250,7 @@
         "cache_read_input_token_cost": 2.6e-07,
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 202800,
+        "max_input_tokens": 202752,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
@@ -25675,6 +28301,7 @@
     "fireworks_ai/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
         "cache_read_input_token_cost_priority": 1.8e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
@@ -25684,7 +28311,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_priority": 7.2e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -25799,7 +28426,7 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "fireworks_ai",
-        "max_input_tokens": 204800,
+        "max_input_tokens": 196608,
         "max_output_tokens": 204800,
         "max_tokens": 204800,
         "mode": "chat",
@@ -26152,6 +28779,7 @@
     "ft:gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.875e-06,
         "cache_read_input_token_cost_batches": 9e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3.75e-06,
         "input_cost_per_token_batches": 2.225e-06,
         "litellm_provider": "openai",
@@ -26173,6 +28801,7 @@
     },
     "ft:gpt-4o-2024-11-20": {
         "cache_creation_input_token_cost": 1.875e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3.75e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -26191,6 +28820,7 @@
     "ft:gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 1.5e-07,
         "cache_read_input_token_cost_batches": 7.5e-08,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "litellm_provider": "openai",
@@ -26212,6 +28842,7 @@
     "ft:gpt-4.1-2025-04-14": {
         "cache_read_input_token_cost": 7.5e-07,
         "cache_read_input_token_cost_batches": 5e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "openai",
@@ -26232,6 +28863,7 @@
     "ft:gpt-4.1-mini-2025-04-14": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_batches": 1e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 8e-07,
         "input_cost_per_token_batches": 4e-07,
         "litellm_provider": "openai",
@@ -26371,7 +29003,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26429,7 +29062,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26481,7 +29115,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26510,11 +29145,13 @@
         "cache_read_input_token_cost": 5e-08,
         "cache_read_input_token_cost_batches": 2.5e-08,
         "cache_read_input_token_cost_flex": 2.5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -26525,10 +29162,12 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26571,7 +29210,8 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26600,10 +29240,13 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_batches": 1.25e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-06-28",
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -26614,10 +29257,12 @@
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.7e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -26794,6 +29439,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -26820,7 +29466,7 @@
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
-        "mode": "image_generation",
+        "mode": "chat",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
@@ -27043,7 +29689,8 @@
             "search_context_size_high": 0.035
         },
         "gemini_native_audio": true,
-        "input_cost_per_image_token": 3e-06
+        "input_cost_per_image_token": 3e-06,
+        "input_cost_per_video_token": 3e-06
     },
     "gemini-live-2.5-flash-preview-native-audio-09-2025": {
         "input_cost_per_audio_token": 3e-06,
@@ -27194,22 +29841,32 @@
         "output_cost_per_token_priority": 1.8e-05
     },
     "gemini-3.1-pro-preview": {
-        "prompt_cache_min_tokens": 4096,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
+        "output_cost_per_image": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "output_cost_per_image": 0.00012,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27228,33 +29885,18 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_url_context": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 3.6e-06,
-        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
-        "output_cost_per_token_priority": 2.16e-05,
-        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
-        "cache_read_input_token_cost_priority": 3.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
-        "cache_read_input_token_cost_flex": 2e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_token_flex": 1e-06,
-        "output_cost_per_token_flex": 6e-06
+        "web_search_billing_unit": "per_query"
     },
     "gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -27369,15 +30011,25 @@
     "vertex_ai/gemini-3-flash-preview": {
         "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
-        "cache_read_input_token_cost_flex": 5e-08,
-        "input_cost_per_token": 5e-07,
+        "cache_read_input_token_cost_priority": 9e-08,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
+        "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
         "max_tokens": 65535,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27396,6 +30048,7 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -27405,23 +30058,7 @@
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 9e-07,
-        "input_cost_per_audio_token_priority": 1.8e-06,
-        "output_cost_per_token_priority": 5.4e-06,
-        "cache_read_input_token_cost_priority": 9e-08,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 5e-07,
-        "input_cost_per_token_batches": 2.5e-07,
-        "input_cost_per_token_flex": 2.5e-07,
-        "output_cost_per_token_batches": 1.5e-06,
-        "output_cost_per_token_flex": 1.5e-06
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.5-flash": {
         "prompt_cache_min_tokens": 4096,
@@ -27525,6 +30162,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -27535,6 +30173,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2026-11-19",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -27585,6 +30224,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -27595,6 +30235,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2027-01-28",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -27605,13 +30246,15 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/gemini-3.8-flash": {
-        "prompt_cache_min_tokens": 4096,
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_batches": 3.75e-08,
         "cache_read_input_token_cost_flex": 3.75e-08,
+        "cache_read_input_token_cost_priority": 1.35e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 7.5e-07,
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_priority": 1.35e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -27621,7 +30264,10 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "prompt_cache_min_tokens": 4096.0,
         "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27640,29 +30286,21 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 1.35e-06,
-        "output_cost_per_token_priority": 6.75e-06,
-        "cache_read_input_token_cost_priority": 1.35e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.8-flash-cyber": {
         "cache_read_input_token_cost": 1.5e-07,
@@ -27705,6 +30343,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": false,
         "supports_url_context": false,
@@ -27714,6 +30353,7 @@
         "supports_native_streaming": true
     },
     "vertex_ai/gemini-3.8-live": {
+        "gemini_audio_only_live": true,
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -27726,7 +30366,8 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 4.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "output_cost_per_video_token": 1e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/vertex_ai/live",
             "/v1/realtime"
@@ -27746,26 +30387,35 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true,
-        "gemini_audio_only_live": true
+        "supports_web_search": true
     },
     "vertex_ai/gemini-3.1-pro-preview": {
-        "prompt_cache_min_tokens": 4096,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
+        "output_cost_per_image": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "output_cost_per_image": 0.00012,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -27784,33 +30434,18 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_url_context": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 3.6e-06,
-        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
-        "output_cost_per_token_priority": 2.16e-05,
-        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
-        "cache_read_input_token_cost_priority": 3.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
-        "cache_read_input_token_cost_flex": 2e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_token_flex": 1e-06,
-        "output_cost_per_token_flex": 6e-06
+        "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -27953,7 +30588,7 @@
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
-        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_reasoning_token": 5e-06,
         "output_cost_per_token": 5e-06,
         "output_cost_per_token_batches": 2.5e-06,
         "search_context_cost_per_query": {
@@ -28174,8 +30809,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28218,8 +30853,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28334,7 +30969,7 @@
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 131072,
+        "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -28371,7 +31006,7 @@
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 131072,
+        "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -28456,6 +31091,7 @@
         "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"},
         "google_maps_grounding_cost_per_query": 0.025,
         "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
         "input_cost_per_token_priority": 5.4e-07,
@@ -28467,7 +31103,7 @@
     },
     "gemini/gemini-2.5-flash-image": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-02",
+        "deprecation_date": "2027-03-15",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
@@ -28487,8 +31123,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28533,6 +31169,7 @@
         "mode": "image_generation",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
+        "output_cost_per_image_token_batches": 6e-05,
         "output_cost_per_token": 1.2e-05,
         "rpm": 1000,
         "tpm": 4000000,
@@ -28542,8 +31179,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28554,7 +31191,7 @@
             "image"
         ],
         "supports_function_calling": false,
-        "supports_prompt_caching": true,
+        "supports_prompt_caching": false,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
@@ -28566,7 +31203,7 @@
         },
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "web_search_billing_unit": "per_query",
-        "supports_reasoning": false
+        "supports_reasoning": true
     },
     "gemini/nano-banana-pro-preview": {
         "input_cost_per_image": 0.0011,
@@ -28590,8 +31227,7 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28625,16 +31261,17 @@
         "mode": "image_generation",
         "output_cost_per_image": 0.045,
         "output_cost_per_image_token": 6e-05,
+        "output_cost_per_image_token_batches": 3e-05,
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
-        "rpm": 1000,
-        "tpm": 4000000,
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28645,17 +31282,14 @@
             "image"
         ],
         "supports_function_calling": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
+        "tpm": 4000000.0,
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-3.1-flash-lite-image": {
@@ -28675,8 +31309,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
+            "/v1/images/generations",
+            "/v1/images/edits"
         ],
         "supported_modalities": [
             "text",
@@ -28687,8 +31321,9 @@
             "image"
         ],
         "supports_function_calling": false,
+        "supports_pdf_input": true,
         "supports_prompt_caching": false,
-        "supports_reasoning": false,
+        "supports_reasoning": true,
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_vision": true,
@@ -28696,21 +31331,20 @@
         "tpm": 4000000
     },
     "gemini/deep-research-pro-preview-12-2025": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "image_generation",
-        "output_cost_per_image": 0.134,
-        "output_cost_per_image_token": 0.00012,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "rpm": 1000,
-        "tpm": 4000000,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035},
+        "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -28718,23 +31352,21 @@
         ],
         "supported_modalities": [
             "text",
-            "image"
+            "image",
+            "audio",
+            "video"
         ],
         "supported_output_modalities": [
-            "text",
-            "image"
+            "text"
         ],
         "supports_function_calling": false,
+        "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.035,
-            "search_context_size_medium": 0.035,
-            "search_context_size_high": 0.035
-        }
+        "tpm": 4000000.0
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_audio_token_cost": 3e-08,
@@ -28788,6 +31420,7 @@
         "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"},
         "google_maps_grounding_cost_per_query": 0.025,
         "input_cost_per_audio_token_batches": 1.5e-07,
+        "input_cost_per_audio_token_priority": 5.4e-07,
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_flex": 5e-08,
         "input_cost_per_token_priority": 1.8e-07,
@@ -28915,6 +31548,7 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-2.5-flash-preview-tts": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "gemini",
@@ -28994,9 +31628,11 @@
         "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "output_cost_per_token_batches": 5e-06,
-        "output_cost_per_token_flex": 5e-06
+        "output_cost_per_token_flex": 5e-06,
+        "supports_url_context": true
     },
     "gemini/gemini-2.5-computer-use-preview-10-2025": {
+        "deprecation_date": "2026-07-28",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "gemini",
@@ -29088,7 +31724,8 @@
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "web_search_billing_unit": "per_query",
         "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 2.5e-07
+        "input_cost_per_audio_token_batches": 2.5e-07,
+        "input_cost_per_audio_token_priority": 9e-07
     },
     "gemini/gemini-3.5-flash-lite": {
         "cache_read_input_token_cost": 3e-08,
@@ -29133,6 +31770,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29317,6 +31955,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29379,6 +32018,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29441,6 +32081,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29493,7 +32134,7 @@
         "supports_video_input": true,
         "supports_vision": true,
         "tpm": 800000,
-        "deprecation_date": "2026-09-30"
+        "deprecation_date": "2026-10-22"
     },
     "gemini/gemini-3.1-pro-preview": {
         "prompt_cache_min_tokens": 4096,
@@ -29626,9 +32267,15 @@
     "gemini-3-flash-preview": {
         "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
-        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token_batches": 5e-07,
+        "input_cost_per_audio_token_priority": 1.8e-06,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
@@ -29636,6 +32283,10 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 3e-06,
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -29654,6 +32305,7 @@
         ],
         "supports_audio_output": false,
         "supports_function_calling": true,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -29664,23 +32316,7 @@
         "supports_url_context": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 9e-07,
-        "input_cost_per_audio_token_priority": 1.8e-06,
-        "output_cost_per_token_priority": 5.4e-06,
-        "cache_read_input_token_cost_priority": 9e-08,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014,
-        "input_cost_per_audio_token_batches": 5e-07,
-        "input_cost_per_token_batches": 2.5e-07,
-        "input_cost_per_token_flex": 2.5e-07,
-        "output_cost_per_token_batches": 1.5e-06,
-        "output_cost_per_token_flex": 1.5e-06
+        "web_search_billing_unit": "per_query"
     },
     "gemini-omni-flash-preview": {
         "input_cost_per_audio_token": 1.5e-06,
@@ -29815,6 +32451,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29825,6 +32462,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2026-11-19",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -29875,6 +32513,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -29885,6 +32524,7 @@
         "input_cost_per_token_priority": 1.35e-06,
         "output_cost_per_token_priority": 6.75e-06,
         "cache_read_input_token_cost_priority": 1.35e-07,
+        "deprecation_date": "2027-01-28",
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
@@ -29895,13 +32535,15 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3.8-flash": {
-        "prompt_cache_min_tokens": 4096,
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_batches": 3.75e-08,
         "cache_read_input_token_cost_flex": 3.75e-08,
+        "cache_read_input_token_cost_priority": 1.35e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
         "input_cost_per_token": 7.5e-07,
         "input_cost_per_token_batches": 3.75e-07,
         "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_priority": 1.35e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
@@ -29911,6 +32553,9 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "prompt_cache_min_tokens": 4096.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
         "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"},
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
@@ -29927,32 +32572,24 @@
         "supported_output_modalities": [
             "text"
         ],
-        "supports_audio_output": false,
         "supports_audio_input": true,
+        "supports_audio_output": false,
         "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_native_streaming": true,
-        "input_cost_per_token_priority": 1.35e-06,
-        "output_cost_per_token_priority": 6.75e-06,
-        "cache_read_input_token_cost_priority": 1.35e-07,
-        "search_context_cost_per_query": {
-            "search_context_size_low": 0.014,
-            "search_context_size_medium": 0.014,
-            "search_context_size_high": 0.014
-        },
-        "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "web_search_billing_unit": "per_query"
     },
     "gemini-3.8-flash-cyber": {
         "cache_read_input_token_cost": 1.5e-07,
@@ -29995,6 +32632,7 @@
         "supports_reasoning": true,
         "supports_minimal_reasoning_effort": false,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": false,
         "supports_url_context": false,
@@ -30005,6 +32643,7 @@
     },
     "gemini/gemini-2.5-pro-preview-tts": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-06,
         "input_cost_per_token_batches": 5e-07,
@@ -30265,6 +32904,7 @@
         "output_cost_per_image": 0.08
     },
     "gemini/veo-3.1-fast-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30281,6 +32921,7 @@
         ]
     },
     "gemini/veo-3.1-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30296,6 +32937,7 @@
         ]
     },
     "gemini/veo-3.1-lite-generate-preview": {
+        "deprecation_date": "2026-10-22",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -30341,83 +32983,270 @@
             "video"
         ]
     },
-    "github_copilot/claude-haiku-4.5": {
+    "github_copilot/claude-fable-5": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
         "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
-            "/v1/chat/completions"
+            "/v1/chat/completions",
+            "/v1/messages"
         ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_vision": true
-    },
-    "github_copilot/claude-opus-4.5": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_vision": true,
-        "supports_output_config": true
-    },
-    "github_copilot/claude-opus-4.6-fast": {
         "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-fable-5.1": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-haiku-4.5": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token": 5e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
         "supports_vision": true
     },
-    "github_copilot/claude-opus-41": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 80000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_vision": true
-    },
-    "github_copilot/claude-sonnet-4": {
+    "github_copilot/claude-haiku-5.5": {
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_above_100k_tokens": 5e-07,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
-            "/v1/chat/completions"
+            "/v1/chat/completions",
+            "/v1/messages"
         ],
+        "supports_adaptive_thinking": true,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": false
+    },
+    "github_copilot/claude-opus-4.8": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
         "supports_vision": true
     },
-    "github_copilot/claude-sonnet-4.5": {
+    "github_copilot/claude-opus-4.8-fast": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
         "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-opus-5": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-opus-5.5": {
+        "cache_creation_input_token_cost": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/claude-sonnet-5": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-sonnet-5.5": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "thinking_always_on": true
+    },
+    "github_copilot/gemini-3.7-flash": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.75e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
+        "supports_vision": true
+    },
+    "github_copilot/gemini-3.8-flash": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 3.75e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_vision": true
     },
     "github_copilot/gpt-3.5-turbo": {
@@ -30462,22 +33291,26 @@
         "supports_parallel_function_calling": true
     },
     "github_copilot/gpt-4.1": {
+        "deprecation_date": "2026-06-01",
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
         "supports_vision": true
     },
     "github_copilot/gpt-4.1-2025-04-14": {
+        "deprecation_date": "2026-06-01",
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -30544,82 +33377,304 @@
         "supports_function_calling": true,
         "supports_parallel_function_calling": true
     },
-    "github_copilot/gpt-5": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
     "github_copilot/gpt-5-mini": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2.5e-07,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.1": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.1-codex-max": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "responses",
-        "supported_endpoints": [
-            "/v1/responses"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "github_copilot/gpt-5.2": {
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/responses"
-        ],
+        "output_cost_per_token": 2e-06,
+        "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
         "supports_vision": true
     },
     "github_copilot/gpt-5.3-codex": {
+        "cache_read_input_token_cost": 1.75e-07,
+        "input_cost_per_token": 1.75e-06,
         "litellm_provider": "github_copilot",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "output_cost_per_token": 1.4e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4-mini": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 4.5e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 5e-06,
+        "input_cost_per_token_above_272k_tokens": 1e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 3e-05,
+        "output_cost_per_token_above_272k_tokens": 4.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.5e-07,
+        "cache_creation_input_token_cost_above_200k_tokens": 5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_200k_tokens": 4e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_200k_tokens": 1.8e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 8e-07,
+        "input_cost_per_token": 4e-06,
+        "input_cost_per_token_above_272k_tokens": 8e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-05,
+        "output_cost_per_token_above_272k_tokens": 3e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "deprecation_date": "2026-11-16",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-astra": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "input_cost_per_token": 1e-05,
+        "input_cost_per_token_above_272k_tokens": 2e-05,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 5e-05,
+        "output_cost_per_token_above_272k_tokens": 7.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-luna": {
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_above_272k_tokens": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/kimi-k3": {
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 917504,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/mai-code-1.1-flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
         "supported_endpoints": [
             "/v1/responses"
         ],
@@ -30628,38 +33683,6 @@
         "supports_response_schema": true,
         "supports_vision": true
     },
-    "github_copilot/mai-code-1-flash": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true
-    },
-    "github_copilot/mai-code-1-flash-internal": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "github_copilot",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_response_schema": true
-    },
     "github_copilot/text-embedding-3-small": {
         "litellm_provider": "github_copilot",
         "max_input_tokens": 8191,
@@ -30678,6 +33701,90 @@
         "max_tokens": 8191,
         "mode": "embedding"
     },
+    "chatgpt/gpt-6-sol": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6-luna": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6-astra": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "chatgpt/gpt-6.1-sol": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "chatgpt/gpt-5.5": {
         "litellm_provider": "chatgpt",
         "source": "https://platform.openai.com/docs/models/gpt-5.5",
@@ -30810,9 +33917,9 @@
         "supports_response_schema": true,
         "supports_vision": true,
         "supports_reasoning": true,
-        "supports_none_reasoning_effort": false,
-        "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": true
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
     },
     "chatgpt/gpt-5.3-codex-spark": {
         "litellm_provider": "chatgpt",
@@ -31143,24 +34250,28 @@
         "output_cost_per_token": 1.2e-06
     },
     "baseten/MiniMaxAI/MiniMax-M2.5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 1.2e-06
     },
     "baseten/nvidia/Nemotron-120B-A12B": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 7.5e-07
     },
     "baseten/zai-org/GLM-5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 3.15e-06
     },
     "baseten/zai-org/GLM-4.7": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.2e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
@@ -31178,24 +34289,28 @@
         "supports_vision": false
     },
     "baseten/zai-org/GLM-4.6": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 2.2e-06
     },
     "baseten/moonshotai/Kimi-K2.5": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 3e-06
     },
     "baseten/moonshotai/Kimi-K2-Thinking": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 2.5e-06
     },
     "baseten/moonshotai/Kimi-K2-Instruct-0905": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
@@ -31219,12 +34334,14 @@
         "supports_vision": false
     },
     "baseten/deepseek-ai/DeepSeek-V3.1": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
         "output_cost_per_token": 1.5e-06
     },
     "baseten/deepseek-ai/DeepSeek-V3-0324": {
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 7.7e-07,
         "litellm_provider": "baseten",
         "mode": "chat",
@@ -31250,14 +34367,21 @@
         "output_cost_per_token": 2e-06
     },
     "google.gemma-3-12b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 9e-08,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.9e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -31265,14 +34389,21 @@
         "supports_vision": true
     },
     "google.gemma-3-27b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.3e-07,
+        "input_cost_per_token_batches": 1.2e-07,
+        "input_cost_per_token_flex": 1.2e-07,
+        "input_cost_per_token_priority": 4e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 3.8e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.9e-07,
+        "output_cost_per_token_flex": 1.9e-07,
+        "output_cost_per_token_priority": 6.7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -31280,14 +34411,21 @@
         "supports_vision": true
     },
     "google.gemma-3-4b-it": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 8e-08,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 4e-08,
+        "output_cost_per_token_flex": 4e-08,
+        "output_cost_per_token_priority": 1.4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -31308,6 +34446,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -31334,7 +34473,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -31346,7 +34489,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -31367,7 +34510,11 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.25e-06,
@@ -31395,17 +34542,27 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5e-07,
-        "output_cost_per_token_batches": 2.5e-06
+        "output_cost_per_token_batches": 2.5e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_priority": 1.3125e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -31628,6 +34785,7 @@
     "gpt-4.1-2025-04-14": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -31714,6 +34872,7 @@
     "gpt-4.1-mini-2025-04-14": {
         "cache_read_input_token_cost": 1e-07,
         "cache_read_input_token_cost_priority": 1.75e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 4e-07,
         "input_cost_per_token_priority": 7e-07,
         "input_cost_per_token_batches": 2e-07,
@@ -31879,6 +35038,7 @@
     "gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.25e-06,
         "cache_read_input_token_cost_priority": 2.125e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_priority": 4.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
@@ -31903,6 +35063,7 @@
     "gpt-4o-2024-11-20": {
         "cache_read_input_token_cost": 1.25e-06,
         "cache_read_input_token_cost_priority": 2.125e-06,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_priority": 4.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
@@ -32108,6 +35269,44 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2026-07-23",
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/realtime",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "gpt-audio-mini-2025-12-15": {
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
@@ -32178,6 +35377,7 @@
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
         "cache_read_input_token_cost_priority": 1.25e-07,
+        "deprecation_date": "2027-01-14",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_priority": 2.5e-07,
         "input_cost_per_token_batches": 7.5e-08,
@@ -32268,6 +35468,34 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "gpt-4o-mini-search-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        },
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview"
+    },
     "gpt-4o-mini-transcribe": {
         "input_cost_per_audio_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
@@ -32302,6 +35530,26 @@
             "audio"
         ]
     },
+    "gpt-4o-mini-tts-2025-03-20": {
+        "deprecation_date": "2027-01-06",
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_second": 0.00025,
+        "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ]
+    },
     "gpt-4o-search-preview": {
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
@@ -32328,6 +35576,34 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "gpt-4o-search-preview-2025-03-11": {
+        "deprecation_date": "2026-07-23",
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_batches": 1.25e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        },
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview"
+    },
     "gpt-4o-transcribe": {
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
@@ -32423,10 +35699,13 @@
     "gpt-image-2.5-flare": {
         "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost_batches": 6.25e-07,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_image_token_batches": 4e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
         "supported_endpoints": [
             "/v1/images/generations",
@@ -32455,10 +35734,13 @@
     "gpt-image-2.5-sunburst": {
         "cache_read_input_image_token_cost": 2e-06,
         "cache_read_input_token_cost": 1.25e-06,
+        "cache_read_input_token_cost_batches": 6.25e-07,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_image_token_batches": 4e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
         "supported_endpoints": [
             "/v1/images/generations",
@@ -32977,7 +36259,8 @@
         "output_cost_per_token_flex": 5e-06,
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": false
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.1-codex-mini": {
         "cache_read_input_token_cost": 2.5e-08,
@@ -33199,6 +36482,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -33316,6 +36600,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -33427,16 +36712,22 @@
         "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
         "cache_creation_input_token_cost_batches": 6.25e-06,
         "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
+        "cache_creation_input_token_cost_ultrafast": 7.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
         "cache_read_input_token_cost_flex": 5e-07,
         "cache_read_input_token_cost_priority": 2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-06,
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_above_272k_tokens": 2e-05,
         "input_cost_per_token_above_272k_tokens_flex": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 4e-05,
         "input_cost_per_token_batches": 5e-06,
         "input_cost_per_token_above_272k_tokens_batches": 1e-05,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
         "input_cost_per_token_flex": 5e-06,
         "input_cost_per_token_priority": 2e-05,
+        "input_cost_per_token_ultrafast": 6e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -33448,8 +36739,10 @@
         "output_cost_per_token_above_272k_tokens_priority": 0.00015,
         "output_cost_per_token_batches": 2.5e-05,
         "output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
         "output_cost_per_token_flex": 2.5e-05,
         "output_cost_per_token_priority": 0.0001,
+        "output_cost_per_token_ultrafast": 0.0003,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -33484,6 +36777,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33560,19 +36854,24 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
     },
     "gpt-6-luna": {
         "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_decisions": 1e-07,
         "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_decisions": 2e-07,
         "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07,
         "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07,
         "cache_creation_input_token_cost_flex": 6.25e-08,
         "cache_creation_input_token_cost_priority": 2.5e-07,
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_decisions": 1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08,
         "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08,
         "cache_read_input_token_cost_batches": 5e-09,
@@ -33582,7 +36881,9 @@
         "cache_read_input_token_cost_flex": 5e-09,
         "cache_read_input_token_cost_priority": 2e-08,
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_decisions": 1e-07,
         "input_cost_per_token_above_272k_tokens": 2e-07,
+        "input_cost_per_token_above_272k_tokens_decisions": 2e-07,
         "input_cost_per_token_above_272k_tokens_flex": 1e-07,
         "input_cost_per_token_above_272k_tokens_priority": 4e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -33595,7 +36896,9 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
+        "output_cost_per_token_decisions": 0.0,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "output_cost_per_token_above_272k_tokens_decisions": 0.0,
         "output_cost_per_token_above_272k_tokens_flex": 3.75e-07,
         "output_cost_per_token_above_272k_tokens_priority": 1.5e-06,
         "output_cost_per_token_batches": 2.5e-07,
@@ -33637,6 +36940,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33710,6 +37014,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33785,6 +37090,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33859,6 +37165,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -33933,6 +37240,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_xhigh_reasoning_effort": true
@@ -34218,6 +37526,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34280,6 +37589,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34334,6 +37644,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34385,6 +37696,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34439,6 +37751,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
@@ -34496,6 +37809,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
@@ -34549,6 +37863,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34601,6 +37916,7 @@
         "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -34656,6 +37972,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34710,6 +38027,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
@@ -34767,7 +38085,8 @@
         "default_reasoning_effort": "none",
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
-        "supports_minimal_reasoning_effort": false
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
@@ -35062,11 +38381,13 @@
         "supports_response_schema": true,
         "supports_system_messages": false,
         "supports_tool_choice": true,
+        "supports_tool_search": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "supports_none_reasoning_effort": false,
-        "supports_xhigh_reasoning_effort": false,
-        "supports_minimal_reasoning_effort": true
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "deprecation_date": "2027-04-01"
     },
     "gpt-5.3-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
@@ -36446,6 +39767,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -36472,7 +39794,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.375e-06,
@@ -36500,7 +39826,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "crusoe/deepseek-ai/DeepSeek-R1-0528": {
         "input_cost_per_token": 3e-06,
@@ -36625,6 +39955,736 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
+    "inferenceapis/deepseek-ai/DeepSeek-V3": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-chat": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-reasoner": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v3": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4-flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 1.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4-pro": {
+        "cache_read_input_token_cost": 1.7e-07,
+        "input_cost_per_token": 1.72e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/deepseek-v4.1-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/glm-5.3": {
+        "cache_read_input_token_cost": 3.4e-07,
+        "input_cost_per_token": 1.82e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5.72e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/glm-5.3-flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/gpt-oss-120b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/gpt-oss-20b": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.9e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/kimi-k2.7-code": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 8.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4.42e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.1-8b-instant": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b-instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/llama-3.3-70b-versatile": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/minimax-m3": {
+        "cache_read_input_token_cost": 8e-08,
+        "input_cost_per_token": 3.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/MiniMaxAI/MiniMax-M3": {
+        "cache_read_input_token_cost": 8e-08,
+        "input_cost_per_token": 3.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 1.56e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/moonshotai/Kimi-K2.7-Code": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 8.9e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4.42e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/openai/gpt-oss-120b": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/openai/gpt-oss-20b": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.9e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/Qwen/Qwen3.8-Flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/qwen3-vl": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/qwen3-vl-235b": {
+        "input_cost_per_token": 2.6e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.15e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "inferenceapis/qwen3.8-flash": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/zai-org/GLM-5.3": {
+        "cache_read_input_token_cost": 3.4e-07,
+        "input_cost_per_token": 1.82e-06,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5.72e-06,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "inferenceapis/zai-org/GLM-5.3-Flash": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "inferenceapis",
+        "max_input_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://inferenceapis.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "text-completion-inception/mercury-edit-2": {
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 2.5e-07,
@@ -37077,51 +41137,64 @@
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "meta.llama3-1-405b-instruct-v1:0": {
-        "input_cost_per_token": 5.32e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 2.4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.6e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-1-70b-instruct-v1:0": {
-        "input_cost_per_token": 9.9e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 9.9e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "meta.llama3-1-8b-instruct-v1:0": {
-        "input_cost_per_token": 2.2e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "meta.llama3-2-11b-instruct-v1:0": {
-        "input_cost_per_token": 3.5e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "meta.llama3-1-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-07,
+        "output_cost_per_token_batches": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "meta.llama3-2-11b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 1.6e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -37129,10 +41202,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -37140,60 +41215,73 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-2-90b-instruct-v1:0": {
-        "input_cost_per_token": 2e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 2e-06,
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "meta.llama3-3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "meta.llama3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.65e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-06
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md"
     },
     "meta.llama3-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 6e-07
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md"
     },
     "meta.llama4-maverick-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "input_cost_per_token_batches": 1.2e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
         "output_cost_per_token_batches": 4.85e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -37206,15 +41294,17 @@
         "supports_tool_choice": false
     },
     "meta.llama4-scout-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.7e-07,
         "input_cost_per_token_batches": 8.5e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 10000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
         "output_cost_per_token_batches": 3.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -37447,6 +41537,49 @@
         ],
         "supports_audio_input": true
     },
+    "meta/muse-wonder-1.0": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "meta",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 2e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.0025,
+            "search_context_size_low": 0.0025,
+            "search_context_size_medium": 0.0025
+        },
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
     "meta_llama/Llama-3.3-70B-Instruct": {
         "litellm_provider": "meta_llama",
         "max_input_tokens": 128000,
@@ -37514,14 +41647,21 @@
         "supports_tool_choice": true
     },
     "minimax.minimax-m2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1000000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37530,33 +41670,46 @@
         "supports_vision": false
     },
     "minimax.minimax-m2.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 196000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "minimax.minimax-m2.5": {
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 196000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -37686,31 +41839,96 @@
         "max_input_tokens": 1000000,
         "max_output_tokens": 128000
     },
+    "minimax/MiniMax-H3": {
+        "litellm_provider": "minimax",
+        "mode": "video_generation",
+        "source": "https://platform.minimax.io/docs/guides/pricing-paygo",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_768p": 0.08,
+        "output_cost_per_second_2k": 0.13,
+        "input_cost_per_image": 0.04,
+        "provider_specific_entry": {
+            "minimax_free_input_images": 5
+        },
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "metadata": {
+            "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call."
+        }
+    },
+    "minimax/MiniMax-H3-Max": {
+        "litellm_provider": "minimax",
+        "mode": "video_generation",
+        "source": "https://platform.minimax.io/docs/guides/pricing-paygo",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_768p": 0.08,
+        "input_cost_per_image": 0.074,
+        "provider_specific_entry": {
+            "minimax_free_input_images": 2
+        },
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ],
+        "supported_endpoints": [
+            "/v1/videos"
+        ],
+        "metadata": {
+            "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call."
+        }
+    },
     "mistral.devstral-2-123b": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-07,
+        "input_cost_per_token_batches": 2e-07,
+        "input_cost_per_token_flex": 2e-07,
+        "input_cost_per_token_priority": 7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
+        "output_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_priority": 3.5e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "mistral.magistral-small-2509": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 40000,
         "max_tokens": 40000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.63e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -37720,13 +41938,19 @@
     },
     "mistral.ministral-3-14b-instruct": {
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_priority": 3.5e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_flex": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37736,13 +41960,19 @@
     },
     "mistral.ministral-3-3b-instruct": {
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 5e-08,
+        "output_cost_per_token_flex": 5e-08,
+        "output_cost_per_token_priority": 1.7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37752,13 +41982,19 @@
     },
     "mistral.ministral-3-8b-instruct": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7e-08,
+        "output_cost_per_token_flex": 7e-08,
+        "output_cost_per_token_priority": 2.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37767,47 +42003,55 @@
         "supports_vision": true
     },
     "mistral.mistral-7b-instruct-v0:2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md",
         "supports_tool_choice": true
     },
     "mistral.mistral-large-2402-v1:0": {
         "input_cost_per_token": 4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md",
         "supports_function_calling": true
     },
     "mistral.mistral-large-2407-v1:0": {
-        "input_cost_per_token": 3e-06,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 8191,
         "max_tokens": 8191,
         "mode": "chat",
-        "output_cost_per_token": 9e-06,
+        "output_cost_per_token": 6e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
     "mistral.mistral-large-3-675b-instruct": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.63e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -37820,47 +42064,62 @@
         "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md",
         "supports_function_calling": true
     },
     "mistral.mixtral-8x7b-instruct-v0:1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 32000,
-        "max_output_tokens": 8191,
-        "max_tokens": 8191,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md",
         "supports_tool_choice": true
     },
     "mistral.voxtral-mini-3b-2507": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 32768,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 4e-08,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 2e-08,
+        "output_cost_per_token_flex": 2e-08,
+        "output_cost_per_token_priority": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": true,
         "supports_system_messages": true,
         "supports_native_structured_output": true
     },
     "mistral.voxtral-small-24b-2507": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.7e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 32768,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": true,
         "supports_system_messages": true,
         "supports_native_structured_output": true
@@ -38080,7 +42339,6 @@
     },
     "mistral/voxtral-small-2507": {
         "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_second": 6.666666666666667e-05,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "mistral",
         "max_input_tokens": 32768,
@@ -38096,7 +42354,6 @@
     },
     "mistral/voxtral-small-latest": {
         "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_second": 6.666666666666667e-05,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "mistral",
         "max_input_tokens": 32768,
@@ -38112,6 +42369,7 @@
     },
     "mistral/zai-glm-5-2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-10-31",
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "mistral",
         "max_input_tokens": 1048576,
@@ -38242,6 +42500,7 @@
         "source": "https://mistral.ai/pricing#api-pricing"
     },
     "mistral/mistral-ocr-4-0": {
+        "deprecation_date": "2026-09-30",
         "litellm_provider": "mistral",
         "ocr_cost_per_page": 0.004,
         "ocr_cost_per_page_batches": 0.002,
@@ -38337,6 +42596,48 @@
         "max_tokens": 8192,
         "mode": "embedding"
     },
+    "mistral/mistral-large-4": {
+        "cache_read_input_token_cost": 6.8e-08,
+        "input_cost_per_token": 6.8e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 2.09e-06,
+        "reasoning_effort_levels": [
+            "none",
+            "high"
+        ],
+        "source": "https://docs.mistral.ai/models/mistral-large-4",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "mistral/mistral-large-4-0": {
+        "cache_read_input_token_cost": 6.8e-08,
+        "input_cost_per_token": 6.8e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 2.09e-06,
+        "reasoning_effort_levels": [
+            "none",
+            "high"
+        ],
+        "source": "https://docs.mistral.ai/models/mistral-large-4",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "mistral/mistral-large-latest": {
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 5e-07,
@@ -38627,14 +42928,19 @@
         "supports_vision": true
     },
     "moonshot.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.38e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -38645,17 +42951,23 @@
     },
     "moonshotai.kimi-k2.5": {
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.25e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true
     },
@@ -39388,6 +43700,7 @@
     "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": {
         "input_cost_per_token": 1.32e-06,
         "litellm_provider": "nebius",
+        "max_input_tokens": 979000,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813",
@@ -39397,12 +43710,14 @@
     "nebius/deepseek-ai/DeepSeek-V4.1-Flash": {
         "input_cost_per_token": 3e-07,
         "litellm_provider": "nebius",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 1048576,
-        "max_tokens": 1048576,
+        "max_input_tokens": 1048000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
         "supports_vision": true
     },
     "nebius/MiniMaxAI/MiniMax-M2.5": {
@@ -39647,6 +43962,16 @@
         "supports_reasoning": true,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B"
     },
+    "nebius/Qwen/Qwen3.8-27B": {
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "nebius",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 3e-06,
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "nebius/zai-org/GLM-5.1": {
         "max_tokens": 202752,
         "max_input_tokens": 202752,
@@ -39674,8 +43999,8 @@
     "nebius/zai-org/GLM-5.3": {
         "input_cost_per_token": 1.4e-06,
         "litellm_provider": "nebius",
-        "max_input_tokens": 1048576,
-        "max_tokens": 1048576,
+        "max_input_tokens": 1024000,
+        "max_tokens": 1024000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
         "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3",
@@ -39692,7 +44017,8 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_reasoning": true,
-        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash"
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash",
+        "supports_vision": true
     },
     "nebius/BAAI/bge-en-icl": {
         "max_tokens": 32768,
@@ -39731,14 +44057,21 @@
         "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B"
     },
     "nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_priority": 3.5e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -39746,14 +44079,21 @@
         "supports_vision": true
     },
     "nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.2e-07,
+        "output_cost_per_token_flex": 1.2e-07,
+        "output_cost_per_token_priority": 4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -39762,16 +44102,22 @@
     },
     "nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "output_cost_per_token_flex": 1.2e-07,
+        "output_cost_per_token_priority": 4.2e-07,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_native_structured_output": true,
         "supports_response_schema": true,
@@ -39779,13 +44125,19 @@
     },
     "nvidia.nemotron-super-3-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 6.5e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3.25e-07,
+        "output_cost_per_token_flex": 3.25e-07,
+        "output_cost_per_token_priority": 1.1375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -39955,6 +44307,39 @@
         "supports_web_search": true
     },
     "o3-deep-research": {
+        "cache_read_input_token_cost": 2.5e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "openai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "responses",
+        "output_cost_per_token": 4e-05,
+        "source": "https://developers.openai.com/api/docs/models/o3-deep-research",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "deprecation_date": "2026-07-23"
+    },
+    "o3-deep-research-2025-06-26": {
+        "deprecation_date": "2026-07-23",
         "cache_read_input_token_cost": 2.5e-06,
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
@@ -40184,6 +44569,39 @@
         "supports_web_search": true
     },
     "o4-mini-deep-research": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "responses",
+        "output_cost_per_token": 8e-06,
+        "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "deprecation_date": "2026-07-23"
+    },
+    "o4-mini-deep-research-2025-06-26": {
+        "deprecation_date": "2026-07-23",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "openai",
@@ -40658,6 +45076,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "reasoning_effort_levels": [],
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
         "supports_function_calling": true,
         "supports_response_schema": false
@@ -40674,6 +45093,72 @@
         "supports_function_calling": true,
         "supports_response_schema": false
     },
+    "oci/xai.grok-4.20-0309-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true
+    },
+    "oci/xai.grok-4.20-0309-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "oci/xai.grok-4.20-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true
+    },
+    "oci/xai.grok-4.20-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "oci",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "reasoning_effort_levels": [],
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "oci/xai.grok-code-fast-1": {
         "input_cost_per_token": 5e-06,
         "litellm_provider": "oci",
@@ -40731,6 +45216,32 @@
         "supports_response_schema": true,
         "supports_vision": true
     },
+    "oci/openai.gpt-oss-120b": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true
+    },
+    "oci/openai.gpt-oss-20b": {
+        "input_cost_per_token": 7e-08,
+        "litellm_provider": "oci",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3e-07,
+        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_reasoning": true
+    },
     "oci/cohere.embed-english-v3.0": {
         "input_cost_per_token": 1e-07,
         "litellm_provider": "oci",
@@ -41112,28 +45623,50 @@
         "output_cost_per_token": 0.0
     },
     "openai.gpt-oss-120b-1:0": {
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
     "openai.gpt-oss-20b-1:0": {
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_flex": 1.5e-07,
+        "output_cost_per_token_priority": 5.25e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -41141,14 +45674,21 @@
     },
     "openai.gpt-oss-safeguard-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -41156,2303 +45696,26 @@
     },
     "openai.gpt-oss-safeguard-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.2e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_flex": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_vision": false
     },
-    "openrouter/anthropic/claude-3-haiku": {
-        "cache_creation_input_token_cost": 3e-07,
-        "cache_creation_input_token_cost_above_1hr": 5e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_image": 0.0004,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "max_input_tokens": 200000,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-3.5-sonnet": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/anthropic/claude-3.7-sonnet": {
-        "input_cost_per_image": 0.0048,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/anthropic/claude-opus-4.1": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 1.875e-05,
-        "cache_creation_input_token_cost_above_1hr": 3e-05,
-        "cache_read_input_token_cost": 1.5e-06,
-        "input_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.6": {
-        "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.5": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.6": {
-        "supports_adaptive_thinking": true,
-        "supports_legacy_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 4096,
-        "supports_response_schema": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.5": {
-        "input_cost_per_image": 0.0048,
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_creation_input_token_cost_above_1hr": 6e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "input_cost_per_token_above_200k_tokens": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 2.25e-05,
-        "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 1024,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-haiku-4.5": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "supports_assistant_prefill": true,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "prompt_cache_min_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.7": {
-        "supports_adaptive_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": false,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true,
-        "prompt_cache_min_tokens": 2048,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-5": {
-        "prompt_cache_min_tokens": 512,
-        "supports_adaptive_thinking": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": false,
-        "supports_audio_input": false,
-        "supports_computer_use": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_max_reasoning_effort": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_xhigh_reasoning_effort": true
-    },
-    "openrouter/anthropic/claude-opus-5.5": {
-        "cache_creation_input_token_cost": 5e-06,
-        "cache_creation_input_token_cost_above_1hr": 8e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/bytedance/ui-tars-1.5-7b": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat": {
-        "input_cost_per_token": 3.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 8.9e-07,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat-v3-0324": {
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 147456,
-        "max_tokens": 147456,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-chat-v3.1": {
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_cache_hit": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 9.5e-07,
-        "supports_assistant_prefill": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 1.3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.2": {
-        "cache_read_input_token_cost": 1.345e-07,
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 2.69e-07,
-        "input_cost_per_token_cache_hit": 1.345e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "supports_assistant_prefill": true,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.2-exp": {
-        "cache_read_input_token_cost": 2e-08,
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 2.7e-07,
-        "input_cost_per_token_cache_hit": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4.1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1": {
-        "cache_read_input_token_cost": 1.4e-07,
-        "input_cost_per_token": 7e-07,
-        "input_cost_per_token_cache_hit": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 64000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1-0528": {
-        "cache_read_input_token_cost": 3.5e-07,
-        "input_cost_per_token": 5e-07,
-        "input_cost_per_token_cache_hit": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2.15e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-pro": {
-        "input_cost_per_token": 8.44944e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "output_cost_per_token": 1.689888e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 7.0412e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4.1-flash": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 6e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 393216,
-        "max_tokens": 393216,
-        "mode": "chat",
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-pro-0813": {
-        "input_cost_per_token": 4.62e-07,
-        "input_cost_per_token_cache_hit": 1.9272e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "output_cost_per_token": 1.386e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 1.54e-08,
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":0.00000132,"output_cost_per_token":0.00000396,"cache_read_input_token_cost":4.4e-8},
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/fireworks/ember-1": {
-        "input_cost_per_token": 3e-06,
-        "output_cost_per_token": 1.5e-05,
-        "cache_read_input_token_cost": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_image_size": false,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-20",
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_pdf_input": true,
-        "supports_reasoning": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-pro": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_pdf_input": true,
-        "supports_reasoning": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3-pro-preview": {
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "input_cost_per_token_batches": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "output_cost_per_token_batches": 6e-06,
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3-flash-preview": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 3e-06,
-        "output_cost_per_token": 3e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-flash-lite-preview": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 5e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 1.5e-06,
-        "output_cost_per_token": 1.5e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000
-    },
-    "openrouter/google/gemini-3.1-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 5e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_reasoning_token": 1.5e-06,
-        "output_cost_per_token": 1.5e-06,
-        "rpm": 2000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/completions",
-            "/v1/batch"
-        ],
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_audio_output": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_url_context": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "tpm": 800000
-    },
-    "openrouter/google/gemini-3.1-pro-preview": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image",
-            "audio",
-            "video"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/gryphe/mythomax-l2-13b": {
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 3686,
-        "max_tokens": 3686,
-        "mode": "chat",
-        "output_cost_per_token": 1.1e-07,
-        "supports_tool_choice": false,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mancer/weaver": {
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 6000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "supports_tool_choice": false,
-        "max_input_tokens": 8000,
-        "max_output_tokens": 6000,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3-70b-instruct": {
-        "input_cost_per_token": 5.9e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 7.9e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 8192,
-        "max_output_tokens": 8000
-    },
-    "openrouter/minimax/minimax-m2": {
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/devstral-2512": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-3b-2512": {
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-8b-2512": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-14b-2512": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-7b-instruct": {
-        "input_cost_per_token": 1.3e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 8191,
-        "mode": "chat",
-        "output_cost_per_token": 1.3e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8191
-    },
-    "openrouter/mistralai/mistral-large": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 102400,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 128000,
-        "max_output_tokens": 102400,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-3.1-24b-instruct": {
-        "input_cost_per_token": 3.51e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 102400,
-        "mode": "chat",
-        "output_cost_per_token": 5.55e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 128000,
-        "max_output_tokens": 102400,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-3.2-24b-instruct": {
-        "input_cost_per_token": 9.375e-08,
-        "litellm_provider": "openrouter",
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "supports_tool_choice": true,
-        "max_input_tokens": 256000,
-        "max_output_tokens": 16384,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mixtral-8x22b-instruct": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 52428,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 65536,
-        "max_output_tokens": 52428,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.5": {
-        "cache_read_input_token_cost": 7e-08,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-lightning": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo": {
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-16k": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "supports_tool_choice": true,
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4": {
-        "input_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "supports_tool_choice": true,
-        "max_input_tokens": 8191,
-        "max_output_tokens": 4096,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4.1": {
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-mini": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-nano": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.25e-06,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o-2024-05-13": {
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-chat": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/openai/gpt-5-codex": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/openai/gpt-5.2-codex": {
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-mini": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-nano": {
-        "cache_read_input_token_cost": 5e-09,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex-max": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2": {
-        "input_cost_per_image": 0,
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-chat": {
-        "input_cost_per_image": 0,
-        "cache_read_input_token_cost": 1.75e-07,
-        "input_cost_per_token": 1.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-pro": {
-        "input_cost_per_image": 0,
-        "input_cost_per_token": 2.1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 0.000168,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "default_reasoning_effort": "medium",
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "reasoning_effort_levels": [
-            "none",
-            "low",
-            "medium",
-            "high",
-            "xhigh",
-            "max"
-        ],
-        "source": "https://openrouter.ai/api/v1/models",
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol-pro": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-oss-120b": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-120b:batch": {
-        "input_cost_per_token": 2.96e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 1.36e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-20b": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 1.8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 9e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o1": {
-        "cache_read_input_token_cost": 7.5e-06,
-        "input_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini": {
-        "input_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4.4e-06,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "cache_read_input_token_cost": 5.5e-07,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini-high": {
-        "input_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4.4e-06,
-        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "cache_read_input_token_cost": 5.5e-07,
-        "supports_prompt_caching": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_pdf_input": true,
-        "supports_response_schema": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen-2.5-coder-32b-instruct": {
-        "input_cost_per_token": 6.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-vl-plus": {
-        "input_cost_per_token": 2.1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 6.3e-07,
-        "supports_tool_choice": true,
-        "supports_vision": true
-    },
-    "openrouter/qwen/qwen3-coder": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_tool_choice": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-plus": {
-        "cache_creation_input_token_cost": 8.125e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 3.9e-07,
-        "input_cost_per_token_above_32k_tokens": 1.17e-06,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06,
-        "cache_read_input_token_cost_above_32k_tokens": 2.34e-07,
-        "output_cost_per_token_above_32k_tokens": 5.85e-06,
-        "cache_read_input_token_cost": 1.3e-07,
-        "input_cost_per_token": 6.5e-07,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3.25e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b-2507": {
-        "cache_read_input_token_cost": 1.75e-08,
-        "input_cost_per_token": 8.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b-thinking-2507": {
-        "input_cost_per_token": 2.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 2.3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-plus": {
-        "cache_creation_input_token_cost": 4.0625e-07,
-        "input_cost_per_token_above_256k_tokens": 1.3e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06,
-        "output_cost_per_token_above_256k_tokens": 3.9e-06,
-        "input_cost_per_token": 3.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.95e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-35b-a3b": {
-        "input_cost_per_token": 3.125e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 1.5625e-07,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-27b": {
-        "input_cost_per_token": 1.95e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.56e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-122b-a10b": {
-        "input_cost_per_token": 2.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 2.08e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-flash-02-23": {
-        "input_cost_per_token": 6.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 2.6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-plus-02-15": {
-        "input_cost_per_token": 2.6e-07,
-        "input_cost_per_token_above_256k_tokens": 3.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.56e-06,
-        "output_cost_per_token_above_256k_tokens": 1.95e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-397b-a17b": {
-        "cache_read_input_token_cost": 2.25e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 3.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/switchpoint/router": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.4e-06,
-        "source": "https://openrouter.ai/switchpoint/router",
-        "supports_tool_choice": true
-    },
-    "openrouter/undi95/remm-slerp-l2-13b": {
-        "input_cost_per_token": 3.5e-07,
-        "litellm_provider": "openrouter",
-        "max_tokens": 5529,
-        "mode": "chat",
-        "output_cost_per_token": 6.5e-07,
-        "supports_tool_choice": false,
-        "max_input_tokens": 6144,
-        "max_output_tokens": 5529,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "max_tokens": 256000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/x-ai/grok-4",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-4.6": {
-        "input_cost_per_token": 4.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true,
-        "cache_read_input_token_cost": 8e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.6:exacto": {
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202800,
-        "max_output_tokens": 131000,
-        "max_tokens": 131000,
-        "mode": "chat",
-        "output_cost_per_token": 1.9e-06,
-        "source": "https://openrouter.ai/z-ai/glm-4.6:exacto",
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/xiaomi/mimo-v2-flash": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true
-    },
-    "openrouter/xiaomi/mimo-v2.5-pro": {
-        "input_cost_per_token": 4.35e-07,
-        "output_cost_per_token": 8.7e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3.6e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/xiaomi/mimo-v2.5": {
-        "input_cost_per_token": 1.4e-07,
-        "output_cost_per_token": 2.8e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 2.8e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_video_input": true,
-        "supports_response_schema": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.7": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 1.75e-06,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_assistant_prefill": true,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.7-flash": {
-        "input_cost_per_token": 6.05e-08,
-        "output_cost_per_token": 4e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5": {
-        "cache_read_input_token_cost": 1.2e-07,
-        "input_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.92e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.1": {
-        "input_cost_per_token": 9.66e-07,
-        "output_cost_per_token": 3.036e-06,
-        "cache_read_input_token_cost": 1.794e-07,
-        "cache_creation_input_token_cost": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.1": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-08",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_computer_use": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.5": {
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1.08e-06,
-        "cache_read_input_token_cost": 2.7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_computer_use": false,
-        "supports_pdf_input": false,
-        "supports_response_schema": true,
-        "supports_web_search": false
-    },
-    "openrouter/openrouter/auto": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_tokens": 2000000,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_video_input": true
-    },
-    "openrouter/openrouter/free": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_tokens": 200000,
-        "mode": "chat",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "openrouter/openrouter/bodybuilder": {
-        "input_cost_per_token": 0,
-        "output_cost_per_token": 0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat"
-    },
     "ovhcloud/DeepSeek-R1-Distill-Llama-70B": {
         "input_cost_per_token": 6.7e-07,
         "litellm_provider": "ovhcloud",
@@ -43655,66 +45918,6 @@
         "supports_response_schema": true,
         "supports_tool_choice": false
     },
-    "palm/chat-bison": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/chat-bison-001": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-001": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-safety-off": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "palm/text-bison-safety-recitation-off": {
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "palm",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "max_tokens": 1024,
-        "mode": "completion",
-        "output_cost_per_token": 1.25e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
     "parallel_ai/search": {
         "input_cost_per_query": 0.005,
         "litellm_provider": "parallel_ai",
@@ -43836,6 +46039,54 @@
         "mode": "chat",
         "output_cost_per_token": 2.8e-07
     },
+    "perplexity/pplx-decider-v1-27b": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/api-reference/decisions-post"
+    },
+    "perplexity/pplx-decider-v1.1-27b": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/getting-started/pricing"
+    },
+    "perplexity/pplx-decider-v1.2": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-latest": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-flash-v1.2": {
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
+    "perplexity/pplx-decider-flash-latest": {
+        "input_cost_per_token": 1e-08,
+        "litellm_provider": "perplexity",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.perplexity.ai/docs/decisions/quickstart"
+    },
     "perplexity/sonar": {
         "input_cost_per_token": 1e-06,
         "litellm_provider": "perplexity",
@@ -44202,6 +46453,14 @@
         "supports_reasoning": true,
         "supports_function_calling": true
     },
+    "perplexity/perplexity/deepseek-v4-pro-0813": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1.32e-06,
+        "output_cost_per_token": 3.96e-06,
+        "cache_read_input_token_cost": 4.4e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
     "perplexity/perplexity/glm-5.2": {
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.4e-06,
@@ -44302,42 +46561,52 @@
         "supports_reasoning": true
     },
     "qwen.qwen3-coder-480b-a35b-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 262000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_native_structured_output": true,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json"
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html"
     },
     "qwen.qwen3-235b-a22b-2507-v1:0": {
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_flex": 1.1e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 8.8e-07,
+        "output_cost_per_token_flex": 4.4e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_native_structured_output": true,
         "input_cost_per_token_batches": 1.1e-07,
-        "output_cost_per_token_batches": 4.4e-07
+        "output_cost_per_token_batches": 4.4e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"
     },
     "qwen.qwen3-coder-30b-a3b-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -44345,12 +46614,19 @@
     },
     "qwen.qwen3-32b-v1:0": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_flex": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
@@ -44375,12 +46651,12 @@
     "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.45e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44391,12 +46667,12 @@
     "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.41e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44407,12 +46683,12 @@
     "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.545e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.236e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44423,12 +46699,12 @@
     "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.41e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44439,12 +46715,12 @@
     "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 2.3e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.86e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44455,12 +46731,12 @@
     "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.45e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html",
         "supports_function_calling": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
@@ -44470,13 +46746,17 @@
     },
     "qwen.qwen3-vl-235b-a22b": {
         "input_cost_per_token": 5.3e-07,
+        "input_cost_per_token_batches": 2.6e-07,
+        "input_cost_per_token_priority": 9.3e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 2.66e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_batches": 1.33e-06,
+        "output_cost_per_token_priority": 4.66e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
         "supports_system_messages": true,
@@ -44486,16 +46766,22 @@
     },
     "qwen.qwen3-coder-next": {
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 8.75e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_flex": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supports_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -45199,6 +47485,53 @@
         "supports_vision": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
+    "scx-ai/DeepSeek-V4.1-flash": {
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 375000,
+        "max_tokens": 375000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://scx.ai/models/deepseek-v4-1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "scx-ai/GLM-5.3": {
+        "cache_read_input_token_cost": 1.8e-07,
+        "input_cost_per_token": 9.8e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3.08e-06,
+        "source": "https://scx.ai/models/glm-5-3",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": false
+    },
+    "scx-ai/Kimi-K3": {
+        "cache_read_input_token_cost": 2.8e-07,
+        "input_cost_per_token": 2.83e-06,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 1.413e-05,
+        "source": "https://scx.ai/models/kimi-k3",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": false
+    },
     "scx-ai/GLM-5.2": {
         "cache_read_input_token_cost": 2.2e-07,
         "input_cost_per_token": 6.1e-07,
@@ -45649,78 +47982,169 @@
         "mode": "image_edit",
         "output_cost_per_image": 0.4
     },
+    "us.stability.stable-conservative-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.4,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-creative-upscale-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.6
     },
+    "us.stability.stable-creative-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.6,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-fast-upscale-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.03
     },
+    "us.stability.stable-fast-upscale-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.03,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-outpaint-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.06
     },
+    "us.stability.stable-outpaint-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.06,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-control-sketch-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-control-sketch-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-control-structure-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-control-structure-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-erase-object-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-erase-object-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-inpaint-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-inpaint-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-remove-background-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-remove-background-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-search-recolor-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-search-recolor-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-search-replace-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-search-replace-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-style-guide-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.07
     },
+    "us.stability.stable-image-style-guide-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.07,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-style-transfer-v1:0": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
         "mode": "image_edit",
         "output_cost_per_image": 0.08
     },
+    "us.stability.stable-style-transfer-v1:0": {
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 77,
+        "mode": "image_edit",
+        "output_cost_per_image": 0.08,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "stability.stable-image-core-v1:1": {
         "litellm_provider": "bedrock",
         "max_input_tokens": 77,
@@ -45951,14 +48375,6 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
-    "together_ai/baai/bge-base-en-v1.5": {
-        "input_cost_per_token": 8e-09,
-        "litellm_provider": "together_ai",
-        "max_input_tokens": 512,
-        "mode": "embedding",
-        "output_cost_per_token": 0.0,
-        "output_vector_size": 768
-    },
     "together_ai/BAAI/bge-base-en-v1.5": {
         "input_cost_per_token": 8e-09,
         "litellm_provider": "together_ai",
@@ -46002,6 +48418,7 @@
         "supports_tool_choice": true
     },
     "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+        "deprecation_date": "2026-10-22",
         "input_cost_per_token": 1.04e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
@@ -46124,7 +48541,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
-        "source": "https://api.together.ai/v1/models",
+        "source": "https://www.together.ai/pricing",
         "supports_prompt_caching": true
     },
     "together_ai/Qwen/Qwen3.7-Plus": {
@@ -46158,7 +48575,7 @@
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-09-29",
+        "deprecation_date": "2026-10-22",
         "input_cost_per_token": 1.4e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1048576,
@@ -46188,7 +48605,6 @@
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": {
         "cache_read_input_token_cost": 1.3e-07,
-        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 1.32e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1048576,
@@ -46213,6 +48629,19 @@
         "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
+    "together_ai/meta-models/Muse-Spark-Open-816B-A42B": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://docs.together.ai/docs/serverless-models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "together_ai/moonshotai/Kimi-K3": {
         "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
@@ -46303,6 +48732,7 @@
         "supports_vision": true
     },
     "tts-1": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -46312,6 +48742,7 @@
         ]
     },
     "tts-1-hd": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_character": 3e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -46369,12 +48800,15 @@
     "us.amazon.nova-lite-v1:0": {
         "cache_read_input_token_cost": 1.5e-08,
         "input_cost_per_token": 6e-08,
+        "input_cost_per_token_batches": 3e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07,
+        "output_cost_per_token_batches": 1.2e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -46385,12 +48819,15 @@
     "us.amazon.nova-micro-v1:0": {
         "cache_read_input_token_cost": 8.75e-09,
         "input_cost_per_token": 3.5e-08,
+        "input_cost_per_token_batches": 1.75e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 1.4e-07,
+        "output_cost_per_token_batches": 7e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
@@ -46398,13 +48835,22 @@
     },
     "us.amazon.nova-pro-v1:0": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 8e-07,
+        "input_cost_per_token_batches": 4e-07,
+        "input_cost_per_token_flex": 4e-07,
+        "input_cost_per_token_priority": 1.4e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 300000,
         "max_output_tokens": 10000,
         "max_tokens": 10000,
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_flex": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
@@ -46456,7 +48902,11 @@
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
-        "output_cost_per_token_batches": 2.75e-06
+        "output_cost_per_token_batches": 2.75e-06,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "input_cost_per_token": 3e-06,
@@ -46554,7 +49004,11 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-1-20250805-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.125e-06,
@@ -46566,6 +49020,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
         "cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
+        "deprecation_date": "2027-04-08",
         "litellm_provider": "bedrock_converse",
         "supports_tool_search": true,
         "max_input_tokens": 200000,
@@ -46592,7 +49047,11 @@
         "prompt_cache_min_tokens": 1024,
         "input_cost_per_token_batches": 1.65e-06,
         "output_cost_per_token_batches": 8.25e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 4.5e-06,
@@ -46623,7 +49082,11 @@
         "supports_native_structured_output": true,
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us-gov.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46648,6 +49111,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -46657,7 +49121,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46682,6 +49151,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -46691,7 +49161,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46724,7 +49199,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -46759,7 +49239,12 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "thinking_always_on": true,
-        "supports_forced_tool_use": false
+        "supports_forced_tool_use": false,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.5e-05,
@@ -46793,7 +49278,12 @@
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5-1",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "us-gov.nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 7.2e-08,
@@ -46813,6 +49303,7 @@
         "supports_vision": false
     },
     "us-gov.nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -46820,6 +49311,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -46827,6 +49319,7 @@
         "supports_response_schema": true
     },
     "us-gov.nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -46834,6 +49327,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -46861,10 +49355,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -46874,19 +49374,31 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
     "us-gov.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2.64e-06,
         "output_cost_per_token": 7.92e-06,
         "cache_read_input_token_cost": 6.6e-07,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
@@ -46924,7 +49436,11 @@
         "prompt_cache_min_tokens": 4096,
         "input_cost_per_token_batches": 5.5e-07,
         "output_cost_per_token_batches": 2.75e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-opus-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -46983,7 +49499,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "global.anthropic.claude-opus-4-5-20251101-v1:0": {
         "cache_creation_input_token_cost": 6.25e-06,
@@ -47016,7 +49536,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "eu.anthropic.claude-opus-4-5-20251101-v1:0": {
         "cache_creation_input_token_cost": 6.875e-06,
@@ -47049,7 +49573,11 @@
         "bedrock_output_config_effort_ceiling": "high",
         "supports_parallel_tool_use_config": true,
         "prompt_cache_min_tokens": 4096,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-5-20251101-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -47061,7 +49589,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "max_input_tokens": 200000,
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
@@ -47082,29 +49610,41 @@
         "supports_vision": true,
         "bedrock_converse_supports_strict_tools": false,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-20250514-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "us.deepseek.r1-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
         "supports_function_calling": false,
         "supports_reasoning": true,
         "supports_tool_choice": false
     },
     "us.deepseek.v3.2": {
         "input_cost_per_token": 6.2e-07,
+        "input_cost_per_token_batches": 3.1e-07,
+        "input_cost_per_token_flex": 3.1e-07,
+        "input_cost_per_token_priority": 1.085e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
         "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 1.85e-06,
+        "output_cost_per_token_batches": 9.25e-07,
+        "output_cost_per_token_flex": 9.25e-07,
+        "output_cost_per_token_priority": 3.2375e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -47115,12 +49655,14 @@
     },
     "eu.deepseek.v3.2": {
         "input_cost_per_token": 7.4e-07,
+        "input_cost_per_token_flex": 3.7e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
         "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 2.22e-06,
+        "output_cost_per_token_flex": 1.11e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
@@ -47130,51 +49672,64 @@
         "supports_vision": false
     },
     "us.meta.llama3-1-405b-instruct-v1:0": {
-        "input_cost_per_token": 5.32e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 2.4e-06,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.6e-05,
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-1-70b-instruct-v1:0": {
-        "input_cost_per_token": 9.9e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 9.9e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "us.meta.llama3-1-8b-instruct-v1:0": {
-        "input_cost_per_token": 2.2e-07,
-        "litellm_provider": "bedrock",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-07,
-        "supports_function_calling": true,
-        "supports_tool_choice": false
-    },
-    "us.meta.llama3-2-11b-instruct-v1:0": {
-        "input_cost_per_token": 3.5e-07,
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 3.5e-07,
+        "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "us.meta.llama3-1-8b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-07,
+        "output_cost_per_token_batches": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
+        "supports_function_calling": true,
+        "supports_tool_choice": false
+    },
+    "us.meta.llama3-2-11b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 1.6e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "us.meta.llama3-2-1b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -47182,10 +49737,12 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-2-3b-instruct-v1:0": {
+        "deprecation_date": "2026-07-07",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -47193,42 +49750,51 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama3-2-90b-instruct-v1:0": {
-        "input_cost_per_token": 2e-06,
+        "deprecation_date": "2026-07-07",
+        "input_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 2e-06,
+        "output_cost_per_token": 7.2e-07,
+        "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json",
         "supports_function_calling": true,
         "supports_tool_choice": false,
         "supports_vision": true
     },
     "us.meta.llama3-3-70b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-07,
+        "input_cost_per_token_batches": 3.6e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "output_cost_per_token_batches": 3.6e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
     "us.meta.llama4-maverick-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "input_cost_per_token_batches": 1.2e-07,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
         "output_cost_per_token_batches": 4.85e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -47241,15 +49807,17 @@
         "supports_tool_choice": false
     },
     "us.meta.llama4-scout-17b-instruct-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.7e-07,
         "input_cost_per_token_batches": 8.5e-08,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_input_tokens": 10000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
         "output_cost_per_token_batches": 3.3e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md",
         "supported_modalities": [
             "text",
             "image"
@@ -47265,11 +49833,11 @@
         "input_cost_per_token": 2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md",
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
@@ -47659,7 +50227,7 @@
         "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-05,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -49431,7 +51999,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "cache_creation_input_token_cost_batches": 1.88e-06
     },
     "vertex_ai/claude-sonnet-5": {
         "deprecation_date": "2026-12-24",
@@ -49488,7 +52057,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -49539,7 +52108,8 @@
         "supports_vision": true,
         "supports_native_streaming": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "cache_creation_input_token_cost_batches": 1.88e-06
     },
     "vertex_ai/mistralai/codestral-2@001": {
         "input_cost_per_token": 3e-07,
@@ -49660,7 +52230,7 @@
         "supported_regions": [
             "global"
         ],
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -49681,7 +52251,7 @@
         "supported_regions": [
             "us-central1"
         ],
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -49708,7 +52278,8 @@
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -49765,7 +52336,14 @@
         "output_cost_per_token_flex": 6e-06,
         "output_cost_per_token_priority": 2.16e-05,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
@@ -49792,17 +52370,26 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
         "supports_reasoning": false,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-image": {
         "cache_read_input_token_cost": 5e-08,
         "cache_read_input_token_cost_batches": 2.5e-08,
         "cache_read_input_token_cost_flex": 2.5e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "input_cost_per_token_flex": 2.5e-07,
+        "input_cost_per_token_priority": 9e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -49813,8 +52400,17 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "output_cost_per_token_flex": 1.5e-06,
+        "output_cost_per_token_priority": 5.4e-06,
+        "regional_endpoint_uplift_multiplier": 1.1,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
@@ -49832,16 +52428,26 @@
         "output_cost_per_token": 3e-06,
         "output_cost_per_token_batches": 1.5e-06,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ]
+
     },
     "vertex_ai/gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_batches": 1.25e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-06-28",
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -49852,10 +52458,12 @@
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
+        "output_cost_per_token_priority": 2.7e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
             "/v1/batch"
         ],
         "supported_modalities": [
@@ -50034,6 +52642,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_url_context": true,
@@ -50060,7 +52669,7 @@
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
-        "mode": "image_generation",
+        "mode": "chat",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
@@ -50945,6 +53554,26 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "voyage/rerank-1": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 8000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
+    "voyage/rerank-lite-1": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 4000,
+        "max_output_tokens": 4000,
+        "max_tokens": 4000,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/rerank-2.5": {
         "input_cost_per_token": 5e-08,
         "litellm_provider": "voyage",
@@ -51081,6 +53710,16 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
+    "voyage/voyage-large-2-instruct": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 16000,
+        "max_tokens": 16000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1024,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/voyage-law-2": {
         "input_cost_per_token": 1.2e-07,
         "litellm_provider": "voyage",
@@ -51630,13 +54269,16 @@
     },
     "xai/grok-4.20-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -51644,8 +54286,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -51674,9 +54319,13 @@
     "xai/grok-4.3": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_image_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
@@ -51684,6 +54333,8 @@
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -51696,9 +54347,13 @@
     "xai/grok-4.3-latest": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_image_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
@@ -51706,6 +54361,8 @@
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -51826,53 +54483,71 @@
         "supports_web_search": true
     },
     "zai.glm-4.7": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 203000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2.2e-06,
+        "output_cost_per_token_batches": 1.1e-06,
+        "output_cost_per_token_flex": 1.1e-06,
+        "output_cost_per_token_priority": 3.85e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "zai.glm-5": {
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "input_cost_per_token_priority": 1.75e-06,
         "output_cost_per_token": 3.2e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.6e-06,
+        "output_cost_per_token_priority": 5.6e-06,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_native_structured_output": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
     },
     "zai.glm-4.7-flash": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 203000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_flex": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_response_schema": true,
         "supports_vision": false
@@ -52081,6 +54756,70 @@
         "litellm_provider": "vertex_ai",
         "mode": "vector_store"
     },
+    "vertex_ai/semantic-ranker-default": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-002": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-003": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
     "openai/container": {
         "code_interpreter_cost_per_session": 0.03,
         "litellm_provider": "openai",
@@ -52129,7 +54868,7 @@
         ]
     },
     "azure/sora-2": {
-        "deprecation_date": "2026-10-15",
+        "deprecation_date": "2026-11-02",
         "litellm_provider": "azure",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -52839,7 +55578,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -52848,7 +55587,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -53308,7 +56047,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m2": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 196608,
         "max_output_tokens": 4096,
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 1.2e-06,
@@ -53479,7 +56218,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 131072,
         "max_output_tokens": 4096,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 1e-07,
@@ -53542,7 +56281,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": {
         "max_tokens": 131072,
-        "max_input_tokens": 131072,
+        "max_input_tokens": 128000,
         "max_output_tokens": 131072,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -53551,7 +56290,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": {
         "max_tokens": 131072,
-        "max_input_tokens": 131072,
+        "max_input_tokens": 128000,
         "max_output_tokens": 131072,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -54147,7 +56886,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 262144,
         "max_output_tokens": 4096,
         "input_cost_per_token": 9e-07,
         "output_cost_per_token": 9e-07,
@@ -54172,15 +56911,6 @@
         "litellm_provider": "fireworks_ai",
         "mode": "embedding"
     },
-    "fireworks_ai/accounts/fireworks/models/": {
-        "max_tokens": 40960,
-        "max_input_tokens": 40960,
-        "max_output_tokens": 40960,
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "fireworks_ai",
-        "mode": "embedding"
-    },
     "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": {
         "max_tokens": 4096,
         "max_input_tokens": 4096,
@@ -54274,7 +57004,7 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": {
         "max_tokens": 4096,
-        "max_input_tokens": 4096,
+        "max_input_tokens": 262144,
         "max_output_tokens": 4096,
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
@@ -56143,6 +58873,7 @@
         ]
     },
     "gpt-4o-mini-tts-2025-12-15": {
+        "deprecation_date": "2027-01-06",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
@@ -56361,6 +59092,7 @@
         ]
     },
     "gemini-2.0-flash-exp-image-generation": {
+        "deprecation_date": "2025-11-14",
         "input_cost_per_token": 0.0,
         "litellm_provider": "gemini",
         "max_input_tokens": 32768,
@@ -56381,6 +59113,7 @@
         "supports_vision": true
     },
     "gemini/gemini-2.0-flash-exp-image-generation": {
+        "deprecation_date": "2025-11-14",
         "input_cost_per_token": 0.0,
         "litellm_provider": "gemini",
         "max_input_tokens": 32768,
@@ -56455,6 +59188,7 @@
         "gemini_native_audio": true
     },
     "gemini-2.5-flash-native-audio-preview-12-2025": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "gemini",
@@ -56485,6 +59219,7 @@
         "supports_web_search": true
     },
     "gemini-3.1-flash-live-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -56646,6 +59381,7 @@
         "gemini_native_audio": true
     },
     "gemini/gemini-2.5-flash-native-audio-preview-12-2025": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "gemini",
@@ -56675,9 +59411,11 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.1-flash-live-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_image_token": 1e-06,
         "input_cost_per_token": 7.5e-07,
@@ -56713,9 +59451,11 @@
         "rpm": 10,
         "gemini_audio_only_live": true,
         "input_cost_per_second": 8.33333333333e-05,
-        "supports_response_schema": false
+        "supports_response_schema": false,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.1-flash-tts-preview": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 1e-06,
         "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "gemini",
@@ -56758,7 +59498,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
-        ]
+        ],
+        "supports_prompt_caching": true
     },
     "gemini/gemini-3.8-flash-lite-tts": {
         "cache_read_input_token_cost": 1.25e-07,
@@ -56782,9 +59523,11 @@
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
-        ]
+        ],
+        "supports_prompt_caching": true
     },
     "gemini-2.5-flash-preview-tts": {
+        "deprecation_date": "2026-11-17",
         "input_cost_per_token": 5e-07,
         "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "gemini",
@@ -57146,7 +59889,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -57175,12 +59918,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -57193,12 +59943,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3.5e-08,
+        "input_cost_per_token_flex": 3.5e-08,
+        "input_cost_per_token_priority": 1.225e-07,
         "output_cost_per_token": 3e-07,
+        "output_cost_per_token_flex": 1.5e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.5e-07,
+        "output_cost_per_token_priority": 5.25e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -57211,12 +59968,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-120b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -57227,12 +59991,19 @@
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-20b": {
         "input_cost_per_token": 7e-08,
+        "input_cost_per_token_batches": 3e-08,
+        "input_cost_per_token_flex": 3e-08,
+        "input_cost_per_token_priority": 1.2e-07,
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_flex": 1e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1e-07,
+        "output_cost_per_token_priority": 3.5e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -57276,6 +60047,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57319,6 +60091,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57333,10 +60106,11 @@
         "cache_read_input_token_cost": 1.375e-06,
         "output_cost_per_token": 8.25e-05,
         "litellm_provider": "bedrock_mantle",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/responses"
@@ -57351,6 +60125,7 @@
         "supports_function_calling": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57427,6 +60202,7 @@
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57436,6 +60212,7 @@
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html"
     },
     "us.openai.gpt-5.6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 4.4e-06,
         "input_cost_per_token_above_272k_tokens": 8.8e-06,
         "cache_creation_input_token_cost": 5.5e-06,
@@ -57445,11 +60222,12 @@
         "output_cost_per_token": 2.2e-05,
         "output_cost_per_token_above_272k_tokens": 3.3e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57466,10 +60244,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-5.6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 4e-06,
         "input_cost_per_token_above_272k_tokens": 8e-06,
         "cache_creation_input_token_cost": 5e-06,
@@ -57479,11 +60259,12 @@
         "output_cost_per_token": 2e-05,
         "output_cost_per_token_above_272k_tokens": 3e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57500,10 +60281,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-5.6-terra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
         "cache_creation_input_token_cost": 2.75e-06,
@@ -57513,11 +60296,12 @@
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57534,10 +60318,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-5.6-terra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "cache_creation_input_token_cost": 2.5e-06,
@@ -57547,11 +60333,12 @@
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_272k_tokens": 1.8e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57568,10 +60355,12 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-5.6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
         "cache_creation_input_token_cost": 2.75e-07,
@@ -57581,11 +60370,12 @@
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57602,6 +60392,7 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -57613,7 +60404,8 @@
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_above_272k_tokens": 2.475e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57644,7 +60436,8 @@
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57675,7 +60468,8 @@
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57706,7 +60500,8 @@
         "output_cost_per_token": 3e-05,
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -57730,6 +60525,7 @@
         ]
     },
     "global.openai.gpt-5.6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_above_272k_tokens": 4e-07,
         "cache_creation_input_token_cost": 2.5e-07,
@@ -57739,11 +60535,12 @@
         "output_cost_per_token": 1.2e-06,
         "output_cost_per_token_above_272k_tokens": 1.8e-06,
         "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html",
         "supported_modalities": [
             "text",
             "image"
@@ -57760,6 +60557,7 @@
         "supports_vision": true,
         "supports_sampling_params": false,
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -57768,8 +60566,14 @@
         "input_cost_per_token_above_272k_tokens": 2.2e-05,
         "cache_creation_input_token_cost": 1.375e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165,
+        "cache_creation_input_token_cost_ultrafast": 8.25e-05,
         "cache_read_input_token_cost": 1.1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05,
+        "cache_read_input_token_cost_ultrafast": 6.6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132,
+        "input_cost_per_token_ultrafast": 6.6e-05,
         "output_cost_per_token": 5.5e-05,
         "output_cost_per_token_above_272k_tokens": 8.25e-05,
         "litellm_provider": "bedrock_mantle",
@@ -57777,6 +60581,8 @@
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495,
+        "output_cost_per_token_ultrafast": 0.00033,
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -57794,6 +60600,7 @@
         "supports_minimal_reasoning_effort": false,
         "supports_none_reasoning_effort": false,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57830,8 +60637,9 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57868,8 +60676,9 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -57878,19 +60687,29 @@
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html"
     },
     "us.openai.gpt-6-astra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1.1e-05,
         "input_cost_per_token_above_272k_tokens": 2.2e-05,
         "cache_creation_input_token_cost": 1.375e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165,
+        "cache_creation_input_token_cost_ultrafast": 8.25e-05,
         "cache_read_input_token_cost": 1.1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05,
+        "cache_read_input_token_cost_ultrafast": 6.6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132,
+        "input_cost_per_token_ultrafast": 6.6e-05,
         "output_cost_per_token": 5.5e-05,
         "output_cost_per_token_above_272k_tokens": 8.25e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495,
+        "output_cost_per_token_ultrafast": 0.00033,
         "supported_modalities": [
             "text",
             "image"
@@ -57907,12 +60726,15 @@
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_sampling_params": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
         "cache_creation_input_token_cost": 2.75e-06,
@@ -57922,6 +60744,7 @@
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -57936,18 +60759,21 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "us.openai.gpt-6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1.1e-07,
         "input_cost_per_token_above_272k_tokens": 2.2e-07,
         "cache_creation_input_token_cost": 1.375e-07,
@@ -57957,6 +60783,7 @@
         "output_cost_per_token": 5.5e-07,
         "output_cost_per_token_above_272k_tokens": 8.25e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -57971,31 +60798,43 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
     "global.openai.gpt-6-astra": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_above_272k_tokens": 2e-05,
         "cache_creation_input_token_cost": 1.25e-05,
         "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
+        "cache_creation_input_token_cost_ultrafast": 7.5e-05,
         "cache_read_input_token_cost": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05,
+        "cache_read_input_token_cost_ultrafast": 6e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
+        "input_cost_per_token_ultrafast": 6e-05,
         "output_cost_per_token": 5e-05,
         "output_cost_per_token_above_272k_tokens": 7.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
+        "output_cost_per_token_ultrafast": 0.0003,
         "supported_modalities": [
             "text",
             "image"
@@ -58012,8 +60851,10 @@
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_sampling_params": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58027,6 +60868,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58041,15 +60883,17 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "global.openai.gpt-6-sol": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "cache_creation_input_token_cost": 2.5e-06,
@@ -58059,6 +60903,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58073,14 +60918,16 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58094,6 +60941,7 @@
         "output_cost_per_token": 5e-07,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58108,15 +60956,17 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
     "global.openai.gpt-6-luna": {
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_above_272k_tokens": 2e-07,
         "cache_creation_input_token_cost": 1.25e-07,
@@ -58126,6 +60976,7 @@
         "output_cost_per_token": 5e-07,
         "output_cost_per_token_above_272k_tokens": 7.5e-07,
         "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
@@ -58140,14 +60991,16 @@
         "supports_function_calling": true,
         "supports_max_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
-        "supports_none_reasoning_effort": false,
+        "supports_none_reasoning_effort": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
+        "supports_sampling_params": false,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supported_endpoints": [
+            "/v1/chat/completions",
             "/v1/responses"
         ]
     },
@@ -58233,12 +61086,19 @@
     },
     "bedrock_mantle/google.gemma-4-31b": {
         "input_cost_per_token": 1.4e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.45e-07,
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_flex": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58252,12 +61112,19 @@
     },
     "bedrock_mantle/google.gemma-4-26b-a4b": {
         "input_cost_per_token": 1.3e-07,
+        "input_cost_per_token_batches": 6.5e-08,
+        "input_cost_per_token_flex": 6.5e-08,
+        "input_cost_per_token_priority": 2.275e-07,
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_flex": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_priority": 7e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58271,12 +61138,19 @@
     },
     "bedrock_mantle/google.gemma-4-e2b": {
         "input_cost_per_token": 4e-08,
+        "input_cost_per_token_batches": 2e-08,
+        "input_cost_per_token_flex": 2e-08,
+        "input_cost_per_token_priority": 7e-08,
         "output_cost_per_token": 8e-08,
+        "output_cost_per_token_flex": 4e-08,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
+        "output_cost_per_token_batches": 4e-08,
+        "output_cost_per_token_priority": 1.4e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "use_openai_responses_path": true,
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -58293,11 +61167,20 @@
         "input_cost_per_token": 1.25e-06,
         "output_cost_per_token": 2.5e-06,
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "input_cost_per_token_priority": 2.1875e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1048576,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_priority": 4.375e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -58307,18 +61190,24 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/xai.grok-4.6": {
         "use_openai_responses_path": true,
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 6.6e-06,
         "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -58359,15 +61248,108 @@
         "input_cost_per_token_batches": 5e-07,
         "output_cost_per_token_batches": 2.5e-06
     },
+    "bedrock_mantle/anthropic.claude-opus-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 5.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 8.8e-06,
+        "cache_read_input_token_cost": 2.2e-07,
+        "input_cost_per_token": 4.4e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html",
+        "thinking_always_on": true,
+        "supports_forced_tool_use": false
+    },
+    "bedrock_mantle/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
     "us.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 6.6e-06,
         "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_prompt_caching": false,
@@ -58376,14 +61358,26 @@
         "supports_vision": true
     },
     "global.xai.grok-4.6": {
+        "supports_regex_lookaround": false,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 6e-06,
         "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_flex": 2.5e-07,
+        "cache_read_input_token_cost_priority": 8.75e-07,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.5e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 500000,
         "max_output_tokens": 500000,
         "max_tokens": 500000,
         "mode": "chat",
+        "output_cost_per_token_flex": 3e-06,
+        "output_cost_per_token_priority": 1.05e-05,
         "source": "https://aws.amazon.com/bedrock/pricing/",
         "supports_function_calling": true,
         "supports_prompt_caching": false,
@@ -58445,6 +61439,41 @@
         "supports_tool_choice": false,
         "supports_vision": true
     },
+    "volcengine/doubao-seed-2-1-pro-260915": {
+        "cache_read_input_token_cost": 1.725e-07,
+        "input_cost_per_token": 8.625e-07,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 1024000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 4.3125e-06,
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
+    "volcengine/doubao-seed-2-1-lite-260915": {
+        "cache_read_input_audio_token_cost": 3.45e-07,
+        "cache_read_input_token_cost": 2.3e-08,
+        "input_cost_per_audio_token": 1.725e-06,
+        "input_cost_per_token": 1.15e-07,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 1024000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 3.88126e-07,
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
     "volcengine/doubao-seed-2-1-turbo-260628": {
         "cache_read_input_token_cost": 8.625e-08,
         "input_cost_per_token": 4.3125e-07,
@@ -58575,6 +61604,61 @@
             }
         ]
     },
+    "volcengine/doubao-seedance-2-5-260628": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.216,
+        "output_cost_per_second_480p": 0.096075,
+        "output_cost_per_second_720p": 0.216,
+        "output_cost_per_second_1080p": 0.5346,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-260128": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.141942857,
+        "output_cost_per_second_480p": 0.066003429,
+        "output_cost_per_second_720p": 0.141942857,
+        "output_cost_per_second_1080p": 0.354085714,
+        "output_cost_per_second_4k": 0.722057143,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-fast-260128": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.114171429,
+        "output_cost_per_second_480p": 0.053089714,
+        "output_cost_per_second_720p": 0.114171429,
+        "supported_modalities": ["text", "image", "video", "audio"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
+    "volcengine/doubao-seedance-2-0-mini-260615": {
+        "litellm_provider": "volcengine",
+        "mode": "video_generation",
+        "source": "https://www.volcengine.com/docs/82379/1544106",
+        "output_cost_per_second": 0.070971429,
+        "output_cost_per_second_480p": 0.033001714,
+        "output_cost_per_second_720p": 0.070971429,
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["video"],
+        "supported_endpoints": ["/v1/videos"],
+        "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}},
+        "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."}
+    },
     "bedrock/us-east-1/zai.glm-5": {
         "input_cost_per_token": 1e-06,
         "output_cost_per_token": 3.2e-06,
@@ -58635,7 +61719,11 @@
         "supports_native_structured_output": true,
         "supports_pdf_input": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": {
         "cache_creation_input_token_cost": 1.5e-06,
@@ -58661,7 +61749,11 @@
         "supports_native_structured_output": true,
         "supports_pdf_input": true,
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-4-5-20251001-v1:0",
+            "litellm_provider": "bedrock"
+        }
     },
     "snowflake/claude-sonnet-4-5": {
         "max_tokens": 16384,
@@ -59463,16 +62555,16 @@
     },
     "tencent/deepseek-v4-pro": {
         "cache_creation_input_token_cost": 0.0,
-        "cache_read_input_token_cost": 3.625e-09,
-        "input_cost_per_token": 4.35e-07,
-        "input_cost_per_token_cache_hit": 3.625e-09,
+        "cache_read_input_token_cost": 1.45e-07,
+        "input_cost_per_token": 1.74e-06,
+        "input_cost_per_token_cache_hit": 1.45e-07,
         "litellm_provider": "tencent",
         "max_input_tokens": 1000000,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 8.7e-07,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "output_cost_per_token": 3.48e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59498,7 +62590,7 @@
         "max_tokens": 384000,
         "mode": "chat",
         "output_cost_per_token": 2.8e-07,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59513,6 +62605,310 @@
         "supports_reasoning": true,
         "supports_vision": false
     },
+    "tencent/deepseek-v4-pro-0813": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 4.4e-08,
+        "input_cost_per_token": 1.32e-06,
+        "input_cost_per_token_cache_hit": 4.4e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "off_peak_pricing": {
+            "cache_read_input_token_cost": 2.2e-08,
+            "input_cost_per_token": 6.6e-07,
+            "output_cost_per_token": 1.98e-06,
+            "weekday_timezone": "Asia/Shanghai",
+            "windows": [
+                {
+                    "hours_utc": [
+                        "00:00-01:00",
+                        "04:00-06:00",
+                        "10:00-00:00"
+                    ],
+                    "weekdays": [
+                        1,
+                        2,
+                        3,
+                        4,
+                        5
+                    ]
+                },
+                {
+                    "hours_utc": "00:00-00:00",
+                    "weekdays": [
+                        6,
+                        7
+                    ]
+                }
+            ]
+        },
+        "output_cost_per_token": 3.96e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_vision": false
+    },
+    "tencent/deepseek-v4.1-flash": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_cache_hit": 6e-09,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "off_peak_pricing": {
+            "cache_read_input_token_cost": 3e-09,
+            "input_cost_per_token": 1.5e-07,
+            "output_cost_per_token": 6e-07,
+            "weekday_timezone": "Asia/Shanghai",
+            "windows": [
+                {
+                    "hours_utc": [
+                        "00:00-01:00",
+                        "04:00-06:00",
+                        "10:00-00:00"
+                    ],
+                    "weekdays": [
+                        1,
+                        2,
+                        3,
+                        4,
+                        5
+                    ]
+                },
+                {
+                    "hours_utc": "00:00-00:00",
+                    "weekdays": [
+                        6,
+                        7
+                    ]
+                }
+            ]
+        },
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3-flashx": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 7.5e-08,
+        "input_cost_per_token": 3.7e-07,
+        "input_cost_per_token_cache_hit": 7.5e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3-flash": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_cache_hit": 3e-08,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "tencent/glm-5.3": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_cache_hit": 2.6e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/glm-5.2": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_cache_hit": 2.6e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k3": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_cache_hit": 3e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.8-preview": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_cache_hit": 2.5e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.7-code-highspeed": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 3.8e-07,
+        "input_cost_per_token": 1.9e-06,
+        "input_cost_per_token_cache_hit": 3.8e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "tencent/kimi-k2.7-code": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_cache_hit": 1.9e-07,
+        "litellm_provider": "tencent",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "tencent/minimax-m3": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 6e-08,
@@ -59522,7 +62918,7 @@
         "max_input_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://www.tencentcloud.com/products/tokenhub",
+        "source": "https://www.tencentcloud.com/document/product/1300/78937",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -59677,13 +63073,16 @@
     },
     "xai/grok-4.20-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -59691,20 +63090,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent-0309": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": false,
         "supports_prompt_caching": true,
@@ -59713,8 +63118,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true,
         "supported_endpoints": [
@@ -59946,6 +63354,9 @@
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 1e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "search_context_cost_per_query": {
@@ -59968,6 +63379,7 @@
         ],
         "supports_audio_input": true,
         "supports_function_calling": true,
+        "supports_reasoning": true,
         "supports_video_input": true,
         "supports_vision": true,
         "supports_web_search": true,
@@ -59995,6 +63407,7 @@
         "supports_vision": true
     },
     "mistral/labs-leanstral-1-5": {
+        "deprecation_date": "2026-09-30",
         "input_cost_per_token": 0.0,
         "litellm_provider": "mistral",
         "max_input_tokens": 262144,
@@ -60140,8 +63553,8 @@
             {
                 "name": "claude-tool-search",
                 "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
-                "description": "Claude at version 4.5 or higher, in any id shape that contains claude-<family>-: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.",
+                "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
+                "description": "Claude at version 4.5 or higher, in any id shape that contains claude-<family>-: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.",
                 "model_info": {
                     "supports_tool_search": true
                 }
@@ -60215,6 +63628,9 @@
         "input_cost_per_audio_token": 2e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 98304,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
         "mode": "audio_transcription",
         "output_cost_per_token": 1.2e-05,
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
@@ -60237,6 +63653,9 @@
         "input_cost_per_audio_token": 3.5e-06,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "audio_transcription",
         "output_cost_per_token": 2.1e-05,
         "source": "https://ai.google.dev/gemini-api/docs/pricing",
@@ -60293,7 +63712,7 @@
     },
     "vertex_ai/gemini-3.5-live-translate-preview": {
         "input_cost_per_audio_token": 3.5e-06,
-        "input_cost_per_second": 8.83333333333e-05,
+        "input_cost_per_second": 8.75e-05,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
@@ -60415,18 +63834,18 @@
         "supports_vision": false
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
-        "cache_read_input_token_cost": 7e-09,
-        "cache_read_input_token_cost_priority": 8.75e-09,
-        "input_cost_per_token": 2.2e-07,
-        "input_cost_per_token_priority": 2.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
-        "output_cost_per_token_priority": 8.25e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -60436,13 +63855,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": {
         "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -60453,13 +63875,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token_priority": 8.25e-07,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
@@ -60511,18 +63936,18 @@
         "supports_vision": false
     },
     "fireworks_ai/deepseek-v4p1-flash": {
-        "cache_read_input_token_cost": 7e-09,
-        "cache_read_input_token_cost_priority": 8.75e-09,
-        "input_cost_per_token": 2.2e-07,
-        "input_cost_per_token_priority": 2.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-07,
-        "output_cost_per_token_priority": 8.25e-07,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -60532,13 +63957,16 @@
     },
     "fireworks_ai/deepseek-v4p1-flash-us": {
         "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -60549,13 +63977,16 @@
     },
     "fireworks_ai/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
+        "output_cost_per_token_priority": 8.25e-07,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
@@ -60684,14 +64115,17 @@
     },
     "fireworks_ai/muse-glimmer-30b": {
         "cache_read_input_token_cost": 4e-08,
+        "cache_read_input_token_cost_priority": 6e-08,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 3.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -60701,14 +64135,18 @@
     },
     "fireworks_ai/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 2.5e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60717,14 +64155,18 @@
     },
     "fireworks_ai/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token_priority": 3e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60733,14 +64175,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": {
         "cache_read_input_token_cost": 4e-08,
+        "cache_read_input_token_cost_priority": 6e-08,
         "deprecation_date": "2026-09-25",
         "input_cost_per_token": 3.5e-07,
+        "input_cost_per_token_priority": 5.25e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_priority": 2.25e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -60748,16 +64193,31 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "fireworks_ai/accounts/fireworks/models/muse-spark-open": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://fireworks.ai/models/fireworks/muse-spark-open",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
     "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 2.5e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -60766,14 +64226,18 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://api.fireworks.ai/v1/serverless/models",
+        "output_cost_per_token_priority": 3e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -62397,6 +65861,7 @@
         "supports_tool_choice": true,
         "supports_response_schema": true,
         "supports_reasoning": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "source": "https://deepinfra.com/pricing",
         "supports_audio_input": true
@@ -62881,6 +66346,40 @@
         "supports_vision": false,
         "source": "https://deepinfra.com/pricing"
     },
+    "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "max_tokens": 131072,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4.2e-07,
+        "cache_read_input_token_cost": 4.2e-09,
+        "supports_prompt_caching": true,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash"
+    },
+    "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "max_tokens": 131072,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 1.4e-07,
+        "output_cost_per_token": 4.2e-07,
+        "cache_read_input_token_cost": 4.2e-09,
+        "supports_prompt_caching": true,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017"
+    },
     "deepinfra/openai/gpt-oss-120b-Ultra": {
         "max_tokens": 131072,
         "max_input_tokens": 131072,
@@ -62989,13 +66488,16 @@
     },
     "xai/grok-4.20": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63003,21 +66505,27 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
     "xai/grok-4.20-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63025,21 +66533,27 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
     "xai/grok-4.20-reasoning-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63047,8 +66561,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -63203,6 +66720,23 @@
             "video"
         ]
     },
+    "xai/grok-imagine-video-1.5-lite": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.02,
+        "output_cost_per_second_1080p": 0.14,
+        "output_cost_per_second_480p": 0.02,
+        "output_cost_per_second_720p": 0.03,
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
     "xai/grok-imagine-video-1.5-2026-05-30": {
         "input_cost_per_image": 0.01,
         "litellm_provider": "xai",
@@ -63240,6 +66774,7 @@
         ]
     },
     "xai/grok-voice-transcribe-1.0": {
+        "deprecation_date": "2026-10-02",
         "input_cost_per_second": 2.778e-05,
         "litellm_provider": "xai",
         "metadata": {
@@ -63285,13 +66820,16 @@
     },
     "xai/grok-4.20-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -63299,20 +66837,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-non-reasoning-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -63320,20 +66864,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supported_endpoints": [
             "/v1/responses"
@@ -63345,20 +66895,26 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "xai/grok-4.20-multi-agent-latest": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "responses",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supported_endpoints": [
             "/v1/responses"
@@ -63370,15 +66926,18 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_response_schema": true
     },
     "groq/qwen/qwen3.8-27b": {
         "input_cost_per_token": 8e-07,
         "litellm_provider": "groq",
-        "max_input_tokens": 131042,
+        "max_input_tokens": 131072,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
@@ -63640,13 +67199,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63675,13 +67237,16 @@
     },
     "fireworks_ai/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -63704,6 +67269,33 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/accounts/fireworks/routers/auto": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "fireworks_ai/accounts/fireworks/routers/auto-instant": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "fireworks_ai/accounts/fireworks/routers/firerouter": {
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "fireworks_ai/glm-5p3-fast": {
         "cache_read_input_token_cost": 3.9e-07,
         "input_cost_per_token": 2.1e-06,
@@ -63738,12 +67330,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -63769,12 +67365,16 @@
     },
     "fireworks_ai/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -63783,13 +67383,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/inkling": {
         "cache_read_input_token_cost": 1.7e-07,
+        "cache_read_input_token_cost_priority": 1.7e-07,
+        "deprecation_date": "2026-11-07",
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_priority": 1e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 4.05e-06,
-        "source": "https://fireworks.ai/models/fireworks/inkling",
+        "output_cost_per_token_priority": 4.05e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -63821,12 +67425,12 @@
         "supports_tool_choice": true
     },
     "together_ai/Qwen/Qwen3.8-Flash": {
-        "input_cost_per_token": 9e-08,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 2.82e-07,
+        "output_cost_per_token": 4.7e-07,
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.5-fp4": {
@@ -63863,6 +67467,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
+        "deprecation_date": "2026-02-25",
         "input_cost_per_token": 6e-08,
         "output_cost_per_token": 2.5e-07,
         "litellm_provider": "together_ai",
@@ -63934,7 +67539,7 @@
     },
     "azure_ai/kimi-k2.7-code": {
         "cache_read_input_token_cost": 1.9e-07,
-        "deprecation_date": "2026-10-03",
+        "deprecation_date": "2027-04-16",
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 262144,
@@ -63957,52 +67562,26 @@
         "supports_vision": true
     },
     "azure_ai/deepseek-v4.1-flash": {
-        "cache_read_input_token_cost": 8e-09,
-        "input_cost_per_token": 3.75e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 1.2e-06,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "deprecation_date": "2026-12-15",
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
-    },
-    "azure_ai/muse-spark-1.3": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "azure_ai",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://ai.developer.meta.com/docs/pricing-rate-limits",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supported_modalities": [
-            "text",
-            "image"
-        ],
-        "supported_output_modalities": [
-            "text"
-        ],
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431"
     },
     "azure_ai/MAI-Image-2.6": {
         "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image_token": 3.8e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -64015,6 +67594,7 @@
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure_ai",
+        "max_input_tokens": 32000,
         "mode": "image_generation",
         "output_cost_per_image_token": 1.9e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
@@ -64135,6 +67715,7 @@
         "supports_vision": true
     },
     "azure_ai/deepseek-r1": {
+        "deprecation_date": "2026-08-13",
         "input_cost_per_token": 1.35e-06,
         "output_cost_per_token": 5.4e-06,
         "litellm_provider": "azure_ai",
@@ -64142,6 +67723,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/deepseek-v3-0324": {
+        "deprecation_date": "2026-07-13",
         "input_cost_per_token": 1.14e-06,
         "output_cost_per_token": 4.56e-06,
         "litellm_provider": "azure_ai",
@@ -64149,6 +67731,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/deepseek-v3.1": {
+        "deprecation_date": "2026-07-13",
         "input_cost_per_token": 1.23e-06,
         "output_cost_per_token": 4.94e-06,
         "litellm_provider": "azure_ai",
@@ -64156,6 +67739,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-3": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 3e-06,
         "output_cost_per_token": 1.5e-05,
         "litellm_provider": "azure_ai",
@@ -64163,6 +67747,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-3-mini": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2.5e-07,
         "output_cost_per_token": 1.27e-06,
         "litellm_provider": "azure_ai",
@@ -64170,6 +67755,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-4-fast-non-reasoning": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
@@ -64177,6 +67763,7 @@
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
     "azure_ai/grok-4-fast-reasoning": {
+        "deprecation_date": "2026-05-01",
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
@@ -64201,6 +67788,7 @@
         "supports_vision": false
     },
     "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64208,6 +67796,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -64215,6 +67804,7 @@
         "supports_response_schema": true
     },
     "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64222,6 +67812,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -64249,10 +67840,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64262,10 +67859,16 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64293,6 +67896,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64302,7 +67906,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64326,6 +67935,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64335,7 +67945,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64367,7 +67982,12 @@
         "supports_sampling_params": false,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_xhigh_reasoning_effort": true
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -64402,7 +68022,12 @@
         "supports_xhigh_reasoning_effort": true,
         "thinking_always_on": true,
         "supports_forced_tool_use": false,
-        "source": "https://aws.amazon.com/bedrock/pricing/"
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": {
         "cache_creation_input_token_cost": 1.5e-05,
@@ -64435,7 +68060,12 @@
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
         "supports_parallel_tool_use_config": true,
-        "prompt_cache_min_tokens": 512
+        "prompt_cache_min_tokens": 512,
+        "token_count_model": {
+            "model": "anthropic.claude-fable-5-1",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": {
         "input_cost_per_token": 7.2e-08,
@@ -64455,6 +68085,7 @@
         "supports_vision": false
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 2.4e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64462,6 +68093,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html",
         "supports_system_messages": true,
         "supports_vision": true,
         "supports_audio_input": false,
@@ -64469,6 +68101,7 @@
         "supports_response_schema": true
     },
     "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 7.2e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
@@ -64476,6 +68109,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.76e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html",
         "supports_system_messages": true,
         "supports_audio_input": false,
         "supports_function_calling": true,
@@ -64503,10 +68137,16 @@
         "input_cost_per_token": 8.4e-08,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.6e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64516,10 +68156,16 @@
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -64547,6 +68193,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64580,6 +68227,7 @@
         "supports_max_reasoning_effort": true,
         "supports_mid_conversation_system": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
         "supports_output_config": true,
         "supports_parallel_tool_use_config": true,
         "supports_pdf_input": true,
@@ -64717,14 +68365,15 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 2.64e-06,
-        "input_cost_per_token_above_272k_tokens": 5.28e-06,
-        "cache_creation_input_token_cost": 3.3e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06,
-        "cache_read_input_token_cost": 2.64e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.28e-07,
-        "output_cost_per_token": 1.584e-05,
-        "output_cost_per_token_above_272k_tokens": 2.376e-05
+        "input_cost_per_token": 2.7e-06,
+        "input_cost_per_token_above_272k_tokens": 5.4e-06,
+        "cache_creation_input_token_cost": 3.375e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 6.75e-06,
+        "cache_read_input_token_cost": 2.7e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5.4e-07,
+        "output_cost_per_token": 1.62e-05,
+        "output_cost_per_token_above_272k_tokens": 2.43e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html"
     },
     "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
         "litellm_provider": "bedrock_mantle",
@@ -64752,14 +68401,15 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 2.64e-07,
-        "input_cost_per_token_above_272k_tokens": 5.28e-07,
-        "cache_creation_input_token_cost": 3.3e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07,
-        "cache_read_input_token_cost": 2.64e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 5.28e-08,
-        "output_cost_per_token": 1.584e-06,
-        "output_cost_per_token_above_272k_tokens": 2.376e-06
+        "input_cost_per_token": 2.7e-07,
+        "input_cost_per_token_above_272k_tokens": 5.4e-07,
+        "cache_creation_input_token_cost": 3.375e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 6.75e-07,
+        "cache_read_input_token_cost": 2.7e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 5.4e-08,
+        "output_cost_per_token": 1.62e-06,
+        "output_cost_per_token_above_272k_tokens": 2.43e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html"
     },
     "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
         "litellm_provider": "bedrock_mantle",
@@ -64786,9 +68436,10 @@
         "supports_tool_choice": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_vision": true,
-        "input_cost_per_token": 3.3e-06,
-        "cache_read_input_token_cost": 3.3e-07,
-        "output_cost_per_token": 1.98e-05
+        "input_cost_per_token": 3.375e-06,
+        "cache_read_input_token_cost": 3.375e-07,
+        "output_cost_per_token": 2.025e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html"
     },
     "bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
         "use_openai_responses_path": true,
@@ -64894,9 +68545,10 @@
         "output_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64912,9 +68564,10 @@
         "output_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64925,6 +68578,77 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 6e-06,
+        "cache_creation_input_token_cost_above_1hr": 9.6e-06,
+        "cache_read_input_token_cost": 2.4e-07,
+        "input_cost_per_token": 4.8e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-05,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true,
+        "supports_forced_tool_use": false,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html"
+    },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
     "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1050000,
@@ -64980,9 +68704,10 @@
         "output_cost_per_token": 3.6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -64998,9 +68723,10 @@
         "output_cost_per_token": 7.2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -65012,91 +68738,131 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/deepseek.v3.1": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 5.8e-07,
+        "input_cost_per_token_batches": 2.9e-07,
+        "input_cost_per_token_flex": 2.9e-07,
+        "input_cost_per_token_priority": 1.015e-06,
         "output_cost_per_token": 1.68e-06,
+        "output_cost_per_token_flex": 8.4e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 128000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 8.4e-07,
+        "output_cost_per_token_priority": 2.94e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/moonshotai.kimi-k2-thinking": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_batches": 3e-07,
+        "input_cost_per_token_flex": 3e-07,
+        "input_cost_per_token_priority": 1.05e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_priority": 4.38e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-235b-a22b-2507": {
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_batches": 1.1e-07,
+        "input_cost_per_token_flex": 1.1e-07,
+        "input_cost_per_token_priority": 3.85e-07,
         "output_cost_per_token": 8.8e-07,
+        "output_cost_per_token_flex": 4.4e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 4.4e-07,
+        "output_cost_per_token_priority": 1.54e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-32b": {
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 32000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
+        "input_cost_per_token_flex": 7.5e-08,
+        "input_cost_per_token_priority": 2.625e-07,
         "output_cost_per_token": 6e-07,
+        "output_cost_per_token_flex": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 3e-07,
+        "output_cost_per_token_priority": 1.05e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_batches": 2.25e-07,
+        "input_cost_per_token_flex": 2.25e-07,
+        "input_cost_per_token_priority": 7.875e-07,
         "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_flex": 9e-07,
         "litellm_provider": "bedrock_mantle",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 262144,
         "max_output_tokens": 16000,
         "max_tokens": 16000,
         "mode": "chat",
+        "output_cost_per_token_batches": 9e-07,
+        "output_cost_per_token_priority": 3.15e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -65106,35 +68872,47 @@
     },
     "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": {
         "input_cost_per_token": 1.4e-07,
+        "input_cost_per_token_batches": 7e-08,
+        "input_cost_per_token_flex": 7e-08,
+        "input_cost_per_token_priority": 2.6e-07,
         "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_flex": 6e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_priority": 2.1e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_reasoning": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": {
         "input_cost_per_token": 5.3e-07,
+        "input_cost_per_token_batches": 2.6e-07,
+        "input_cost_per_token_flex": 2.6e-07,
+        "input_cost_per_token_priority": 9.3e-07,
         "output_cost_per_token": 2.66e-06,
+        "output_cost_per_token_flex": 1.33e-06,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
         "max_tokens": 8000,
         "mode": "chat",
+        "output_cost_per_token_batches": 1.33e-06,
+        "output_cost_per_token_priority": 4.66e-06,
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json"
     },
     "azure/us-gov/gpt-5.1": {
         "cache_read_input_token_cost": 1.71875e-07,
@@ -65277,7 +69055,7 @@
     "gemini/lyria-3.5": {
         "input_cost_per_token": 0,
         "litellm_provider": "gemini",
-        "max_input_tokens": 1048576,
+        "max_input_tokens": 131072,
         "max_output_tokens": 65536,
         "max_tokens": 65536,
         "mode": "chat",
@@ -65385,12 +69163,12 @@
         "mode": "responses",
         "supports_web_search": true,
         "supports_function_calling": true,
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "input_cost_per_token": 4e-06,
+        "output_cost_per_token": 2e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "input_cost_per_token_above_272k_tokens": 8e-06,
+        "output_cost_per_token_above_272k_tokens": 3e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
     "perplexity/openai/gpt-5.6-terra": {
@@ -65473,6 +69251,22 @@
         "cache_read_input_token_cost": 1.25e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
+    "perplexity/openai/gpt-5-nano": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 4e-07,
+        "cache_read_input_token_cost": 5e-09,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-5.3-codex": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 3.5e-06,
+        "output_cost_per_token": 2.8e-05,
+        "cache_read_input_token_cost": 3.5e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
     "perplexity/google/gemini-3.1-pro-preview": {
         "litellm_provider": "perplexity",
         "mode": "responses",
@@ -65509,6 +69303,7 @@
     "perplexity/google/gemini-3.5-flash-lite": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 3e-07,
@@ -65519,6 +69314,7 @@
     "perplexity/google/gemini-3.6-flash": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 1.5e-06,
@@ -65529,6 +69325,7 @@
     "perplexity/google/gemini-3.7-flash": {
         "litellm_provider": "perplexity",
         "mode": "responses",
+        "supports_sampling_params": false,
         "supports_web_search": true,
         "supports_function_calling": true,
         "input_cost_per_token": 7.5e-07,
@@ -65652,675 +69449,6 @@
         "cache_read_input_token_cost": 2.5e-07,
         "source": "https://docs.perplexity.ai/docs/agent-api/models"
     },
-    "openrouter/anthropic/claude-fable-5": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "thinking_always_on": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1e-06,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "prompt_cache_min_tokens": 512,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-fable-5.1": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "thinking_always_on": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.5e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "prompt_cache_min_tokens": 512,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.8": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 2.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-5": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "supports_sampling_params": false,
-        "supports_adaptive_thinking": true,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-2.5-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-08,
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 1e-08,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 3e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-07,
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 9e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_audio_token": 3e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash-lite": {
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 3e-08,
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_audio_token": 3e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.6-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.7-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.8-flash": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 3.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/openai/gpt-4o-mini": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 7.5e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1.25e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.3-codex": {
-        "input_cost_per_token": 1.75e-06,
-        "output_cost_per_token": 1.4e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 1.75e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-mini": {
-        "input_cost_per_token": 7.5e-07,
-        "output_cost_per_token": 4.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 7.5e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-nano": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-08,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna": {
-        "cache_creation_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
-        "input_cost_per_token_above_272k_tokens": 4e-07,
-        "output_cost_per_token_above_272k_tokens": 1.8e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna-pro": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 2e-08,
-        "cache_creation_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token_above_272k_tokens": 4e-07,
-        "output_cost_per_token_above_272k_tokens": 1.8e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra-pro": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o4-mini": {
-        "input_cost_per_token": 1.1e-06,
-        "output_cost_per_token": 4.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2.75e-07,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.20": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 1800000,
-        "max_tokens": 1800000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.20-multi-agent": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 1800000,
-        "max_tokens": 1800000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.3": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 900000,
-        "max_tokens": 900000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 5e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.5": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 3e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-4.6": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.2e-05,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/x-ai/grok-build-0.1": {
-        "input_cost_per_token": 1e-06,
-        "output_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 230400,
-        "max_tokens": 230400,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": false,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "output_cost_per_token_above_200k_tokens": 4e-06,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
     "baseten/zai-org/GLM-5.3": {
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.4e-06,
@@ -66369,2794 +69497,21 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
-    "openrouter/minimax/minimax-m3": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 512000,
-        "max_tokens": 512000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 6e-08,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.7-plus": {
-        "input_cost_per_token": 3.2e-07,
-        "input_cost_per_token_above_256k_tokens": 9.6e-07,
-        "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06,
-        "cache_read_input_token_cost_above_256k_tokens": 1.92e-07,
-        "output_cost_per_token_above_256k_tokens": 3.84e-06,
-        "output_cost_per_token": 1.28e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "cache_read_input_token_cost": 6.4e-08,
-        "supports_prompt_caching": true,
-        "cache_creation_input_token_cost": 4e-07,
-        "supports_audio_input": false,
-        "supports_pdf_input": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-6-astra": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra-pro": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3.8-flash": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 4.7e-07,
-        "cache_read_input_token_cost": 1.6e-08,
-        "cache_creation_input_token_cost": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-flash": {
-        "input_cost_per_token": 4.5e-08,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 2.85e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4-flash-vision-exp": {
-        "input_cost_per_token": 2.2e-07,
-        "output_cost_per_token": 6.6e-07,
-        "cache_read_input_token_cost": 7e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3": {
-        "input_cost_per_token": 1.4e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 2.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943717,
-        "max_tokens": 943717,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-27b": {
-        "input_cost_per_token": 4.2e-07,
-        "output_cost_per_token": 3e-06,
-        "cache_read_input_token_cost": 8.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-2.4t-a95b": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-lightning:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-max": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/qwen/qwen3.8-max",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/qwen/qwen3.8-max-0902": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_creation_input_token_cost": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-max-prime": {
-        "input_cost_per_token": 4e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_video_input": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/deepseek/deepseek-v4-flash-0731": {
-        "input_cost_per_token": 3e-08,
-        "output_cost_per_token": 3.2e-07,
-        "cache_read_input_token_cost": 1.6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.7-flash": {
-        "input_cost_per_token": 3e-08,
-        "input_cost_per_token_above_32k_tokens": 1e-07,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07,
-        "cache_read_input_token_cost_above_32k_tokens": 2e-08,
-        "output_cost_per_token_above_32k_tokens": 4e-07,
-        "output_cost_per_token": 1.3e-07,
-        "cache_read_input_token_cost": 6e-09,
-        "cache_creation_input_token_cost": 3.8e-08,
-        "input_cost_per_token_above_256k_tokens": 2e-07,
-        "output_cost_per_token_above_256k_tokens": 8e-07,
-        "cache_read_input_token_cost_above_256k_tokens": 4e-08,
-        "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-s-2.1": {
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 1.8e-07,
-        "cache_read_input_token_cost": 9e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-s-2.1:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k3": {
-        "input_cost_per_token": 3e-06,
-        "output_cost_per_token": 1.5e-05,
-        "cache_read_input_token_cost": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-xs-2.1": {
-        "input_cost_per_token": 6e-08,
-        "output_cost_per_token": 1.2e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/poolside/laguna-xs-2.1:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-3.1-flash-lite-image": {
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 1.5e-06,
-        "output_cost_per_image_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-flash-image": {
-        "input_cost_per_token": 5e-07,
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_image_token": 6e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3-pro-image": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "output_cost_per_image_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-5.2": {
-        "input_cost_per_token": 6.496e-07,
-        "output_cost_per_token": 2.0416e-06,
-        "cache_read_input_token_cost": 1.2064e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.2:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.7-code": {
-        "input_cost_per_token": 6.562e-07,
-        "output_cost_per_token": 3.3e-06,
-        "cache_read_input_token_cost": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-content-safety": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3.5-content-safety:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-ultra-550b-a55b": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 182520,
-        "max_tokens": 182520,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m3:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "source": "https://openrouter.ai/minimax/minimax-m3:free",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true
-    },
-    "openrouter/qwen/qwen3.7-max": {
-        "input_cost_per_token": 1.475e-06,
-        "output_cost_per_token": 4.425e-06,
-        "cache_read_input_token_cost": 2.95e-07,
-        "cache_creation_input_token_cost": 1.84375e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3-5": {
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": true,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-plus-20260420": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.8e-06,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "input_cost_per_token_above_256k_tokens": 3.75e-07,
-        "output_cost_per_token_above_256k_tokens": 2.25e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-flash": {
-        "input_cost_per_token": 1.875e-07,
-        "output_cost_per_token": 1.125e-06,
-        "cache_creation_input_token_cost": 2.34375e-07,
-        "input_cost_per_token_above_256k_tokens": 7.5e-07,
-        "output_cost_per_token_above_256k_tokens": 3e-06,
-        "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-35b-a3b": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-max-preview": {
-        "input_cost_per_token": 1.027e-06,
-        "output_cost_per_token": 6.162e-06,
-        "cache_creation_input_token_cost": 1.28375e-06,
-        "input_cost_per_token_above_128k_tokens": 1.58e-06,
-        "output_cost_per_token_above_128k_tokens": 9.48e-06,
-        "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.6-27b": {
-        "input_cost_per_token": 3.2e-07,
-        "output_cost_per_token": 2.7e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 262140,
-        "max_tokens": 262140,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5.5-pro": {
-        "input_cost_per_token": 3e-05,
-        "output_cost_per_token": 0.00018,
-        "input_cost_per_token_above_272k_tokens": 6e-05,
-        "output_cost_per_token_above_272k_tokens": 0.00027,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-chat-latest": {
-        "input_cost_per_token": 5e-06,
-        "output_cost_per_token": 3e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/deepseek/deepseek-v4-flash": {
-        "input_cost_per_token": 4.9e-08,
-        "output_cost_per_token": 9.8e-08,
-        "cache_read_input_token_cost": 9.8e-09,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2.6": {
-        "input_cost_per_token": 9.5e-07,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 1.6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_parallel_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-26b-a4b-it": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-26b-a4b-it:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-31b-it": {
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3.4e-07,
-        "cache_read_input_token_cost": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-4-31b-it:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5v-turbo": {
-        "input_cost_per_token": 1.2e-06,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 2.4e-07,
-        "deprecation_date": "2098-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202752,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.7": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 204800,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2.7:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 196608,
-        "max_output_tokens": 176947,
-        "max_tokens": 176947,
-        "mode": "chat",
-        "source": "https://openrouter.ai/minimax/minimax-m2.7:free",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false
-    },
-    "openrouter/mistralai/mistral-small-2603": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 1.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5-turbo": {
-        "input_cost_per_token": 1.2e-06,
-        "output_cost_per_token": 4e-06,
-        "cache_read_input_token_cost": 2.4e-07,
-        "deprecation_date": "2098-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 202752,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-super-120b-a12b": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-super-120b-a12b:free": {
-        "input_cost_per_token": 0.0,
-        "output_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.5-9b": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5.4-pro": {
-        "input_cost_per_token": 3e-05,
-        "output_cost_per_token": 0.00018,
-        "input_cost_per_token_above_272k_tokens": 6e-05,
-        "output_cost_per_token_above_272k_tokens": 0.00027,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-flash-image-preview": {
-        "input_cost_per_token": 5e-07,
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_image_token": 6e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-3.1-pro-preview-customtools": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/qwen/qwen3-max-thinking": {
-        "input_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_32k_tokens": 1.56e-06,
-        "output_cost_per_token_above_32k_tokens": 7.8e-06,
-        "output_cost_per_token": 3.9e-06,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-next": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 8e-07,
-        "cache_read_input_token_cost": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m2-her": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 1.2e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-audio": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "input_cost_per_audio_token": 3.2e-05,
-        "output_cost_per_audio_token": 6.4e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-audio-mini": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "input_cost_per_audio_token": 6e-07,
-        "output_cost_per_audio_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_audio_input": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/nvidia/nemotron-3-nano-30b-a3b": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 2e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.6v": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 9e-07,
-        "cache_read_input_token_cost": 5.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-3-pro-image-preview": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 1.2e-05,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "output_cost_per_image_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1-codex-mini": {
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/moonshotai/kimi-k2-thinking": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.5e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/voxtral-small-24b-2507": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_audio_token": 0.0001,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 26214,
-        "max_tokens": 26214,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-oss-safeguard-20b": {
-        "input_cost_per_token": 7.5e-08,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 3.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-32b-instruct": {
-        "input_cost_per_token": 1.04e-07,
-        "output_cost_per_token": 4.16e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-8b-thinking": {
-        "input_cost_per_token": 1.8e-07,
-        "output_cost_per_token": 2.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-8b-instruct": {
-        "input_cost_per_token": 1.17e-07,
-        "output_cost_per_token": 4.55e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash-image": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 2.5e-06,
-        "cache_read_input_token_cost": 3e-08,
-        "cache_creation_input_token_cost": 8.33333333333333e-08,
-        "cache_read_input_audio_token_cost": 1e-07,
-        "deprecation_date": "2027-03-15",
-        "input_cost_per_audio_token": 1e-06,
-        "output_cost_per_image_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3-vl-30b-a3b-thinking": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-30b-a3b-instruct": {
-        "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 5.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-5-pro": {
-        "input_cost_per_token": 1.5e-05,
-        "output_cost_per_token": 0.00012,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3-vl-235b-a22b-thinking": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-vl-235b-a22b-instruct": {
-        "input_cost_per_token": 2.1e-07,
-        "output_cost_per_token": 1.9e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-max": {
-        "input_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_32k_tokens": 1.56e-06,
-        "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06,
-        "cache_read_input_token_cost_above_32k_tokens": 3.12e-07,
-        "output_cost_per_token_above_32k_tokens": 7.8e-06,
-        "output_cost_per_token": 3.9e-06,
-        "cache_read_input_token_cost": 1.56e-07,
-        "cache_creation_input_token_cost": 9.75e-07,
-        "input_cost_per_token_above_128k_tokens": 1.95e-06,
-        "output_cost_per_token_above_128k_tokens": 9.75e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 3.9e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v3.1-terminus": {
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 1.35e-07,
-        "deprecation_date": "2026-09-28",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-flash": {
-        "input_cost_per_token": 1.95e-07,
-        "input_cost_per_token_above_32k_tokens": 3.25e-07,
-        "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07,
-        "cache_read_input_token_cost_above_32k_tokens": 6.5e-08,
-        "output_cost_per_token_above_32k_tokens": 1.625e-06,
-        "output_cost_per_token": 9.75e-07,
-        "cache_read_input_token_cost": 3.9e-08,
-        "cache_creation_input_token_cost": 2.4375e-07,
-        "input_cost_per_token_above_128k_tokens": 5.2e-07,
-        "output_cost_per_token_above_128k_tokens": 2.6e-06,
-        "cache_read_input_token_cost_above_128k_tokens": 1.04e-07,
-        "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-next-80b-a3b-thinking": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 1.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-next-80b-a3b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 1.1e-06,
-        "cache_read_input_token_cost": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-plus-2025-07-28": {
-        "cache_creation_input_token_cost": 3.25e-07,
-        "cache_read_input_token_cost": 5.2e-08,
-        "input_cost_per_token": 2.6e-07,
-        "output_cost_per_token": 7.8e-07,
-        "input_cost_per_token_above_256k_tokens": 7.8e-07,
-        "output_cost_per_token_above_256k_tokens": 2.34e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2-0905": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b-thinking-2507": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 2.4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 81920,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3.1": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5v": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 1.8e-06,
-        "cache_read_input_token_cost": 1.1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/codestral-2508": {
-        "input_cost_per_token": 3e-07,
-        "output_cost_per_token": 9e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 204800,
-        "max_tokens": 204800,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-coder-30b-a3b-instruct": {
-        "input_cost_per_token": 7e-08,
-        "output_cost_per_token": 2.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b-instruct-2507": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.2e-06,
-        "cache_read_input_token_cost": 1.1e-07,
-        "deprecation_date": "2026-12-31",
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-4.5-air": {
-        "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 8.5e-07,
-        "cache_read_input_token_cost": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_response_schema": false,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k2": {
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 98304,
-        "max_tokens": 98304,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-m1": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 40000,
-        "max_tokens": 40000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o3-pro": {
-        "input_cost_per_token": 2e-05,
-        "output_cost_per_token": 8e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemini-2.5-pro-preview": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/mistralai/mistral-medium-3": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 2e-06,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-pro-preview-05-06": {
-        "input_cost_per_token": 1.25e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost": 3.75e-07,
-        "input_cost_per_audio_token": 1.25e-06,
-        "input_cost_per_token_above_200k_tokens": 2.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_audio_input": true,
-        "supports_prompt_caching": true
-    },
-    "openrouter/meta-llama/llama-guard-4-12b": {
-        "input_cost_per_token": 1.8e-07,
-        "output_cost_per_token": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 163840,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-30b-a3b": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-8b": {
-        "input_cost_per_token": 1.17e-07,
-        "output_cost_per_token": 4.55e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-14b": {
-        "input_cost_per_token": 1.2e-07,
-        "output_cost_per_token": 2.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-32b": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 2.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3-235b-a22b": {
-        "input_cost_per_token": 4.55e-07,
-        "output_cost_per_token": 1.82e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o4-mini-high": {
-        "input_cost_per_token": 1.1e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 2.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta-llama/llama-4-maverick": {
-        "input_cost_per_token": 1.875e-07,
-        "output_cost_per_token": 6.525e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-4-scout": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/o1-pro": {
-        "input_cost_per_token": 0.00015,
-        "output_cost_per_token": 0.0006,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_web_search": true
-    },
-    "openrouter/google/gemma-3-4b-it": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-3-12b-it": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemma-3-27b-it": {
-        "input_cost_per_token": 8e-08,
-        "output_cost_per_token": 4.5e-07,
-        "cache_read_input_token_cost": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-saba": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 26214,
-        "max_tokens": 26214,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen2.5-vl-72b-instruct": {
-        "input_cost_per_token": 8e-07,
-        "output_cost_per_token": 1e-06,
-        "cache_read_input_token_cost": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-plus": {
-        "input_cost_per_token": 2.6e-07,
-        "output_cost_per_token": 7.8e-07,
-        "cache_read_input_token_cost": 5.2e-08,
-        "cache_creation_input_token_cost": 3.25e-07,
-        "input_cost_per_token_above_256k_tokens": 7.8e-07,
-        "output_cost_per_token_above_256k_tokens": 2.34e-06,
-        "cache_read_input_token_cost_above_256k_tokens": 1.56e-07,
-        "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-24b-instruct-2501": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 8e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-r1-distill-llama-70b": {
-        "deprecation_date": "2026-09-28",
-        "input_cost_per_token": 8e-07,
-        "output_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 7372,
-        "max_tokens": 7372,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_tool_choice": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/minimax/minimax-01": {
-        "input_cost_per_token": 2e-07,
-        "output_cost_per_token": 1.1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000192,
-        "max_output_tokens": 900172,
-        "max_tokens": 900172,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.3-70b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 3.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-2024-11-20": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/mistralai/mistral-large-2407": {
-        "input_cost_per_token": 2e-06,
-        "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-2.5-7b-instruct": {
-        "input_cost_per_token": 1e-07,
-        "output_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.2-1b-instruct": {
-        "input_cost_per_token": 2.7e-08,
-        "output_cost_per_token": 2.01e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 60000,
-        "max_output_tokens": 54000,
-        "max_tokens": 54000,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.2-3b-instruct": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 3.3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen-2.5-72b-instruct": {
-        "input_cost_per_token": 3.6e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-2024-08-06": {
-        "input_cost_per_token": 2.5e-06,
-        "output_cost_per_token": 1e-05,
-        "cache_read_input_token_cost": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/meta-llama/llama-3.1-70b-instruct": {
-        "input_cost_per_token": 4e-07,
-        "output_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta-llama/llama-3.1-8b-instruct": {
-        "input_cost_per_token": 5e-08,
-        "output_cost_per_token": 8e-08,
-        "cache_read_input_token_cost": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-nemo": {
-        "input_cost_per_token": 1.9e-08,
-        "output_cost_per_token": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4o-mini-2024-07-18": {
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "cache_read_input_token_cost": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_web_search": true,
-        "supports_vision": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false
-    },
-    "openrouter/google/gemma-2-27b-it": {
-        "input_cost_per_token": 6.5e-07,
-        "output_cost_per_token": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 2048,
-        "max_tokens": 2048,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4-turbo": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-4-turbo-preview": {
-        "input_cost_per_token": 1e-05,
-        "output_cost_per_token": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "source": "https://openrouter.ai/openai/gpt-4-turbo-preview",
-        "supports_function_calling": true,
-        "supports_tool_choice": true,
-        "supports_response_schema": true,
-        "supports_vision": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-instruct": {
-        "input_cost_per_token": 1.5e-06,
-        "output_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 4095,
-        "max_output_tokens": 3685,
-        "max_tokens": 3685,
-        "mode": "chat",
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_tool_choice": false,
-        "supports_response_schema": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
     "together_ai/arcee-ai/trinity-mini": {
         "input_cost_per_token": 4.5e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000
     },
     "vertex_ai/gemini-2.5-flash-native-audio": {
         "deprecation_date": "2026-12-13",
         "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_image_token": 3e-06,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_video_token": 3e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
@@ -69191,7 +69546,7 @@
     },
     "vertex_ai/gemini-3.5-transcribe-live": {
         "input_cost_per_audio_token": 3.5e-06,
-        "input_cost_per_second": 8.33333333333e-05,
+        "input_cost_per_second": 8.75e-05,
         "litellm_provider": "vertex_ai",
         "mode": "audio_transcription",
         "output_cost_per_token": 2.1e-05,
@@ -69249,6 +69604,15 @@
         "source": "https://developers.openai.com/api/docs/pricing",
         "supports_reasoning": true
     },
+    "gpt-5.5-cyber-preview": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 1.25e-05,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_reasoning": true
+    },
     "gpt-rosalind-research": {
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 5e-06,
@@ -69262,45 +69626,75 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 3.5e-06,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 4096,
+        "max_tokens": 4096
     },
     "together_ai/meta-llama/Llama-3.2-1B-Instruct": {
         "input_cost_per_token": 6e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072
     },
     "together_ai/meta-llama/Llama-3.2-3B-Instruct": {
         "input_cost_per_token": 6e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 131072,
+        "max_tokens": 131072
     },
     "together_ai/Qwen/Qwen2-1.5B-Instruct": {
         "input_cost_per_token": 2e-08,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 2e-08,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
     },
     "together_ai/Qwen/Qwen2.5-14B-Instruct": {
         "input_cost_per_token": 8e-07,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 8e-07,
-        "source": "https://api.together.ai/v1/models"
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
     },
     "together_ai/Qwen/Qwen2.5-72B-Instruct": {
         "input_cost_per_token": 1.2e-06,
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "max_input_tokens": 32768,
+        "max_tokens": 32768
+    },
+    "together_ai/Salesforce/Llama-Rank-V1": {
+        "deprecation_date": "2026-02-06",
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
         "source": "https://api.together.ai/v1/models"
     },
+    "together_ai/meta-llama/Meta-Llama-3.1-8B": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "completion",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.xyz/v1/models"
+    },
     "together_ai/together/Tev1-4B-experimental": {
-        "cache_read_input_token_cost": 4.2e-08,
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "together_ai",
         "max_input_tokens": 32768,
@@ -69510,7 +69904,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/google/gemma-4-31B-it": {
-        "deprecation_date": "2026-09-14",
+        "deprecation_date": "2026-09-15",
         "input_cost_per_token": 3.9e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
@@ -69643,6 +70037,7 @@
     },
     "together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2026-08-27",
         "input_cost_per_token": 6e-07,
         "litellm_provider": "together_ai",
         "max_input_tokens": 512288,
@@ -69652,7 +70047,7 @@
         "source": "https://api.together.ai/v1/models"
     },
     "together_ai/openai/gpt-oss-20b": {
-        "deprecation_date": "2026-09-14",
+        "deprecation_date": "2026-09-15",
         "input_cost_per_token": 5e-08,
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
@@ -69707,7 +70102,7 @@
         "cache_read_input_token_cost": 4.13e-07,
         "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 6.6e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69762,6 +70157,9 @@
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_batches": 2.75e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_batches": 8.25e-06,
@@ -69787,7 +70185,7 @@
         "cache_read_input_token_cost": 1.38e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69823,7 +70221,7 @@
         "input_cost_per_token": 1.65e-05,
         "input_cost_per_token_batches": 8.25e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000132,
         "output_cost_per_token_batches": 6.6e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69833,7 +70231,7 @@
         "cache_read_input_token_cost": 1.375e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69857,7 +70255,7 @@
         "cache_read_input_token_cost": 1.925e-07,
         "input_cost_per_token": 1.925e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -69865,7 +70263,7 @@
         "input_cost_per_token": 2.31e-05,
         "input_cost_per_token_batches": 1.155e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.0001848,
         "output_cost_per_token_batches": 9.24e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69877,7 +70275,7 @@
         "input_cost_per_token": 1.925e-06,
         "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "output_cost_per_token_priority": 3.08e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -69916,7 +70314,7 @@
         "input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
         "input_cost_per_token_batches": 1.65e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000198,
         "output_cost_per_token_above_272k_tokens": 0.000297,
         "output_cost_per_token_above_272k_tokens_batches": 0.0001485,
@@ -69925,18 +70323,47 @@
     },
     "azure/eu/gpt-6-astra": {
         "deprecation_date": "2028-01-11",
-        "cache_creation_input_token_cost": 1.375e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
-        "cache_read_input_token_cost": 1.1e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token": 1.1e-05,
-        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.5e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 3e-05,
+        "cache_read_input_token_cost": 1.2e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.4e-06,
+        "input_cost_per_token": 1.2e-05,
+        "input_cost_per_token_above_272k_tokens": 2.4e-05,
         "litellm_provider": "azure",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 5.5e-05,
-        "output_cost_per_token_above_272k_tokens": 8.25e-05,
-        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
-        "supports_reasoning": true
+        "output_cost_per_token": 6e-05,
+        "output_cost_per_token_above_272k_tokens": 9e-05,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": false,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
     },
     "azure/eu/gpt-6-luna": {
         "deprecation_date": "2028-03-11",
@@ -70046,12 +70473,29 @@
         "output_cost_per_token_batches": 2.42e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
+    "azure/eu/o3": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_batches": 1.1e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-06,
+        "output_cost_per_token_batches": 4.4e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
     "azure/eu/o3-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_batches": 1.1e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8.8e-06,
         "output_cost_per_token_batches": 4.4e-06,
@@ -70066,12 +70510,29 @@
         "output_cost_per_token": 4.4e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
+    "azure/eu/o4-mini": {
+        "deprecation_date": "2026-11-19",
+        "cache_read_input_token_cost": 3.03e-07,
+        "input_cost_per_token": 1.21e-06,
+        "input_cost_per_token_batches": 6.05e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 4.84e-06,
+        "output_cost_per_token_batches": 2.42e-06,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
     "azure/eu/o4-mini-2025-04-16": {
         "deprecation_date": "2026-11-19",
         "cache_read_input_token_cost": 3.03e-07,
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.84e-06,
         "output_cost_per_token_batches": 2.42e-06,
@@ -70117,7 +70578,8 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "gemini/gemini-3.8-live-extended-thinking": {
         "input_cost_per_audio_token": 3e-06,
@@ -70138,14 +70600,15 @@
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_reasoning": true
     },
     "azure/us/codex-mini": {
         "deprecation_date": "2026-11-15",
         "cache_read_input_token_cost": 4.13e-07,
         "input_cost_per_token": 1.65e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 6.6e-06,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70200,6 +70663,9 @@
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_batches": 2.75e-06,
         "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
         "output_cost_per_token_batches": 8.25e-06,
@@ -70225,7 +70691,7 @@
         "cache_read_input_token_cost": 1.38e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70261,7 +70727,7 @@
         "input_cost_per_token": 1.65e-05,
         "input_cost_per_token_batches": 8.25e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000132,
         "output_cost_per_token_batches": 6.6e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70271,7 +70737,7 @@
         "cache_read_input_token_cost": 1.375e-07,
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70295,7 +70761,7 @@
         "cache_read_input_token_cost": 1.925e-07,
         "input_cost_per_token": 1.925e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
     },
@@ -70303,7 +70769,7 @@
         "input_cost_per_token": 2.31e-05,
         "input_cost_per_token_batches": 1.155e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.0001848,
         "output_cost_per_token_batches": 9.24e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70315,7 +70781,7 @@
         "input_cost_per_token": 1.925e-06,
         "input_cost_per_token_priority": 3.85e-06,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.54e-05,
         "output_cost_per_token_priority": 3.08e-05,
         "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
@@ -70354,7 +70820,7 @@
         "input_cost_per_token_above_272k_tokens_batches": 3.3e-05,
         "input_cost_per_token_batches": 1.65e-05,
         "litellm_provider": "azure",
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 0.000198,
         "output_cost_per_token_above_272k_tokens": 0.000297,
         "output_cost_per_token_above_272k_tokens_batches": 0.0001485,
@@ -70496,7 +70962,7 @@
         "supports_audio_input": true
     },
     "azure/gpt-realtime-translate": {
-        "deprecation_date": "2027-05-06",
+        "deprecation_date": "2027-11-09",
         "input_cost_per_second": 0.000566666666667,
         "litellm_provider": "azure",
         "max_input_tokens": 32000,
@@ -70951,6 +71417,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "supports_web_search": true
     },
@@ -70968,6 +71435,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_sampling_params": false,
         "supports_vision": true,
         "supports_web_search": true
     },
@@ -71639,26 +72107,150 @@
         "supports_reasoning": true,
         "supports_vision": true
     },
-    "openrouter/typesafe/jev-1.13": {
-        "input_cost_per_token": 4.2e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32000,
-        "max_output_tokens": 28800,
-        "max_tokens": 28800,
+    "bespoke/nimble-latest": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/typesafe/jev-1.13"
+        "source": "https://github.com/bespokelabsai/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "bespoke/nimble": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://ollama.com/library/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately"
+        }
+    },
+    "bespoke/bespokelabs/Bespoke-Nimble-9B": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "bespoke",
+        "max_input_tokens": 8192,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/bespokelabsai/nimble",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/english": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/multilingual": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "laya/typed-decisions": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "laya",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://github.com/NandhaKishorM/laya",
+        "supported_endpoints": [
+            "/v1/systemone"
+        ],
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "strands_decider/strands-decider-2B-hobson-v19": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "strands_decider",
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19",
+        "metadata": {
+            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+        }
+    },
+    "nace/drex-v1.0": {
+        "input_cost_per_token": 4e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 32768,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-v1.5": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-v2.0": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
+    },
+    "nace/drex-latest": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "nace",
+        "max_input_tokens": 131072,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://console.nace.ai/docs/drex/reference/models"
     },
     "typesafe/jev-1.13.0": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://docs.typesafe.ai/models"
     },
+    "typesafe/jev-1.14.0": {
+        "input_cost_per_token": 4.2e-08,
+        "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.typesafe.ai/models",
+        "supports_box_questions": true
+    },
     "typesafe/jev-latest": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://docs.typesafe.ai/models"
@@ -71666,9 +72258,11 @@
     "typesafe/jev-preview": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "typesafe",
+        "max_input_tokens": 65536,
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
-        "source": "https://docs.typesafe.ai/models"
+        "source": "https://docs.typesafe.ai/models",
+        "supports_box_questions": true
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash": {
         "cache_read_input_token_cost": 3e-08,
@@ -71705,4109 +72299,109 @@
         "max_input_tokens": 1049000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://wandb.ai/site/pricing/tokens/",
+        "source": "https://docs.wandb.ai/inference/models.md",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
-        "supports_tool_choice": true
-    },
-    "openrouter/~anthropic/claude-fable-latest": {
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_1hr": 2e-05,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-haiku-latest": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-opus-latest": {
-        "cache_creation_input_token_cost": 5e-06,
-        "cache_creation_input_token_cost_above_1hr": 8e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~anthropic/claude-sonnet-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~deepseek/deepseek-flash-latest": {
-        "cache_read_input_token_cost": 6e-09,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~deepseek/deepseek-pro-latest": {
-        "cache_read_input_token_cost": 4.4e-08,
-        "input_cost_per_token": 1.32e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 384000,
-        "max_tokens": 384000,
-        "mode": "chat",
-        "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8},
-        "output_cost_per_token": 3.96e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/~deepseek/deepseek-v4-flash-latest": {
-        "cache_read_input_token_cost": 1.6e-08,
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 6.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/~google/gemini-flash-latest": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 7.5e-08,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 7.5e-07,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~google/gemini-pro-latest": {
-        "cache_creation_input_token_cost": 3.75e-07,
-        "cache_read_input_audio_token_cost": 2e-07,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
-        "input_cost_per_audio_token": 2e-06,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_200k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_200k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~moonshotai/kimi-latest": {
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~openai/gpt-astra-latest": {
-        "cache_creation_input_token_cost": 1.25e-05,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
-        "cache_read_input_token_cost": 1e-06,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
-        "input_cost_per_token": 1e-05,
-        "input_cost_per_token_above_272k_tokens": 2e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-05,
-        "output_cost_per_token_above_272k_tokens": 7.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-luna-latest": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-mini-latest": {
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-sol-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~openai/gpt-terra-latest": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_above_272k_tokens": 1.8e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~x-ai/grok-latest": {
-        "cache_read_input_token_cost": 4e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 8e-07,
-        "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_above_200k_tokens": 3.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "output_cost_per_token": 4.8e-06,
-        "output_cost_per_token_above_200k_tokens": 9.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/~z-ai/glm-flash-latest": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/~z-ai/glm-latest": {
-        "cache_read_input_token_cost": 1.2142e-07,
-        "input_cost_per_token": 6.538e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1310720,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2.0548e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-2.0": {
-        "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.0": {
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.0-mini": {
-        "cache_read_input_token_cost": 1.8e-07,
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.5": {
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-3.5-mini": {
-        "cache_read_input_token_cost": 1.8e-07,
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/aion-labs/aion-rp-llama-3.1-8b": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 1.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-2-lite-v1": {
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-lite-v1": {
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 300000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 2.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-micro-v1": {
-        "input_cost_per_token": 3.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-premier-v1": {
-        "cache_read_input_token_cost": 6.25e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/amazon/nova-pro-v1": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 300000,
-        "max_output_tokens": 5120,
-        "max_tokens": 5120,
-        "mode": "chat",
-        "output_cost_per_token": 3.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/anthracite-org/magnum-v4-72b": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/anthropic/claude-fable-5:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-fable-5.1:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 1e-05,
-        "cache_read_input_token_cost": 1.25e-07,
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-haiku-4.5:batch": {
-        "cache_creation_input_token_cost": 6.25e-07,
-        "cache_creation_input_token_cost_above_1hr": 1e-06,
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.1:batch": {
-        "cache_creation_input_token_cost": 9.375e-06,
-        "cache_creation_input_token_cost_above_1hr": 1.5e-05,
-        "cache_read_input_token_cost": 7.5e-07,
-        "input_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 32000,
-        "max_tokens": 32000,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.5:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.6:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.7:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-4.8:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-opus-5:batch": {
-        "cache_creation_input_token_cost": 3.125e-06,
-        "cache_creation_input_token_cost_above_1hr": 5e-06,
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.5:batch": {
-        "cache_creation_input_token_cost": 1.875e-06,
-        "cache_creation_input_token_cost_above_1hr": 3e-06,
-        "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 3e-07,
-        "input_cost_per_token": 1.5e-06,
-        "input_cost_per_token_above_200k_tokens": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "output_cost_per_token_above_200k_tokens": 1.125e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-4.6:batch": {
-        "cache_creation_input_token_cost": 1.875e-06,
-        "cache_creation_input_token_cost_above_1hr": 3e-06,
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/anthropic/claude-sonnet-5:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_1hr": 2e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/arcee-ai/trinity-large-thinking": {
-        "cache_read_input_token_cost": 6e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 80000,
-        "max_tokens": 80000,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/baidu/ernie-4.5-vl-424b-a47b": {
-        "deprecation_date": "2026-10-08",
-        "input_cost_per_token": 4.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 123000,
-        "max_output_tokens": 16000,
-        "max_tokens": 16000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-1.6": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_above_128k_tokens": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_128k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-1.6-flash": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 7.5e-08,
-        "input_cost_per_token_above_128k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "output_cost_per_token_above_128k_tokens": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2-1-turbo": {
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-code": {
-        "deprecation_date": "2026-11-11",
-        "input_cost_per_token": 5e-07,
-        "input_cost_per_token_above_128k_tokens": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "output_cost_per_token_above_128k_tokens": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-lite": {
-        "input_cost_per_token": 2.5e-07,
-        "input_cost_per_token_above_128k_tokens": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_128k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/bytedance-seed/seed-2.0-mini": {
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_128k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "output_cost_per_token_above_128k_tokens": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": {
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-a": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r-08-2024": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r-plus-08-2024": {
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/command-r7b-12-2024": {
-        "input_cost_per_token": 3.75e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4000,
-        "max_tokens": 4000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/cohere/north-mini-code:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/dots-studio/dots-3-note-preview:free": {
-        "deprecation_date": "2026-12-31",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 512000,
-        "max_output_tokens": 460800,
-        "max_tokens": 460800,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/google/gemini-2.5-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 3e-08,
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_audio_token": 1.5e-07,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-flash:batch": {
-        "cache_read_input_audio_token_cost": 1e-07,
-        "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-2.5-pro:batch": {
-        "cache_read_input_audio_token_cost": 1.25e-07,
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-20",
-        "input_cost_per_audio_token": 6.25e-07,
-        "input_cost_per_token": 6.25e-07,
-        "input_cost_per_token_above_200k_tokens": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_200k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3-flash-preview:batch": {
-        "input_cost_per_audio_token": 5e-07,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 2.5e-08,
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_audio_token": 2.5e-07,
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.1-pro-preview:batch": {
-        "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_200k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash-lite:batch": {
-        "cache_read_input_audio_token_cost": 1.5e-08,
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_audio_token": 1.5e-07,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.5-flash:batch": {
-        "cache_read_input_audio_token_cost": 1.5e-07,
-        "cache_read_input_token_cost": 7.5e-08,
-        "input_cost_per_audio_token": 1.5e-06,
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.6-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.7-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/google/gemini-3.8-flash:batch": {
-        "cache_creation_input_token_cost": 4.16666666666667e-08,
-        "cache_read_input_audio_token_cost": 3.75e-08,
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_audio_token": 3.75e-07,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.875e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true,
-        "supports_video_input": true
-    },
-    "openrouter/ibm-granite/granite-4.0-h-micro": {
-        "input_cost_per_token": 1.7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131000,
-        "max_output_tokens": 117900,
-        "max_tokens": 117900,
-        "mode": "chat",
-        "output_cost_per_token": 1.12e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/ibm-granite/granite-4.2-8b": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inception/mercury-2": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 50000,
-        "max_tokens": 50000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inception/mercury-2.5": {
-        "cache_read_input_token_cost": 4e-09,
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 260000,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash": {
-        "cache_read_input_token_cost": 4.2e-09,
-        "input_cost_per_token": 2.1e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 6.3e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-fin": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 1.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-fin:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-sante:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-vl": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/inclusionai/ling-3.0-flash-vl:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/inference-net/schematron-v2-small": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/inference-net/schematron-v2-turbo": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 3e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/kwaipilot/kat-coder-pro-v2.5": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 7.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.96e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/liquid/lfm-2.5-2.6b:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meituan/longcat-2.0": {
-        "cache_read_input_token_cost": 6e-09,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048756,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/meta/muse-glimmer-30b": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/meta/muse-spark-1.1": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.2": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.2-contributor": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.3": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 4.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/meta/muse-spark-1.3-contributor": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 943718,
-        "max_tokens": 943718,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/microsoft/phi-4": {
-        "input_cost_per_token": 7e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16384,
-        "max_output_tokens": 14745,
-        "max_tokens": 14745,
-        "mode": "chat",
-        "output_cost_per_token": 1.4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/microsoft/wizardlm-2-8x22b": {
-        "input_cost_per_token": 6.2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65535,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 6.2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/codestral-2508:batch": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 204800,
-        "max_tokens": 204800,
-        "mode": "chat",
-        "output_cost_per_token": 4.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/ministral-8b-2512:batch": {
-        "cache_read_input_token_cost": 7.5e-09,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-large-2512": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-large-2512:batch": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3-5:batch": {
-        "input_cost_per_token": 7.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 3.75e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-medium-3.1:batch": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 104857,
-        "max_tokens": 104857,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/mistralai/mistral-small-2603:batch": {
-        "cache_read_input_token_cost": 7.5e-09,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 209715,
-        "max_tokens": 209715,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/moonshotai/kimi-k3:batch": {
-        "cache_read_input_token_cost": 2.28e-07,
-        "input_cost_per_token": 2.28e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1.14e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/morph/morph-v3-fast": {
-        "input_cost_per_token": 8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 81920,
-        "max_output_tokens": 38000,
-        "max_tokens": 38000,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/morph/morph-v3-large": {
-        "input_cost_per_token": 9e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-mini:free": {
-        "deprecation_date": "2026-09-25",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-pro:free": {
-        "deprecation_date": "2026-09-25",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-3-llama-3.1-405b": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-3-llama-3.1-70b": {
-        "input_cost_per_token": 7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/nousresearch/hermes-4-405b": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo-0613": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 4095,
-        "max_output_tokens": 3685,
-        "max_tokens": 3685,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-3.5-turbo:batch": {
-        "input_cost_per_token": 2.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16385,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4-turbo:batch": {
-        "input_cost_per_token": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-mini:batch": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1-nano:batch": {
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4.1:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1047576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o-mini:batch": {
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-4o:batch": {
-        "cache_read_input_token_cost": 6.25e-07,
-        "input_cost_per_token": 1.25e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-image": {
-        "cache_read_input_token_cost": 1.25e-06,
-        "input_cost_per_token": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-image-mini": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-mini:batch": {
-        "cache_read_input_token_cost": 1.25e-08,
-        "input_cost_per_token": 1.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-nano:batch": {
-        "cache_read_input_token_cost": 2.5e-09,
-        "input_cost_per_token": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5-pro:batch": {
-        "input_cost_per_token": 7.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5:batch": {
-        "cache_read_input_token_cost": 6.25e-08,
-        "input_cost_per_token": 6.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.1:batch": {
-        "cache_read_input_token_cost": 6.25e-08,
-        "input_cost_per_token": 6.25e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2-pro:batch": {
-        "input_cost_per_token": 1.05e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 8.4e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.2:batch": {
-        "cache_read_input_token_cost": 8.75e-08,
-        "input_cost_per_token": 8.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-image-2": {
-        "cache_read_input_token_cost": 2e-06,
-        "input_cost_per_token": 8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-mini:batch": {
-        "cache_read_input_token_cost": 3.75e-08,
-        "input_cost_per_token": 3.75e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-nano:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6.25e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4-pro:batch": {
-        "input_cost_per_token": 1.5e-05,
-        "input_cost_per_token_above_272k_tokens": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 9e-05,
-        "output_cost_per_token_above_272k_tokens": 0.000135,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.4:batch": {
-        "cache_read_input_token_cost": 1.25e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.5e-07,
-        "input_cost_per_token": 1.25e-06,
-        "input_cost_per_token_above_272k_tokens": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "output_cost_per_token_above_272k_tokens": 1.125e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5-pro:batch": {
-        "input_cost_per_token": 1.5e-05,
-        "input_cost_per_token_above_272k_tokens": 3e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 9e-05,
-        "output_cost_per_token_above_272k_tokens": 0.000135,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.5:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna-pro:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_token_above_272k_tokens": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-luna:batch": {
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_token_above_272k_tokens": 9e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol-pro:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-sol:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra-pro:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-5.6-terra:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra-pro:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "output_cost_per_token_above_272k_tokens": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-astra:batch": {
-        "cache_creation_input_token_cost": 6.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-05,
-        "output_cost_per_token_above_272k_tokens": 3.75e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna-pro": {
-        "cache_creation_input_token_cost": 1.25e-07,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
-        "cache_read_input_token_cost": 1e-08,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
-        "input_cost_per_token": 1e-07,
-        "input_cost_per_token_above_272k_tokens": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "output_cost_per_token_above_272k_tokens": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol-pro": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
-        "cache_read_input_token_cost": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
-        "input_cost_per_token": 2e-06,
-        "input_cost_per_token_above_272k_tokens": 4e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3-mini:batch": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o3:batch": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/o4-mini:batch": {
-        "cache_read_input_token_cost": 1.375e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 100000,
-        "max_tokens": 100000,
-        "mode": "chat",
-        "output_cost_per_token": 2.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perceptron/perceptron-mk1": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/perplexity/sonar": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 127072,
-        "max_output_tokens": 114364,
-        "max_tokens": 114364,
-        "mode": "chat",
-        "output_cost_per_token": 1e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-deep-research": {
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-pro": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-pro-search": {
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 200000,
-        "max_output_tokens": 8000,
-        "max_tokens": 8000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/perplexity/sonar-reasoning-pro": {
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 115200,
-        "max_tokens": 115200,
-        "mode": "chat",
-        "output_cost_per_token": 8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/qwen/qwen3.8-27b:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/rekaai/reka-edge": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 16384,
-        "max_output_tokens": 14745,
-        "max_tokens": 14745,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/rekaai/reka-flash-3": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 65536,
-        "max_output_tokens": 58982,
-        "max_tokens": 58982,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/relace/relace-apply-3": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/relace/relace-search": {
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 256000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sakana/fugu-max": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/fugu-ultra": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/fugu-ultra-v2": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-06,
-        "input_cost_per_token": 5e-06,
-        "input_cost_per_token_above_272k_tokens": 1e-05,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 3e-05,
-        "output_cost_per_token_above_272k_tokens": 4.5e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sakana/sakana-namazu": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 9.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/sao10k/l3-lunaris-8b": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 7372,
-        "max_tokens": 7372,
-        "mode": "chat",
-        "output_cost_per_token": 5e-08,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sao10k/l3.1-euryale-70b": {
-        "input_cost_per_token": 8.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 8.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/sao10k/l3.3-euryale-70b": {
-        "input_cost_per_token": 6.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/stealth/space-bunny-alpha": {
-        "deprecation_date": "2098-12-31",
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_tool_choice": true,
-        "supports_video_input": true,
         "supports_vision": true
     },
-    "openrouter/stepfun/step-3.5-flash": {
-        "input_cost_per_token": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 65536,
-        "max_tokens": 65536,
-        "mode": "chat",
-        "output_cost_per_token": 3e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/stepfun/step-3.7-flash": {
-        "cache_read_input_token_cost": 4e-08,
-        "input_cost_per_token": 2e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 230400,
-        "max_tokens": 230400,
-        "mode": "chat",
-        "output_cost_per_token": 1.15e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hunyuan-a13b-instruct": {
-        "input_cost_per_token": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 5.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-1.8b": {
-        "input_cost_per_token": 4.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 1.77e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-30b-a3b": {
-        "input_cost_per_token": 7.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.95e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy-mt2-7b": {
-        "input_cost_per_token": 7.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 8192,
-        "max_output_tokens": 4096,
-        "max_tokens": 4096,
-        "mode": "chat",
-        "output_cost_per_token": 2.95e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy3": {
-        "cache_read_input_token_cost": 3.3e-08,
-        "input_cost_per_token": 1.32e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8},
-        "output_cost_per_token": 5.28e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy3-preview": {
-        "cache_read_input_token_cost": 6e-08,
-        "input_cost_per_token": 1.8e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/tencent/hy4-preview": {
-        "cache_read_input_token_cost": 4.2e-08,
-        "input_cost_per_token": 8.34e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 2.501e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/cydonia-24b-v4.1": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/skyfall-36b-v2": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 5.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 32768,
-        "max_output_tokens": 29491,
-        "max_tokens": 29491,
-        "mode": "chat",
-        "output_cost_per_token": 8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thedrummer/unslopnemo-12b": {
-        "input_cost_per_token": 4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1024000,
-        "max_output_tokens": 819200,
-        "max_tokens": 819200,
-        "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling": {
-        "cache_read_input_token_cost": 1.7e-07,
-        "input_cost_per_token": 1e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 471859,
-        "max_tokens": 471859,
-        "mode": "chat",
-        "output_cost_per_token": 4.05e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling-small": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling-small:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/thinkingmachines/inkling:free": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 262144,
-        "max_tokens": 262144,
-        "mode": "chat",
-        "output_cost_per_token": 0.0,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/unbiased/pareto": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-pro-3": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-pro4": {
-        "cache_read_input_token_cost": 1.8e-08,
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 524288,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.6e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/upstage/solar-mini4": {
-        "cache_read_input_token_cost": 5e-09,
-        "input_cost_per_token": 5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 524288,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/writer/palmyra-x5": {
-        "input_cost_per_token": 6e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1040000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": false,
-        "supports_response_schema": false,
-        "supports_tool_choice": false,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4.3:batch": {
-        "cache_read_input_token_cost": 1.6e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 3.2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_200k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 900000,
-        "max_tokens": 900000,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "output_cost_per_token_above_200k_tokens": 4e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/z-ai/glm-5.3-flash:batch": {
-        "cache_read_input_token_cost": 1.2e-08,
-        "input_cost_per_token": 6e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3:batch": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 4.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 2e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/prism-ml/ternary-bonsai-2-27b": {
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-prime": {
-        "cache_read_input_token_cost": 5.6e-07,
-        "input_cost_per_token": 2.8e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 8.8e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/z-ai/glm-5.3-flashx": {
-        "cache_read_input_token_cost": 9e-08,
-        "deprecation_date": "2098-12-31",
-        "input_cost_per_token": 3.7e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/x-ai/grok-4.7": {
-        "cache_read_input_token_cost": 4e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 8e-07,
-        "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_above_200k_tokens": 3.2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 500000,
-        "max_output_tokens": 450000,
-        "max_tokens": 450000,
-        "mode": "chat",
-        "output_cost_per_token": 4.8e-06,
-        "output_cost_per_token_above_200k_tokens": 9.6e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
     "moonshotai.kimi-k3": {
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "global.moonshotai.kimi-k3": {
-        "cache_creation_input_token_cost": 3.75e-06,
-        "cache_read_input_token_cost": 3e-07,
-        "input_cost_per_token": 3e-06,
-        "litellm_provider": "bedrock_converse",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "us.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
         "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
         "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
         "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
         "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
         "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.65e-05,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
         "supports_audio_input": false,
         "supports_function_calling": true,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
+        "supports_vision": true
+    },
+    "global.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_flex": 1.875e-06,
+        "cache_creation_input_token_cost_priority": 6.5625e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_flex": 1.5e-07,
+        "cache_read_input_token_cost_priority": 5.25e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_flex": 1.5e-06,
+        "input_cost_per_token_priority": 5.25e-06,
+        "litellm_provider": "bedrock_converse",
         "token_count_framing": 64,
-        "token_count_tokenizer": "kimi_k3"
-    },
-    "openrouter/xiaomi/mimo-v2.6-flash": {
-        "cache_read_input_token_cost": 2.8e-09,
-        "input_cost_per_token": 1.4e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 2.8e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_flex": 7.5e-06,
+        "output_cost_per_token_priority": 2.625e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
         "supports_function_calling": true,
-        "supports_pdf_input": false,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
+        "supports_vision": true
     },
-    "openrouter/xiaomi/mimo-v2.6-pro": {
-        "cache_read_input_token_cost": 3.6e-09,
-        "input_cost_per_token": 4.35e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
+    "us.moonshotai.kimi-k3": {
+        "supports_regex_lookaround": false,
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 8.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
+        "output_cost_per_token": 1.65e-05,
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
         "supports_function_calling": true,
-        "supports_pdf_input": false,
+        "supports_prompt_cache_breakpoint": false,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": {
-        "cache_read_input_token_cost": 3.6e-08,
-        "input_cost_per_token": 4.35e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 8.7e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
+        "supports_vision": true
     },
     "xiaomi_mimo/mimo-v2.6-pro": {
         "cache_read_input_token_cost": 3.6e-09,
@@ -75857,13 +72451,16 @@
     },
     "xai/grok-4.20-0309": {
         "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1.6e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 2e-06,
         "source": "https://api.x.ai/v1/language-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -75871,8 +72468,11 @@
         "supports_vision": true,
         "supports_web_search": true,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "input_cost_per_token_above_200k_tokens_batches": 2e-06,
         "output_cost_per_token_above_200k_tokens": 5e-06,
+        "output_cost_per_token_above_200k_tokens_batches": 4e-06,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07,
         "input_cost_per_image_token": 1.25e-06,
         "supports_prompt_caching": true,
         "supports_response_schema": true
@@ -76277,53 +72877,13 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true
     },
-    "openrouter/nex-agi/nex-n2.5-mini": {
-        "cache_read_input_token_cost": 2.5e-09,
-        "input_cost_per_token": 2.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 1e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": false,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/nex-agi/nex-n2.5-pro": {
-        "cache_read_input_token_cost": 1.5e-08,
-        "input_cost_per_token": 7.5e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 262144,
-        "max_output_tokens": 235929,
-        "max_tokens": 235929,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
     "baseten/deepseek-ai/DeepSeek-V4.1-Flash": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "baseten",
         "max_input_tokens": 1048576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://inference.baseten.co/v1/models",
@@ -76335,6 +72895,7 @@
         "supports_vision": true
     },
     "baseten/moonshotai/Kimi-K2.6": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.6e-07,
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
@@ -76352,6 +72913,7 @@
         "supports_vision": true
     },
     "baseten/moonshotai/Kimi-K2.7-Code": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.6e-07,
         "input_cost_per_token": 9.5e-07,
         "litellm_provider": "baseten",
@@ -76403,6 +72965,7 @@
         "supports_vision": false
     },
     "baseten/thinkingmachines/inkling": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.7e-07,
         "input_cost_per_token": 1e-06,
         "litellm_provider": "baseten",
@@ -76420,6 +72983,7 @@
         "supports_vision": true
     },
     "baseten/thinkingmachines/inkling-small": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "baseten",
@@ -76488,6 +73052,7 @@
         "supports_vision": false
     },
     "baseten/deepseek-ai/DeepSeek-V4-Pro": {
+        "deprecation_date": "2026-10-16",
         "cache_read_input_token_cost": 1.45e-07,
         "input_cost_per_token": 1.74e-06,
         "litellm_provider": "baseten",
@@ -76636,13 +73201,25 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "fireworks_ai/accounts/fireworks/routers/rune": {
+        "cache_read_input_token_cost": 8.4e-09,
+        "input_cost_per_token": 4.2e-08,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 262144,
+        "mode": "evaluation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.fireworks.ai"
+    },
     "fireworks_ai/accounts/fireworks/models/ember-1": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -76650,224 +73227,6 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
-    "openrouter/anthropic/claude-opus-5.5:batch": {
-        "cache_creation_input_token_cost": 2.5e-06,
-        "cache_creation_input_token_cost_above_1hr": 4e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 1e-05,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/cohere/command-a-plus": {
-        "cache_read_input_token_cost": 1.5e-07,
-        "input_cost_per_token": 3e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 192000,
-        "max_output_tokens": 64000,
-        "max_tokens": 64000,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": false,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/deepseek/deepseek-v4.1-flash:batch": {
-        "cache_read_input_token_cost": 3.36e-09,
-        "input_cost_per_token": 1.12e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 3.36e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/openai/gpt-6-luna-pro:batch": {
-        "cache_creation_input_token_cost": 6.25e-08,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07,
-        "cache_read_input_token_cost": 5e-09,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-08,
-        "input_cost_per_token": 5e-08,
-        "input_cost_per_token_above_272k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "output_cost_per_token_above_272k_tokens": 3.75e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-luna:batch": {
-        "cache_creation_input_token_cost": 6.25e-08,
-        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07,
-        "cache_read_input_token_cost": 5e-09,
-        "cache_read_input_token_cost_above_272k_tokens": 1e-08,
-        "input_cost_per_token": 5e-08,
-        "input_cost_per_token_above_272k_tokens": 1e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 2.5e-07,
-        "output_cost_per_token_above_272k_tokens": 3.75e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol-pro:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-6-sol:batch": {
-        "cache_creation_input_token_cost": 1.25e-06,
-        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1050000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
-        "mode": "chat",
-        "output_cost_per_token": 5e-06,
-        "output_cost_per_token_above_272k_tokens": 7.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": true
-    },
-    "openrouter/openai/gpt-oss-20b:batch": {
-        "input_cost_per_token": 2.4e-08,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 117964,
-        "max_tokens": 117964,
-        "mode": "chat",
-        "output_cost_per_token": 1.12e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": false,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": false,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": false,
-        "supports_web_search": false
-    },
-    "openrouter/qwen/qwen3.8-omni-flash": {
-        "cache_read_input_token_cost": 1.6e-08,
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 1000000,
-        "max_output_tokens": 131072,
-        "max_tokens": 131072,
-        "mode": "chat",
-        "output_cost_per_token": 4.7e-07,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_pdf_input": false,
-        "supports_prompt_caching": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_vision": true,
-        "supports_web_search": false
-    },
-    "openrouter/perceptron/perceptron-mk1.5": {
-        "input_cost_per_token": 1.5e-07,
-        "litellm_provider": "openrouter",
-        "max_input_tokens": 36864,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
-        "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
-        "source": "https://openrouter.ai/api/v1/models",
-        "supports_audio_input": true,
-        "supports_function_calling": true,
-        "supports_reasoning": true,
-        "supports_response_schema": true,
-        "supports_tool_choice": true,
-        "supports_video_input": true,
-        "supports_vision": true
-    },
     "vertex_ai/gemini-2.0-flash": {
         "deprecation_date": "2026-06-01",
         "input_cost_per_audio_token": 1e-06,
@@ -77142,7 +73501,12 @@
         "cache_read_input_token_cost": 1.1e-06,
         "output_cost_per_token": 5.5e-05,
         "cache_creation_input_token_cost_above_1hr": 2.2e-05,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-mythos-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        }
     },
     "apac.anthropic.claude-fable-5": {
         "litellm_provider": "bedrock_converse",
@@ -77164,7 +73528,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77197,7 +73561,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
-        "supports_native_structured_output": true,
+        "supports_native_structured_output": false,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77241,7 +73605,12 @@
         "input_cost_per_token": 5.5e-06,
         "cache_creation_input_token_cost_above_1hr": 1.1e-05,
         "cache_read_input_token_cost": 5.5e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-7",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "apac.anthropic.claude-opus-4-8": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77265,6 +73634,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77275,7 +73645,12 @@
         "output_cost_per_token": 2.75e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_creation_input_token_cost": 6.875e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-4-8",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-northeast-1"
+        }
     },
     "apac.anthropic.claude-opus-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77308,7 +73683,12 @@
         "input_cost_per_token": 5.5e-06,
         "cache_read_input_token_cost": 5.5e-07,
         "output_cost_per_token": 2.75e-05,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "apac.anthropic.claude-opus-5-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77343,7 +73723,12 @@
         "input_cost_per_token": 4.4e-06,
         "output_cost_per_token": 2.2e-05,
         "cache_read_input_token_cost": 2.2e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "apac.anthropic.claude-sonnet-4-6": {
         "supports_adaptive_thinking": true,
@@ -77354,7 +73739,7 @@
         "max_output_tokens": 64000,
         "max_tokens": 64000,
         "mode": "chat",
-        "supports_assistant_prefill": true,
+        "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
@@ -77373,7 +73758,11 @@
         "cache_read_input_token_cost": 3.3e-07,
         "cache_creation_input_token_cost": 4.125e-06,
         "input_cost_per_token": 3.3e-06,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-4-6",
+            "litellm_provider": "bedrock"
+        }
     },
     "apac.anthropic.claude-sonnet-5": {
         "bedrock_converse_supports_strict_tools": false,
@@ -77397,6 +73786,7 @@
         "supports_vision": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
         "supports_max_reasoning_effort": true,
         "supports_output_config": true,
         "bedrock_output_config_effort_ceiling": "xhigh",
@@ -77407,7 +73797,12 @@
         "input_cost_per_token": 2.2e-06,
         "output_cost_per_token": 1.1e-05,
         "cache_read_input_token_cost": 2.2e-07,
-        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        }
     },
     "us.anthropic.claude-mythos-preview": {
         "litellm_provider": "bedrock_converse",
@@ -77470,6 +73865,7 @@
         "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
     "deepseek.r1-v1:0": {
+        "deprecation_date": "2027-03-30",
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
@@ -77477,7 +73873,7 @@
         "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
-        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
         "supports_function_calling": false,
         "supports_reasoning": true,
         "supports_tool_choice": false
@@ -77494,61 +73890,3103 @@
         "supports_function_calling": true,
         "supports_tool_choice": false
     },
-    "cloudflare/clef": {
-        "input_cost_per_token": 2.4e-07,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/MAI-Cyber-1-Flash": {
+        "cache_read_input_token_cost": 6e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
     },
-    "cloudflare/clef-flash": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/mistral-ocr-2505": {
+        "litellm_provider": "azure_ai",
+        "mode": "ocr",
+        "ocr_cost_per_page": 0.001,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/"
     },
-    "cloudflare/@cf/cloudflare/clef": {
-        "input_cost_per_token": 2.4e-07,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "azure_ai/mistral-ocr-2512": {
+        "litellm_provider": "azure_ai",
+        "mode": "ocr",
+        "ocr_cost_per_page": 0.002,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/"
     },
-    "cloudflare/@cf/cloudflare/clef-flash": {
-        "input_cost_per_token": 9e-08,
-        "litellm_provider": "cloudflare",
-        "max_input_tokens": 65536,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/"
+    "anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
-    "perplexity/pplx-decider-v1-27b": {
-        "input_cost_per_token": 4e-08,
-        "litellm_provider": "perplexity",
-        "max_input_tokens": 262144,
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://docs.perplexity.ai/api-reference/decisions-post"
+    "apac.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "input_cost_per_token": 2.2e-06,
+        "output_cost_per_token": 1.1e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
     },
-    "strands_decider/strands-decider-2B-hobson-v19": {
-        "input_cost_per_token": 0.0,
-        "litellm_provider": "strands_decider",
-        "mode": "evaluation",
-        "output_cost_per_token": 0.0,
-        "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19",
-        "metadata": {
-            "notes": "Self-hosted decision model; infrastructure costs are paid separately"
+    "au.anthropic.claude-sonnet-5-5": {
+        "token_count_model": {
+            "model": "au.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        },
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "azure_ai/claude-sonnet-5-5": {
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-09-29",
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
+    },
+    "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
         }
     },
+    "eu.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "global.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "jp.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "perplexity/anthropic/claude-sonnet-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_adaptive_thinking": true,
+        "supports_web_search": true,
+        "supports_function_calling": true,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/anthropic/claude-fable-5-1": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-05,
+        "output_cost_per_token": 5e-05,
+        "cache_read_input_token_cost": 2.5e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/anthropic/claude-opus-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 4e-06,
+        "output_cost_per_token": 2e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6.1-sol": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-sol": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-astra": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-05,
+        "output_cost_per_token": 5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_creation_input_token_cost": 1.25e-05,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/openai/gpt-6-luna": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token_above_272k_tokens": 2e-07,
+        "output_cost_per_token_above_272k_tokens": 7.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/google/gemini-3.8-flash": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_sampling_params": false,
+        "input_cost_per_token": 7.5e-07,
+        "output_cost_per_token": 3.75e-06,
+        "cache_read_input_token_cost": 7.5e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "perplexity/xai/grok-4.7": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 6e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "us-gov.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 3e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.8e-06,
+        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 2.4e-06,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-sonnet-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "us.anthropic.claude-sonnet-5-5": {
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 4.4e-06,
+        "cache_read_input_token_cost": 1.1e-07,
+        "input_cost_per_token": 2.2e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "us.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "vertex_ai/claude-sonnet-5-5": {
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/claude-sonnet-5-5@default": {
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_1hr": 4e-06,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": false,
+        "thinking_always_on": true,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "prism/deepseek-v4.1-flash": {
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token": 1.7e-07,
+        "litellm_provider": "prism",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "output_cost_per_token": 6.3e-07,
+        "source": "https://prisminference.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "prism/deepseek-v4-flash": {
+        "cache_read_input_token_cost": 7e-08,
+        "input_cost_per_token": 1.7e-07,
+        "litellm_provider": "prism",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 384000,
+        "max_tokens": 384000,
+        "mode": "chat",
+        "output_cost_per_token": 2.1e-07,
+        "source": "https://prisminference.com/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses",
+            "/v1/messages"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "global.xai.grok-4.7": {
+        "supports_regex_lookaround": false,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_flex": 2.5e-07,
+        "cache_read_input_token_cost_priority": 8.75e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.5e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_flex": 3e-06,
+        "output_cost_per_token_priority": 1.05e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html",
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "us.xai.grok-4.7": {
+        "supports_regex_lookaround": false,
+        "supported_endpoints": ["/v1/chat/completions"],
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_flex": 2.75e-07,
+        "cache_read_input_token_cost_priority": 9.625e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_flex": 1.1e-06,
+        "input_cost_per_token_priority": 3.85e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "output_cost_per_token_flex": 3.3e-06,
+        "output_cost_per_token_priority": 1.155e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html",
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
+        "cache_read_input_token_cost": 1.4e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_creation_input_token_cost_flex": 1.25e-06,
+        "cache_creation_input_token_cost_priority": 5e-06,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 2e-07,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_flex": 2e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 4e-06,
+        "input_cost_per_token_ultrafast": 1.2e-05,
+        "litellm_provider": "openai",
+        "max_input_tokens": 922000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_flex": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 2e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
+        "regional_processing_uplift_multiplier_eu": 1.1,
+        "regional_processing_uplift_multiplier_us": 1.1,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_none_reasoning_effort": false,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_tool_search": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "global.openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_ultrafast": 1.2e-05,
+        "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_sampling_params": false,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock_mantle/openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "responses",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_prompt_cache_breakpoint": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "use_openai_responses_path": true
+    },
+    "us.openai.gpt-6.1-sol": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
+        "cache_read_input_token_cost": 1.1e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
+        "litellm_provider": "bedrock_converse",
+        "supports_bedrock_converse_tool_result_images": false,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_bedrock_runtime_chat_completions_response_format": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_none_reasoning_effort": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_sampling_params": false,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "vertex_ai/gemini-3.8-flash-tts": {
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 9e-06,
+        "output_cost_per_token": 9e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ]
+    },
+    "vertex_ai/gemini-3.8-flash-lite-tts": {
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 6e-06,
+        "output_cost_per_token": 6e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ]
+    },
+    "vertex_ai/xai/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure_ai/kimi-k2-thinking": {
+        "deprecation_date": "2026-03-29",
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_video_input": false,
+        "supports_vision": false
+    },
+    "global.zai.glm-5.3": {
+        "cache_creation_input_token_cost": 2.1e-06,
+        "cache_creation_input_token_cost_batches": 1.05e-06,
+        "cache_creation_input_token_cost_flex": 1.05e-06,
+        "cache_creation_input_token_cost_priority": 3.675e-06,
+        "cache_read_input_token_cost": 3.12e-07,
+        "cache_read_input_token_cost_batches": 1.56e-07,
+        "cache_read_input_token_cost_flex": 1.56e-07,
+        "cache_read_input_token_cost_priority": 5.46e-07,
+        "input_cost_per_token": 1.68e-06,
+        "input_cost_per_token_batches": 8.4e-07,
+        "input_cost_per_token_flex": 8.4e-07,
+        "input_cost_per_token_priority": 2.94e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.28e-06,
+        "output_cost_per_token_batches": 2.64e-06,
+        "output_cost_per_token_flex": 2.64e-06,
+        "output_cost_per_token_priority": 9.24e-06,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "us.zai.glm-5.3": {
+        "cache_creation_input_token_cost": 2.31e-06,
+        "cache_creation_input_token_cost_batches": 1.155e-06,
+        "cache_creation_input_token_cost_flex": 1.155e-06,
+        "cache_creation_input_token_cost_priority": 4.0425e-06,
+        "cache_read_input_token_cost": 3.432e-07,
+        "cache_read_input_token_cost_batches": 1.716e-07,
+        "cache_read_input_token_cost_flex": 1.716e-07,
+        "cache_read_input_token_cost_priority": 6.006e-07,
+        "input_cost_per_token": 1.848e-06,
+        "input_cost_per_token_batches": 9.24e-07,
+        "input_cost_per_token_flex": 9.24e-07,
+        "input_cost_per_token_priority": 3.234e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.808e-06,
+        "output_cost_per_token_batches": 2.904e-06,
+        "output_cost_per_token_flex": 2.904e-06,
+        "output_cost_per_token_priority": 1.0164e-05,
+        "source": "https://aws.amazon.com/bedrock/pricing/",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "amazon.nova-2-5-sonic": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 3.3e-07,
+        "litellm_provider": "bedrock",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2.75e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
+    "azure/model-router": {
+        "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it",
+        "deprecation_date": "2027-05-20",
+        "input_cost_per_token": 1.4e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/",
+        "supports_vision": true
+    },
+    "azure/whisper": {
+        "deprecation_date": "2026-12-15",
+        "input_cost_per_second": 0.0001,
+        "litellm_provider": "azure",
+        "mode": "audio_transcription",
+        "output_cost_per_second": 0.0001,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
+    },
+    "gemini/gemini-nano-banana-2.1": {
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "rpm": 1000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 4000000.0,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini-nano-banana-2.1": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "cache_read_input_token_cost_batches": 7.5e-08,
+        "cache_read_input_token_cost_priority": 2.7e-07,
+        "input_cost_per_image": 0.00168,
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "input_cost_per_token_priority": 2.7e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "output_cost_per_token_priority": 1.35e-05,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-nano-banana-2.1": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "cache_read_input_token_cost_batches": 7.5e-08,
+        "cache_read_input_token_cost_priority": 2.7e-07,
+        "input_cost_per_image": 0.00168,
+        "input_cost_per_token": 1.5e-06,
+        "input_cost_per_token_batches": 7.5e-07,
+        "input_cost_per_token_priority": 2.7e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0336,
+        "output_cost_per_image_token": 3e-05,
+        "output_cost_per_token": 7.5e-06,
+        "output_cost_per_token_batches": 3.75e-06,
+        "output_cost_per_token_priority": 1.35e-05,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "azure_ai/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "deprecation_date": "2027-10-05",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://docs.x.ai/developers/models/grok-4.7",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "in.moonshotai.kimi-k3": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_creation_input_token_cost_flex": 2.0625e-06,
+        "cache_creation_input_token_cost_priority": 7.21875e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "cache_read_input_token_cost_flex": 1.65e-07,
+        "cache_read_input_token_cost_priority": 5.775e-07,
+        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token_flex": 1.65e-06,
+        "input_cost_per_token_priority": 5.775e-06,
+        "litellm_provider": "bedrock_converse",
+        "token_count_framing": 64,
+        "token_count_tokenizer": "kimi_k3",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "output_cost_per_token_flex": 8.25e-06,
+        "output_cost_per_token_priority": 2.8875e-05,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md",
+        "supports_audio_input": false,
+        "supports_function_calling": true,
+        "supports_prompt_cache_breakpoint": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_regex_lookaround": false,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+"claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens_batches": 2.5e-07,
+        "output_cost_per_token_above_100k_tokens_batches": 1.25e-06,
+        "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07,
+        "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08,
+        "supports_anthropic_compaction": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "provider_specific_entry": {
+            "us": 1.1
+        },
+        "supports_output_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview",
+        "supports_web_search": true,
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08
+    },
+    "bedrock_mantle/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
+    },
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock_mantle",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
+    },
+    "anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "apac.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "input_cost_per_token": 1.1e-07,
+        "output_cost_per_token": 5.5e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "au.anthropic.claude-haiku-5-5": {
+        "token_count_model": {
+            "model": "au.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "ap-southeast-4"
+        },
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "azure_ai/claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2027-09-29",
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide"
+    },
+    "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "eu.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "global.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_token": 1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "global.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "jp.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "perplexity/anthropic/claude-haiku-5-5": {
+        "litellm_provider": "perplexity",
+        "mode": "responses",
+        "supports_adaptive_thinking": true,
+        "supports_web_search": true,
+        "supports_function_calling": true,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "source": "https://docs.perplexity.ai/docs/agent-api/models"
+    },
+    "us-gov.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 6e-07,
+        "output_cost_per_token_above_100k_tokens": 3e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 6e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "cache_creation_input_token_cost": 1.5e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.4e-07,
+        "cache_read_input_token_cost": 1.2e-08,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock_converse",
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": false,
+        "supports_output_config": true,
+        "supports_parallel_tool_use_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "token_count_model": {
+            "model": "anthropic.claude-haiku-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-gov-west-1"
+        }
+    },
+    "us.anthropic.claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5.5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.75e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
+        "bedrock_converse_supports_strict_tools": false,
+        "cache_creation_input_token_cost": 1.375e-07,
+        "cache_creation_input_token_cost_above_1hr": 2.2e-07,
+        "cache_read_input_token_cost": 1.1e-08,
+        "input_cost_per_token": 1.1e-07,
+        "litellm_provider": "bedrock_converse",
+        "token_count_model": {
+            "model": "us.anthropic.claude-opus-5-5",
+            "litellm_provider": "bedrock_mantle",
+            "region": "us-east-1"
+        },
+        "supports_tool_search": true,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_mid_conversation_system": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_native_structured_output": false,
+        "supports_bedrock_native_structured_output": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "bedrock_output_config_effort_ceiling": "xhigh",
+        "supports_parallel_tool_use_config": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
+    },
+    "vertex_ai/claude-haiku-5-5": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
+    "vertex_ai/claude-haiku-5-5@default": {
+        "input_cost_per_token_above_100k_tokens": 5e-07,
+        "output_cost_per_token_above_100k_tokens": 2.5e-06,
+        "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
+        "cache_read_input_token_cost_above_100k_tokens": 5e-08,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "supports_mid_conversation_system": true,
+        "cache_creation_input_token_cost": 1.25e-07,
+        "cache_creation_input_token_cost_above_1hr": 2e-07,
+        "cache_creation_input_token_cost_batches": 6.25e-08,
+        "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_batches": 5e-09,
+        "input_cost_per_token": 1e-07,
+        "input_cost_per_token_batches": 5e-08,
+        "litellm_provider": "vertex_ai-anthropic_models",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_batches": 2.5e-07,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_max_reasoning_effort": true,
+        "supports_forced_tool_use": true,
+        "thinking_always_on": false,
+        "prompt_cache_min_tokens": 512,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
+    "microsoft_365_copilot/chat": {
+        "litellm_provider": "microsoft_365_copilot",
+        "mode": "chat",
+        "supports_mid_conversation_system": true,
+        "input_cost_per_token": 0.0,
+        "output_cost_per_token": 0.0
+    },
+    "us.twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
+    "global.twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
+    "twelvelabs.pegasus-1-5-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 261120,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-06,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
+        "supports_video_input": true
+    },
     "azure_ai/Microsoft-Decision-1": {
         "input_cost_per_token": 4.2e-08,
         "litellm_provider": "azure_ai",
         "mode": "evaluation",
         "output_cost_per_token": 0.0,
         "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'"
+    },
+    "gpt-rosalind-discovery": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "chatgpt/gpt-rosalind-discovery": {
+        "litellm_provider": "chatgpt",
+        "mode": "responses",
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/responses"
+        ]
+    },
+    "azure_ai/Cohere-Embed-V5-Fast": {
+        "deprecation_date": "2027-01-23",
+        "input_cost_per_image_token": 4e-07,
+        "input_cost_per_token": 8e-08,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048.0,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/embeddings"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_embedding_image_input": true
+    },
+    "azure_ai/Cohere-Embed-V5-Pro": {
+        "deprecation_date": "2027-01-23",
+        "input_cost_per_image_token": 4e-07,
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 2048.0,
+        "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
+        "supported_endpoints": [
+            "/v1/embeddings"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_embedding_image_input": true
+    },
+    "scaledown/extract": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_response_schema": false,
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/summarize": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/compress": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_function_calling": false,
+        "supports_vision": false
+    },
+    "scaledown/classify": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "scaledown/decisions": {
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "scaledown",
+        "mode": "chat",
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_function_calling": false
+    },
+    "vertex_ai/gemini-robotics-er-2-preview": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 5e-06,
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini-robotics-er-2-preview": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 5e-06,
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "gemini/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05,
+        "prompt_cache_min_tokens": 4096.0,
+        "rpm": 2000.0,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 800000.0,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "cache_read_input_token_cost_batches": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_audio_token_batches": 1e-06,
+        "input_cost_per_audio_token_priority": 3.6e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05,
+        "prompt_cache_min_tokens": 6144.0,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "vertex_ai/gemini-4-argon-cyber-permissive": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_audio_token": 4e-06,
+        "input_cost_per_audio_token_batches": 2e-06,
+        "input_cost_per_audio_token_priority": 7.2e-06,
+        "input_cost_per_token": 4e-06,
+        "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_flex": 2e-06,
+        "input_cost_per_token_priority": 7.2e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2e-05,
+        "output_cost_per_token": 2e-05,
+        "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_flex": 1e-05,
+        "output_cost_per_token_priority": 3.6e-05,
+        "prompt_cache_min_tokens": 6144.0,
+        "regional_endpoint_uplift_multiplier": 1.1,
+        "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_minimal_reasoning_effort": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "github_copilot/gemini-4-argon": {
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_vision": true
+    },
+    "openinfer/@oi/GLM-5.3-Flash": {
+        "max_tokens": 393216,
+        "max_input_tokens": 393216,
+        "max_output_tokens": 393216,
+        "input_cost_per_token": 1.95e-07,
+        "output_cost_per_token": 1.56e-06,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "openinfer/@oi/Qwen3.5-27B": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 1.95e-07,
+        "output_cost_per_token": 1.56e-06,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "openinfer/@oi/Qwen3.5-9B": {
+        "max_tokens": 100000,
+        "max_input_tokens": 100000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 5e-06,
+        "output_cost_per_token": 1.5e-07,
+        "litellm_provider": "openinfer",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "source": "https://api.openinfer.ai/v1/models"
+    },
+    "xai/grok-voice-3.0": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "xai/grok-voice-latest": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "xai/grok-voice-2.0": {
+        "input_cost_per_second": 0.001333333333333,
+        "input_cost_per_text_message": 0.004,
+        "litellm_provider": "xai",
+        "mode": "realtime",
+        "source": "https://docs.x.ai/developers/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true
+    },
+    "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "jp.amazon.nova-2-lite-v1:0": {
+        "cache_read_input_token_cost": 9.9e-08,
+        "cache_read_input_token_cost_flex": 4.95e-08,
+        "cache_read_input_token_cost_priority": 1.7325e-07,
+        "input_cost_per_token": 3.96e-07,
+        "input_cost_per_token_batches": 1.98e-07,
+        "input_cost_per_token_flex": 1.98e-07,
+        "input_cost_per_token_priority": 6.93e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 3.311e-06,
+        "output_cost_per_token_batches": 1.6555e-06,
+        "output_cost_per_token_flex": 1.6555e-06,
+        "output_cost_per_token_priority": 5.79425e-06,
+        "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json",
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "vertex_ai-deepseek_models",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_regions": [
+            "global"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure_ai/claude-opus-5-5-fast": {
+        "cache_creation_input_token_cost": 1e-05,
+        "cache_creation_input_token_cost_above_1hr": 1.6e-05,
+        "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-10-01",
+        "input_cost_per_token": 8e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 4e-05,
+        "prompt_cache_min_tokens": 512.0,
+        "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02},
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_forced_tool_use": false,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_mid_conversation_system": true,
+        "supports_native_structured_output": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true,
+        "thinking_always_on": true
+    },
+    "baseten/meta-models/muse-spark-open": {
+        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 4.25e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "wandb",
+        "max_input_tokens": 1049000,
+        "max_tokens": 943718,
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-07,
+        "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "together_ai/reflection/Beam-1.0-501B-A23B": {
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 4e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "baseten/reflection/Beam-1.0": {
+        "cache_read_input_token_cost": 1.3e-07,
+        "input_cost_per_token": 1.3e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 4.3e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "nebius/reflection/beam": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "nebius",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1e-06,
+        "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam",
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": {
+        "cache_read_input_token_cost": 1.4e-08,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2.4e-06,
+        "source": "https://inference.baseten.co/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": {
+        "cache_read_input_token_cost": 6e-09,
+        "cache_read_input_token_cost_priority": 7.5e-09,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 3.75e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "github_copilot/claude-sonnet-4.6": {
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2026-09-01",
+        "input_cost_per_token": 3e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/messages"
+        ],
+        "supports_adaptive_thinking": true,
+        "supports_function_calling": true,
+        "supports_legacy_thinking": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/gpt-5.4-nano": {
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.25e-06,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "deprecation_date": "2026-10-19",
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.6": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "github_copilot/grok-4.7": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "github_copilot",
+        "max_input_tokens": 500000,
+        "max_output_tokens": 500000,
+        "max_tokens": 500000,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "meta/muse-image-1.0": {
+        "litellm_provider": "meta",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.01,
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits",
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "image"
+        ]
+    },
+    "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": {
+        "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 2.25e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 2.25e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 1048576,
+        "max_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_priority": 9e-07,
+        "source": "https://platform.minimax.io/docs/guides/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "meta/sam-3.1": {
+        "input_cost_per_image": 0.0025,
+        "litellm_provider": "meta",
+        "mode": "responses",
+        "source": "https://dev.meta.ai/docs/pricing-rate-limits.md",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ]
+    },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": {
+        "cache_read_input_token_cost": 9e-09,
+        "cache_read_input_token_cost_priority": 1.125e-08,
+        "input_cost_per_token": 4.5e-07,
+        "input_cost_per_token_priority": 5.625e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-06,
+        "output_cost_per_token_priority": 2.25e-06,
+        "source": "https://docs.fireworks.ai/serverless/us-only-serverless",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
     }
 }
diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json
index 7048dfa9dcb..d4dfeb25429 100644
--- a/model_prices_and_context_window.schema.json
+++ b/model_prices_and_context_window.schema.json
@@ -83,7 +83,12 @@
           "minimum": 0,
           "description": "USD per token written to the provider's prompt cache."
         },
-        "cache_creation_input_token_cost_above_128k_tokens": {
+        "cache_creation_input_token_cost_above_100k_tokens": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
+        "cache_creation_input_token_cost_above_100k_tokens_batches": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -93,6 +98,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_creation_input_token_cost_above_1hr_above_100k_tokens": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -103,11 +113,6 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
-        "cache_creation_input_token_cost_above_256k_tokens": {
-          "type": "number",
-          "minimum": 0,
-          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
-        },
         "cache_creation_input_token_cost_above_272k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -118,6 +123,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_creation_input_token_cost_above_272k_tokens_decisions": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_creation_input_token_cost_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -128,7 +138,7 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "cache_creation_input_token_cost_above_32k_tokens": {
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -137,6 +147,10 @@
           "type": "number",
           "minimum": 0
         },
+        "cache_creation_input_token_cost_decisions": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_creation_input_token_cost_flex": {
           "type": "number",
           "minimum": 0,
@@ -147,6 +161,10 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
+        "cache_creation_input_token_cost_ultrafast": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_read_input_audio_token_cost": {
           "type": "number",
           "minimum": 0
@@ -160,7 +178,12 @@
           "minimum": 0,
           "description": "USD per prompt token served from the provider's prompt cache."
         },
-        "cache_read_input_token_cost_above_128k_tokens": {
+        "cache_read_input_token_cost_above_100k_tokens": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
+        "cache_read_input_token_cost_above_100k_tokens_batches": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -170,16 +193,16 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_read_input_token_cost_above_200k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_read_input_token_cost_above_200k_tokens_priority": {
           "type": "number",
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "cache_read_input_token_cost_above_256k_tokens": {
-          "type": "number",
-          "minimum": 0,
-          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
-        },
         "cache_read_input_token_cost_above_272k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -190,6 +213,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_read_input_token_cost_above_272k_tokens_decisions": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_read_input_token_cost_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -200,7 +228,7 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "cache_read_input_token_cost_above_32k_tokens": {
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -210,10 +238,18 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_read_input_token_cost_balanced": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_read_input_token_cost_batches": {
           "type": "number",
           "minimum": 0
         },
+        "cache_read_input_token_cost_decisions": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_read_input_token_cost_flex": {
           "type": "number",
           "minimum": 0,
@@ -224,6 +260,10 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
+        "cache_read_input_token_cost_ultrafast": {
+          "type": "number",
+          "minimum": 0
+        },
         "citation_cost_per_token": {
           "type": "number",
           "minimum": 0
@@ -235,6 +275,10 @@
         "comment": {
           "type": "string"
         },
+        "cost_per_second": {
+          "type": "number",
+          "minimum": 0
+        },
         "default_reasoning_effort": {
           "type": "string",
           "description": "Reasoning effort the provider applies when the request omits reasoning_effort. Gates whether a non-default temperature or the top_p/logprobs sampling params are accepted, which hold only when the effort resolves to 'none'.",
@@ -253,6 +297,10 @@
           "format": "date",
           "pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$"
         },
+        "explicit_cache_read_input_token_cost": {
+          "type": "number",
+          "minimum": 0
+        },
         "gemini_audio_only_live": {
           "type": "boolean"
         },
@@ -336,11 +384,25 @@
           "type": "number",
           "minimum": 0
         },
+        "input_cost_per_text_message": {
+          "type": "number",
+          "minimum": 0
+        },
         "input_cost_per_token": {
           "type": "number",
           "minimum": 0,
           "description": "USD per prompt token."
         },
+        "input_cost_per_token_above_100k_tokens": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
+        "input_cost_per_token_above_100k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "input_cost_per_token_above_128k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -351,16 +413,16 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "input_cost_per_token_above_200k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "input_cost_per_token_above_200k_tokens_priority": {
           "type": "number",
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "input_cost_per_token_above_256k_tokens": {
-          "type": "number",
-          "minimum": 0,
-          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
-        },
         "input_cost_per_token_above_272k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -371,6 +433,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "input_cost_per_token_above_272k_tokens_decisions": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "input_cost_per_token_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -381,7 +448,7 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "input_cost_per_token_above_32k_tokens": {
+        "input_cost_per_token_above_272k_tokens_ultrafast": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -391,6 +458,10 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "input_cost_per_token_balanced": {
+          "type": "number",
+          "minimum": 0
+        },
         "input_cost_per_token_batches": {
           "type": "number",
           "minimum": 0,
@@ -400,6 +471,10 @@
           "type": "number",
           "minimum": 0
         },
+        "input_cost_per_token_decisions": {
+          "type": "number",
+          "minimum": 0
+        },
         "input_cost_per_token_flex": {
           "type": "number",
           "minimum": 0,
@@ -410,6 +485,10 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
+        "input_cost_per_token_ultrafast": {
+          "type": "number",
+          "minimum": 0
+        },
         "input_cost_per_video_per_second": {
           "type": "number",
           "minimum": 0
@@ -474,6 +553,7 @@
             "completion",
             "embedding",
             "evaluation",
+            "extraction",
             "guardrail",
             "image_edit",
             "image_generation",
@@ -656,6 +736,10 @@
           "type": "number",
           "minimum": 0
         },
+        "output_cost_per_image_token_batches": {
+          "type": "number",
+          "minimum": 0
+        },
         "output_cost_per_pixel": {
           "type": "number",
           "minimum": 0
@@ -698,6 +782,16 @@
           "minimum": 0,
           "description": "USD per generated token."
         },
+        "output_cost_per_token_above_100k_tokens": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
+        "output_cost_per_token_above_100k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "output_cost_per_token_above_128k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -708,16 +802,16 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "output_cost_per_token_above_200k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "output_cost_per_token_above_200k_tokens_priority": {
           "type": "number",
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "output_cost_per_token_above_256k_tokens": {
-          "type": "number",
-          "minimum": 0,
-          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
-        },
         "output_cost_per_token_above_272k_tokens": {
           "type": "number",
           "minimum": 0,
@@ -728,6 +822,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "output_cost_per_token_above_272k_tokens_decisions": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "output_cost_per_token_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -738,7 +837,7 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
-        "output_cost_per_token_above_32k_tokens": {
+        "output_cost_per_token_above_272k_tokens_ultrafast": {
           "type": "number",
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -748,11 +847,19 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "output_cost_per_token_balanced": {
+          "type": "number",
+          "minimum": 0
+        },
         "output_cost_per_token_batches": {
           "type": "number",
           "minimum": 0,
           "description": "USD per generated token via the provider's batch API."
         },
+        "output_cost_per_token_decisions": {
+          "type": "number",
+          "minimum": 0
+        },
         "output_cost_per_token_flex": {
           "type": "number",
           "minimum": 0,
@@ -763,6 +870,10 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
+        "output_cost_per_token_ultrafast": {
+          "type": "number",
+          "minimum": 0
+        },
         "output_cost_per_video_per_second": {
           "type": "number",
           "minimum": 0
@@ -945,6 +1056,24 @@
         "supports_audio_output": {
           "type": "boolean"
         },
+        "supports_bedrock_converse_tool_result_images": {
+          "type": "boolean"
+        },
+        "supports_bedrock_native_structured_output": {
+          "type": "boolean"
+        },
+        "supports_bedrock_runtime_chat_completions_inline_reasoning": {
+          "type": "boolean"
+        },
+        "supports_bedrock_runtime_chat_completions_response_format": {
+          "type": "boolean"
+        },
+        "supports_bedrock_runtime_chat_completions_tools_with_reasoning": {
+          "type": "boolean"
+        },
+        "supports_box_questions": {
+          "type": "boolean"
+        },
         "supports_computer_use": {
           "type": "boolean"
         },
@@ -1017,6 +1146,9 @@
         "supports_reasoning": {
           "type": "boolean"
         },
+        "supports_regex_lookaround": {
+          "type": "boolean"
+        },
         "supports_response_schema": {
           "type": "boolean"
         },
@@ -1115,6 +1247,31 @@
           "minimum": 0,
           "description": "Tokens added once per request to a local count estimate, for the provider's chat framing."
         },
+        "token_count_model": {
+          "type": "object",
+          "required": [
+            "model"
+          ],
+          "additionalProperties": false,
+          "properties": {
+            "model": {
+              "type": "string",
+              "pattern": "\\S"
+            },
+            "region": {
+              "type": "string",
+              "pattern": "\\S"
+            },
+            "litellm_provider": {
+              "type": "string",
+              "enum": [
+                "bedrock",
+                "bedrock_mantle"
+              ]
+            }
+          },
+          "description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in."
+        },
         "token_count_tokenizer": {
           "type": "string",
           "description": "Tokenizer litellm counts this model's requests with when the provider cannot count them.",
diff --git a/pyproject.toml b/pyproject.toml
index a844ccdeea3..24ef859796e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -286,7 +286,7 @@ ci = [
     "langchain-openai==1.1.14",
     "langgraph>=1.2.4,<1.3.0",
     "langgraph-prebuilt>=1.1.0,<1.3.0",
-    "claude-agent-sdk==0.1.44",
+    "claude-agent-sdk==0.2.165",
     "google-cloud-speech==2.40.0",
 ]
 healthcheck = [
diff --git a/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py
new file mode 100644
index 00000000000..40676400184
--- /dev/null
+++ b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py
@@ -0,0 +1,349 @@
+import asyncio
+import json
+import re
+import threading
+import uuid
+from dataclasses import dataclass
+from pathlib import Path
+from queue import SimpleQueue
+from types import MappingProxyType
+from typing import Final
+from urllib.parse import urlsplit
+
+import httpx
+import psutil
+import pytest
+import yaml
+from integration._support.client import Gateway, eventually
+from integration._support.database import read_rows
+from integration._support.process import owned_proxy_process
+from integration._support.wire import Reply, Request, Wire, wire_server
+from integration.providers.test_anthropic_safeguards_beta_wire import (
+    ANTHROPIC_KEY,
+    ANTHROPIC_MODEL,
+    BETA,
+    OMITTED,
+    anthropic_peer,
+    marker_of,
+    messages_body,
+    stream_frames,
+)
+from pydantic import JsonValue, TypeAdapter
+
+_CONFIG_MODEL: Final = "anthropic-safeguards-chaos"
+_FOUNDRY_CONFIG_MODEL: Final = "azure-ai-safeguards-chaos"
+_YAML_OBJECT: Final = TypeAdapter(dict[str, JsonValue])
+_MARKER: Final = re.compile(r"marker-([0-9a-f]{32})")
+_STARTED_WORKER: Final = re.compile(r"Started server process \[(\d+)\]")
+_MODEL_LIST: Final = json.dumps(
+    {"object": "list", "data": [{"id": ANTHROPIC_MODEL, "object": "model", "owned_by": "anthropic"}]}
+).encode()
+
+
+@dataclass(frozen=True, slots=True)
+class _Call:
+    stream: bool
+    marker: str
+    safeguards: bool = True
+
+
+@dataclass(frozen=True, slots=True)
+class _Served:
+    call: _Call
+    status: int
+    text: str
+
+
+def _calls(count: int, stream: bool, safeguards: bool = True) -> tuple[_Call, ...]:
+    return tuple(_Call(stream=stream, marker=uuid.uuid4().hex, safeguards=safeguards) for _ in range(count))
+
+
+def _streamed_reply(marker: str, abort_after: int | None = None, pause: float = 0) -> Reply:
+    return Reply(
+        content_type="text/event-stream",
+        chunks=stream_frames(marker),
+        abort_after=abort_after,
+        pause_between_chunks=pause,
+    )
+
+
+async def _send(client: httpx.AsyncClient, key: str, model: str, call: _Call) -> _Served:
+    async with client.stream(
+        "POST",
+        "/v1/messages",
+        json=(
+            messages_body(model, call.marker, stream=call.stream)
+            if call.safeguards
+            else messages_body(model, call.marker, stream=call.stream, safeguards=OMITTED)
+        ),
+        headers={"Authorization": f"Bearer {key}", "anthropic-version": "2023-06-01"},
+    ) as response:
+        raw: Final = await response.aread()
+    return _Served(call=call, status=response.status_code, text=raw.decode())
+
+
+async def _burst(
+    base_url: str, key: str, model: str, calls: tuple[_Call, ...], *, tolerate_transport_errors: bool = False
+) -> tuple[_Served, ...]:
+    async with httpx.AsyncClient(base_url=base_url, timeout=60, trust_env=False) as client:
+        results: Final = await asyncio.gather(
+            *(_send(client, key, model, call) for call in calls), return_exceptions=tolerate_transport_errors
+        )
+    for result in results:
+        assert not isinstance(result, BaseException) or isinstance(result, httpx.TransportError), repr(result)
+    return tuple(result for result in results if isinstance(result, _Served))
+
+
+def _assert_answered_with_its_own_marker(served: _Served) -> None:
+    assert served.status == 200, served.text
+    assert set(_MARKER.findall(served.text)) == {served.call.marker}, served.text
+    assert f"msg_{served.call.marker}" in served.text, served.text
+    if served.call.stream:
+        assert "event: message_stop" in served.text, served.text
+
+
+def _assert_every_request_carried_the_beta(received: tuple[Request, ...], markers: frozenset[str]) -> None:
+    assert sorted(marker_of(request) for request in received) == sorted(markers)
+    missing: Final = [
+        frozenset(request.headers) for request in received if request.headers.get("anthropic-beta") != BETA
+    ]
+    assert missing == [], missing
+
+
+def _spend_success_ids(model: str, expected: frozenset[str]) -> None:
+    rows: Final = eventually(
+        lambda: read_rows(
+            'SELECT request_id FROM "LiteLLM_SpendLogs" WHERE model_group=%s AND status=%s', (model, "success")
+        ),
+        lambda found: expected <= {str(row["request_id"]) for row in found},
+        seconds=70,
+    )
+    identities: Final = [row["request_id"] for row in rows]
+    assert len(set(identities)) == len(identities), identities
+
+
+async def test_burst_with_aborted_streams_keeps_the_beta_on_every_forwarded_request(gateway: Gateway) -> None:
+    calls: Final = tuple(_Call(stream=index % 2 == 0, marker=uuid.uuid4().hex) for index in range(30))
+    aborted: Final = frozenset(call.marker for index, call in enumerate(calls) if call.stream and index % 3 == 0)
+
+    def respond(request: Request) -> Reply:
+        marker: Final = marker_of(request)
+        if marker in aborted:
+            return _streamed_reply(marker, abort_after=0)
+        return anthropic_peer(request)
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        served: Final = await _burst(str(gateway.client.base_url), gateway.key, model, calls)
+        assert len(served) == 30
+        for item in served:
+            if item.call.marker in aborted:
+                assert item.status == 500, item.text
+                assert '"type":"api_error"' in item.text and "marker-" not in item.text, item.text
+            else:
+                _assert_answered_with_its_own_marker(item)
+        recovery: Final = _Call(stream=True, marker=uuid.uuid4().hex)
+        (recovered,) = await _burst(str(gateway.client.base_url), gateway.key, model, (recovery,))
+        _assert_answered_with_its_own_marker(recovered)
+        _assert_every_request_carried_the_beta(wire.drain(), frozenset(call.marker for call in (*calls, recovery)))
+        answered: Final = frozenset(f"msg_{call.marker}" for call in (*calls, recovery) if call.marker not in aborted)
+        _spend_success_ids(model, answered)
+
+
+async def test_slow_streams_complete_with_the_beta_on_every_request(gateway: Gateway) -> None:
+    calls: Final = _calls(10, stream=True)
+    with (
+        wire_server(lambda request: _streamed_reply(marker_of(request), pause=0.3)) as wire,
+        gateway.scenario() as scenario,
+    ):
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        served: Final = await _burst(str(gateway.client.base_url), gateway.key, model, calls)
+        assert len(served) == 10
+        for item in served:
+            _assert_answered_with_its_own_marker(item)
+        _assert_every_request_carried_the_beta(wire.drain(), frozenset(call.marker for call in calls))
+        _spend_success_ids(model, frozenset(f"msg_{call.marker}" for call in calls))
+
+
+def _anthropic_deployment(wire: Wire) -> dict[str, JsonValue]:
+    return {
+        "model_name": _CONFIG_MODEL,
+        "litellm_params": {"model": f"anthropic/{ANTHROPIC_MODEL}", "api_base": wire.url, "api_key": ANTHROPIC_KEY},
+    }
+
+
+def _foundry_deployment(wire: Wire) -> dict[str, JsonValue]:
+    return {
+        "model_name": _FOUNDRY_CONFIG_MODEL,
+        "litellm_params": {
+            "model": "azure_ai/claude-sonnet-4-6",
+            "api_base": wire.url,
+            "api_key": "synthetic-foundry-key",
+        },
+    }
+
+
+def _chaos_config(tmp_path: Path, *deployments: dict[str, JsonValue]) -> Path:
+    base: Final = _YAML_OBJECT.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()))
+    config: Final = {**base, "model_list": list(deployments)}
+    path: Final = tmp_path / "anthropic-safeguards-chaos.yaml"
+    path.write_text(yaml.safe_dump(config))
+    return path
+
+
+def _open_upstream_connections(pid: int, upstream: str) -> int:
+    port: Final = urlsplit(upstream).port
+    return sum(
+        1
+        for connection in psutil.Process(pid).net_connections(kind="tcp")
+        if connection.status == psutil.CONN_ESTABLISHED and connection.raddr and connection.raddr.port == port
+    )
+
+
+@pytest.mark.skip(reason="Needs OwnedProxy.replacing_worker, which this stable line's integration harness does not have")
+@pytest.mark.timeout(180)
+async def test_worker_sigkill_mid_burst_leaves_the_sibling_sending_the_beta(gateway: Gateway, tmp_path: Path) -> None:
+    calls: Final = _calls(20, stream=False)
+    release: Final = threading.Event()
+    held_markers: Final[SimpleQueue[str]] = SimpleQueue()
+
+    def held(request: Request) -> Reply:
+        if (request.method, request.target) == ("GET", "/v1/models"):
+            return Reply(body=_MODEL_LIST)
+        held_markers.put(marker_of(request))
+        assert release.wait(timeout=60), "The burst was never released"
+        return anthropic_peer(request)
+
+    with wire_server(held) as wire:
+        path: Final = _chaos_config(tmp_path, _anthropic_deployment(wire))
+        with owned_proxy_process(gateway, tmp_path, {}, config=path, workers=2) as owned:
+            candidate: Final = owned.gateway
+            workers: Final = eventually(
+                lambda: tuple(int(found.group(1)) for found in _STARTED_WORKER.finditer(owned.log.read_text())),
+                lambda pids: len(pids) == 2,
+                seconds=30,
+            )
+            burst: Final = asyncio.create_task(
+                _burst(
+                    str(candidate.client.base_url), candidate.key, _CONFIG_MODEL, calls, tolerate_transport_errors=True
+                )
+            )
+            await asyncio.to_thread(eventually, held_markers.qsize, lambda size: size == 20, 60)
+            held_by: Final = MappingProxyType({pid: _open_upstream_connections(pid, wire.url) for pid in workers})
+            assert sum(held_by.values()) == 20, held_by
+            victim_pid, survivor_pid = sorted(workers, key=held_by.__getitem__)
+            with owned.replacing_worker(victim_pid) as kill:
+                kill.freeze()
+                await asyncio.to_thread(kill)
+                release.set()
+                served: Final = await burst
+                assert held_by[survivor_pid] >= 10, held_by
+                assert len(served) == held_by[survivor_pid], (held_by, len(served))
+                for item in served:
+                    _assert_answered_with_its_own_marker(item)
+            follow_up: Final = _Call(stream=False, marker=uuid.uuid4().hex)
+            (answered,) = await _burst(str(candidate.client.base_url), candidate.key, _CONFIG_MODEL, (follow_up,))
+            _assert_answered_with_its_own_marker(answered)
+            received: Final = wire.drain()
+            posts: Final = tuple(request for request in received if request.method == "POST")
+            probes: Final[list[tuple[str, str]]] = [
+                (request.method, request.target) for request in received if request.method != "POST"
+            ]
+            assert set(probes) <= {("GET", "/v1/models")}, probes
+            _assert_every_request_carried_the_beta(posts, frozenset(call.marker for call in (*calls, follow_up)))
+
+
+def _beta_map_gets(received: tuple[Request, ...]) -> int:
+    return sum(1 for request in received if (request.method, request.target) == ("GET", "/beta.json"))
+
+
+async def _chat(base_url: str, key: str, marker: str) -> httpx.Response:
+    async with httpx.AsyncClient(base_url=base_url, timeout=60, trust_env=False) as client:
+        return await client.post(
+            "/v1/chat/completions",
+            json={
+                "model": _CONFIG_MODEL,
+                "max_tokens": 16,
+                "messages": [{"role": "user", "content": f"Question marker-{marker}"}],
+            },
+            headers={"Authorization": f"Bearer {key}"},
+        )
+
+
+async def _answered_while_the_beta_map_is_held(
+    base_url: str, key: str, guarded: tuple[_Call, ...], chat_markers: tuple[str, ...]
+) -> None:
+    served: Final = await _burst(base_url, key, _CONFIG_MODEL, guarded)
+    chats: Final = await asyncio.gather(*(_chat(base_url, key, marker) for marker in chat_markers))
+    for item in served:
+        _assert_answered_with_its_own_marker(item)
+    for marker, chat in zip(chat_markers, chats, strict=True):
+        assert chat.status_code == 200, chat.text
+        assert f"marker-{marker}" in chat.text, chat.text
+
+
+@pytest.mark.timeout(240)
+async def test_cold_workers_fetch_the_beta_map_only_for_filtered_safeguards_requests_off_the_shared_threads(
+    gateway: Gateway, tmp_path: Path
+) -> None:
+    beta_map: Final = Path("litellm/anthropic_beta_headers_config.json").read_bytes()
+    release: Final = threading.Event()
+
+    def held_beta_map(_: Request) -> Reply:
+        assert release.wait(timeout=180), "The beta map was never released"
+        return Reply(body=beta_map)
+
+    def upstream(request: Request) -> Reply:
+        if (request.method, request.target) == ("GET", "/v1/models"):
+            return Reply(body=_MODEL_LIST)
+        return anthropic_peer(request)
+
+    plain: Final = _calls(8, stream=False, safeguards=False)
+    plain_foundry: Final = _calls(8, stream=False, safeguards=False)
+    direct: Final = _calls(8, stream=False)
+    foundry: Final = _calls(80, stream=False)
+    direct_while_held: Final = _calls(8, stream=False)
+    chat_markers: Final = tuple(uuid.uuid4().hex for _ in range(4))
+    with wire_server(held_beta_map) as beta_map_wire, wire_server(upstream) as wire:
+        path: Final = _chaos_config(tmp_path, _anthropic_deployment(wire), _foundry_deployment(wire))
+        with owned_proxy_process(
+            gateway,
+            tmp_path,
+            {"LITELLM_ANTHROPIC_BETA_HEADERS_URL": f"{beta_map_wire.url}/beta.json"},
+            remove_environment=("LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS",),
+            config=path,
+            workers=2,
+        ) as owned:
+            base_url: Final = str(owned.gateway.client.base_url)
+            key: Final = owned.gateway.key
+            cold: Final = (
+                *await _burst(base_url, key, _CONFIG_MODEL, plain),
+                *await _burst(base_url, key, _FOUNDRY_CONFIG_MODEL, plain_foundry),
+                *await _burst(base_url, key, _CONFIG_MODEL, direct),
+            )
+            for served_cold in cold:
+                _assert_answered_with_its_own_marker(served_cold)
+            assert beta_map_wire.received.qsize() == 0, "a request that never filters betas fetched the beta map"
+
+            held: Final = asyncio.create_task(_burst(base_url, key, _FOUNDRY_CONFIG_MODEL, foundry))
+            try:
+                await asyncio.to_thread(eventually, beta_map_wire.received.qsize, lambda size: size >= 1, 60)
+                await asyncio.wait_for(
+                    _answered_while_the_beta_map_is_held(base_url, key, direct_while_held, chat_markers), timeout=45
+                )
+                assert not held.done(), "Foundry safeguards requests were answered before the beta map loaded"
+            finally:
+                release.set()
+            for served_foundry in await held:
+                _assert_answered_with_its_own_marker(served_foundry)
+
+        received: Final = tuple(request for request in wire.drain() if request.method == "POST")
+        beta_by_marker: Final = MappingProxyType(
+            {marker_of(request): request.headers.get("anthropic-beta") for request in received}
+        )
+        assert {beta_by_marker[call.marker] for call in (*direct, *direct_while_held, *foundry)} == {BETA}, (
+            beta_by_marker
+        )
+        assert {beta_by_marker[call.marker] for call in (*plain, *plain_foundry)} == {None}, beta_by_marker
+        fetches: Final = _beta_map_gets(beta_map_wire.drain())
+        assert 1 <= fetches <= 2, fetches
diff --git a/tests/integration/providers/test_anthropic_safeguards_beta_wire.py b/tests/integration/providers/test_anthropic_safeguards_beta_wire.py
new file mode 100644
index 00000000000..0c41efffe73
--- /dev/null
+++ b/tests/integration/providers/test_anthropic_safeguards_beta_wire.py
@@ -0,0 +1,809 @@
+import itertools
+import json
+import re
+import time
+import uuid
+from collections.abc import Callable, Mapping
+from dataclasses import dataclass
+from pathlib import Path
+from types import MappingProxyType
+from typing import Final
+
+import anthropic
+import httpx
+import openai
+import pytest
+from integration._support.client import Gateway, eventually
+from integration._support.database import read_rows
+from integration._support.process import owned_proxy
+from integration._support.vertex import service_account_json
+from integration._support.wire import Reply, Request, Wire, wire_server
+from pydantic import JsonValue, TypeAdapter
+
+BETA: Final = "dangerous-tool-use-2026-09-03"
+SAFEGUARDS: Final[list[JsonValue]] = [
+    {"type": "dangerous_tool_use", "classifier_context": {"v": 1, "permission_mode": "auto"}}
+]
+ANTHROPIC_MODEL: Final = "claude-sonnet-4-5-20250929"
+ANTHROPIC_KEY: Final = "synthetic-anthropic-key"
+_CLAUDE_CODE_BETAS: Final = (
+    "claude-code-20250219",
+    "interleaved-thinking-2025-05-14",
+    "fine-grained-tool-streaming-2025-05-14",
+    "context-management-2025-06-27",
+)
+_CLIENT_BETAS: Final = ",".join(_CLAUDE_CODE_BETAS)
+_CLIENT_BETAS_WITH_DANGEROUS: Final = ",".join((*_CLAUDE_CODE_BETAS, BETA))
+_MERGED_BETAS: Final = ",".join(sorted((*_CLAUDE_CODE_BETAS, BETA)))
+_FOUNDRY_MODEL: Final = "azure_ai/claude-sonnet-4-6"
+_FOUNDRY_KEY: Final = "synthetic-foundry-key"
+_FOUNDRY_TARGET: Final = "/anthropic/v1/messages"
+_FOUNDRY_ARRAY_ERROR: Final = "safeguards: Input should be a valid array"
+_FOUNDRY_EXTRA_INPUT_ERROR: Final = "safeguards: Extra inputs are not permitted"
+_ANTHROPIC_VERSION: Final = MappingProxyType({"anthropic-version": "2023-06-01"})
+_MESSAGES_KEYS: Final = frozenset({"max_tokens", "messages", "model", "stream"})
+_RESPONSES_KEYS: Final = frozenset({"include", "input", "max_output_tokens", "model"})
+_SDK_EXTRA: Final[dict[str, JsonValue]] = {"safeguards": SAFEGUARDS, "cache": {"no-cache": True}, "num_retries": 0}
+_MARKER: Final = re.compile(r"marker-([0-9a-f]{32})")
+_JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue])
+
+
+@dataclass(frozen=True, slots=True)
+class _Omitted:
+    pass
+
+
+OMITTED: Final = _Omitted()
+
+
+@dataclass(frozen=True, slots=True)
+class _Observed:
+    method: str
+    target: str
+    marker: str
+    headers: Mapping[str, str]
+    body: Mapping[str, JsonValue]
+
+    @property
+    def beta(self) -> str | None:
+        return self.headers.get("anthropic-beta")
+
+    @property
+    def keys(self) -> frozenset[str]:
+        return frozenset(self.body)
+
+    @property
+    def header_names(self) -> frozenset[str]:
+        return frozenset(self.headers)
+
+
+def marker_of(request: Request) -> str:
+    found: Final = _MARKER.search(request.body.decode())
+    assert found is not None, request.body
+    return found.group(1)
+
+
+def _message(marker: str) -> dict[str, JsonValue]:
+    return {
+        "id": f"msg_{marker}",
+        "type": "message",
+        "role": "assistant",
+        "model": ANTHROPIC_MODEL,
+        "content": [{"type": "text", "text": f"answer marker-{marker}"}],
+        "stop_reason": "end_turn",
+        "stop_sequence": None,
+        "usage": {"input_tokens": 12, "output_tokens": 5},
+    }
+
+
+def stream_frames(marker: str) -> tuple[bytes, ...]:
+    opening: Final[dict[str, JsonValue]] = {
+        **_message(marker),
+        "content": [],
+        "stop_reason": None,
+        "usage": {"input_tokens": 12, "output_tokens": 0},
+    }
+    events: Final[tuple[tuple[str, dict[str, JsonValue]], ...]] = (
+        ("message_start", {"message": opening}),
+        ("content_block_start", {"index": 0, "content_block": {"type": "text", "text": ""}}),
+        ("content_block_delta", {"index": 0, "delta": {"type": "text_delta", "text": f"answer marker-{marker}"}}),
+        ("content_block_stop", {"index": 0}),
+        ("message_delta", {"delta": {"stop_reason": "end_turn", "stop_sequence": None}, "usage": {"output_tokens": 5}}),
+        ("message_stop", {}),
+    )
+    return tuple(
+        f"event: {kind}\ndata: {json.dumps({'type': kind, **payload})}\n\n".encode() for kind, payload in events
+    )
+
+
+def anthropic_peer(request: Request) -> Reply:
+    marker: Final = marker_of(request)
+    if _JSON_OBJECT.validate_json(request.body).get("stream") is True:
+        return Reply(content_type="text/event-stream", chunks=stream_frames(marker))
+    return Reply(body=json.dumps(_message(marker)).encode())
+
+
+def _responses_peer(request: Request) -> Reply:
+    marker: Final = marker_of(request)
+    return Reply(
+        body=json.dumps(
+            {
+                "id": f"resp_{marker}",
+                "object": "response",
+                "created_at": 1,
+                "status": "completed",
+                "model": "gpt-4o-mini",
+                "output": [
+                    {
+                        "type": "message",
+                        "id": f"msg_{marker}",
+                        "status": "completed",
+                        "role": "assistant",
+                        "content": [{"type": "output_text", "text": f"answer marker-{marker}", "annotations": []}],
+                    }
+                ],
+                "usage": {"input_tokens": 12, "output_tokens": 5, "total_tokens": 17},
+            }
+        ).encode()
+    )
+
+
+def _error_peer(status: int, kind: str, message: str) -> Callable[[Request], Reply]:
+    body: Final = json.dumps({"type": "error", "error": {"type": kind, "message": message}}).encode()
+    return lambda request: Reply(status=status, body=body)
+
+
+def messages_body(
+    model: str,
+    marker: str,
+    *,
+    safeguards: JsonValue | _Omitted = SAFEGUARDS,
+    stream: bool = False,
+    no_cache: bool = True,
+) -> dict[str, JsonValue]:
+    base: Final[dict[str, JsonValue]] = {
+        "model": model,
+        "max_tokens": 16,
+        "messages": [{"role": "user", "content": f"Question marker-{marker}"}],
+        "num_retries": 0,
+        **({"stream": True} if stream else {}),
+        **({"cache": {"no-cache": True}} if no_cache else {}),
+    }
+    if isinstance(safeguards, _Omitted):
+        return base
+    return {**base, "safeguards": safeguards}
+
+
+def _observe(request: Request) -> _Observed:
+    return _Observed(
+        request.method, request.target, marker_of(request), request.headers, _JSON_OBJECT.validate_json(request.body)
+    )
+
+
+def _only(wire: Wire) -> _Observed:
+    (request,) = wire.drain()
+    return _observe(request)
+
+
+def _post(gateway: Gateway, body: Mapping[str, JsonValue], *, beta: str | None = None) -> httpx.Response:
+    headers: Final = {**_ANTHROPIC_VERSION, **({"anthropic-beta": beta} if beta else {})}
+    return gateway.request("POST", "/v1/messages", body, headers=headers)
+
+
+def _assert_answered(response: httpx.Response, marker: str) -> None:
+    assert response.status_code == 200, response.text
+    assert response.json()["id"] == f"msg_{marker}", response.text
+
+
+def _assert_streamed(response: httpx.Response, marker: str) -> None:
+    assert response.status_code == 200, response.text
+    assert f"msg_{marker}" in response.text and f"answer marker-{marker}" in response.text, response.text
+    assert "event: message_stop" in response.text, response.text
+
+
+def _spend_row(identity: str) -> None:
+    rows: Final = eventually(
+        lambda: read_rows('SELECT request_id, status FROM "LiteLLM_SpendLogs" WHERE request_id=%s', (identity,)),
+        lambda found: len(found) == 1,
+        seconds=70,
+    )
+    assert rows[0]["status"] == "success", rows
+
+
+def _cache_hit_spend_row(identity: str) -> None:
+    rows: Final = eventually(
+        lambda: read_rows(
+            'SELECT request_id, status, cache_hit FROM "LiteLLM_SpendLogs" WHERE request_id LIKE %s',
+            (f"{identity}\\_cache\\_hit%",),
+        ),
+        lambda found: len(found) == 1,
+        seconds=70,
+    )
+    assert (rows[0]["status"], str(rows[0]["cache_hit"])) == ("success", "True"), rows
+
+
+def _responses_spend_row(model: str) -> None:
+    rows: Final = eventually(
+        lambda: read_rows(
+            'SELECT request_id, status FROM "LiteLLM_SpendLogs" WHERE model_group = %s AND call_type = %s',
+            (model, "aresponses"),
+        ),
+        lambda found: len(found) == 1,
+        seconds=70,
+    )
+    assert rows[0]["status"] == "success", rows
+
+
+def _expect_messages(
+    observed: _Observed,
+    *,
+    target: str,
+    auth: tuple[str, str] | None,
+    beta: str | None,
+    safeguards: JsonValue | _Omitted = SAFEGUARDS,
+    keys: frozenset[str] = _MESSAGES_KEYS,
+) -> None:
+    assert (observed.method, observed.target) == ("POST", target)
+    if auth is not None:
+        credential_matches: Final = observed.headers.get(auth[0]) == auth[1]
+        assert credential_matches, f"{auth[0]} differs from the deployment credential; headers {observed.header_names}"
+    assert observed.beta == beta, observed.header_names
+    if isinstance(safeguards, _Omitted):
+        assert observed.keys == keys
+        return
+    assert observed.keys == keys | {"safeguards"}
+    assert observed.body["safeguards"] == safeguards
+
+
+def _expect_anthropic_version(observed: _Observed) -> None:
+    assert observed.headers.get("anthropic-version") == "2023-06-01", observed.header_names
+
+
+@dataclass(frozen=True, slots=True)
+class _ShapeCase:
+    sent: JsonValue | _Omitted
+    forwarded: JsonValue | _Omitted
+    client_beta: str | None
+    expected_beta: str | None
+    stream: bool = False
+
+
+_ANTHROPIC_SHAPES: Final = MappingProxyType(
+    {
+        "D1_safeguards_without_client_header": _ShapeCase(SAFEGUARDS, SAFEGUARDS, None, BETA),
+        "D2_safeguards_with_claude_code_header": _ShapeCase(
+            SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS_WITH_DANGEROUS, _MERGED_BETAS
+        ),
+        "D3_safeguards_with_claude_code_header_lacking_the_beta": _ShapeCase(
+            SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS, _MERGED_BETAS
+        ),
+        "D4_empty_safeguards": _ShapeCase([], [], None, BETA),
+        "D5_null_safeguards": _ShapeCase(None, OMITTED, None, None),
+        "D6_missing_safeguards": _ShapeCase(OMITTED, OMITTED, None, None),
+    }
+)
+_FOUNDRY_SHAPES: Final = MappingProxyType(
+    {
+        "D9_streamed_safeguards_with_claude_code_header": _ShapeCase(
+            SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS_WITH_DANGEROUS, BETA, stream=True
+        ),
+        "D11_empty_safeguards": _ShapeCase([], [], None, BETA),
+        "D12_null_safeguards": _ShapeCase(None, OMITTED, None, None),
+        "D13_missing_safeguards_with_claude_code_header_lacking_the_beta": _ShapeCase(
+            OMITTED, OMITTED, _CLIENT_BETAS, None
+        ),
+    }
+)
+
+
+@pytest.mark.parametrize("row", tuple(_ANTHROPIC_SHAPES))
+def test_anthropic_messages_derive_the_dangerous_tool_use_beta_from_safeguards(gateway: Gateway, row: str) -> None:
+    case: Final = _ANTHROPIC_SHAPES[row]
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        response: Final = _post(gateway, messages_body(model, marker, safeguards=case.sent), beta=case.client_beta)
+        _assert_answered(response, marker)
+        observed: Final = _only(wire)
+        _expect_messages(
+            observed,
+            target="/v1/messages",
+            auth=("x-api-key", ANTHROPIC_KEY),
+            beta=case.expected_beta,
+            safeguards=case.forwarded,
+        )
+        _expect_anthropic_version(observed)
+        _spend_row(f"msg_{marker}")
+
+
+@dataclass(frozen=True, slots=True, kw_only=True)
+class _DropCase:
+    deployment: Callable[[Gateway], Mapping[str, JsonValue]]
+    target: str
+    auth: tuple[str, str] | None
+    keys: frozenset[str] = _MESSAGES_KEYS
+
+
+_VERTEX_PROJECT: Final = "scripted-project"
+_VERTEX_LOCATION: Final = "us-east5"
+_VERTEX_MODEL: Final = "claude-opus-5-5"
+
+_DROP_CASES: Final = MappingProxyType(
+    {
+        "anthropic": _DropCase(
+            deployment=lambda _: {"model": f"anthropic/{ANTHROPIC_MODEL}", "api_key": ANTHROPIC_KEY},
+            target="/v1/messages",
+            auth=("x-api-key", ANTHROPIC_KEY),
+        ),
+        "azure_ai": _DropCase(
+            deployment=lambda _: {"model": _FOUNDRY_MODEL, "api_key": _FOUNDRY_KEY},
+            target=_FOUNDRY_TARGET,
+            auth=("x-api-key", _FOUNDRY_KEY),
+        ),
+        "bedrock_claude_platform": _DropCase(
+            deployment=lambda _: {
+                "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}",
+                "api_key": "synthetic-platform-key",
+                "workspace_id": "ws-synthetic",
+                "aws_region_name": "us-east-1",
+            },
+            target="/v1/messages",
+            auth=("x-api-key", "synthetic-platform-key"),
+        ),
+        "vertex_ai": _DropCase(
+            deployment=lambda gateway: {
+                "model": f"vertex_ai/{_VERTEX_MODEL}",
+                "api_key": None,
+                "vertex_project": _VERTEX_PROJECT,
+                "vertex_location": _VERTEX_LOCATION,
+                "vertex_credentials": service_account_json(_VERTEX_PROJECT, gateway.upstream_url.rstrip("/")),
+            },
+            target=(
+                f"/v1/projects/{_VERTEX_PROJECT}/locations/{_VERTEX_LOCATION}"
+                f"/publishers/anthropic/models/{_VERTEX_MODEL}:rawPredict"
+            ),
+            auth=None,
+            keys=frozenset({"anthropic_version", "max_tokens", "messages", "stream"}),
+        ),
+    }
+)
+
+
+@pytest.mark.parametrize("row", tuple(_DROP_CASES))
+def test_a_deployment_dropping_safeguards_sends_neither_the_field_nor_the_beta(gateway: Gateway, row: str) -> None:
+    case: Final = _DROP_CASES[row]
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            api_base=wire.url, additional_drop_params=["safeguards"], **case.deployment(gateway)
+        )
+        response: Final = _post(gateway, messages_body(model, marker))
+        _assert_answered(response, marker)
+        _expect_messages(_only(wire), target=case.target, auth=case.auth, beta=None, safeguards=OMITTED, keys=case.keys)
+        _spend_row(f"msg_{marker}")
+
+
+def test_a_deployment_dropping_context_management_sends_neither_the_field_nor_its_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            model=f"anthropic/{ANTHROPIC_MODEL}",
+            api_base=wire.url,
+            api_key=ANTHROPIC_KEY,
+            additional_drop_params=["context_management"],
+        )
+        body: Final = {
+            **messages_body(model, marker, safeguards=OMITTED),
+            "context_management": {"edits": [{"type": "clear_tool_uses_20250919"}]},
+        }
+        response: Final = _post(gateway, body)
+        _assert_answered(response, marker)
+        _expect_messages(
+            _only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=None, safeguards=OMITTED
+        )
+        _spend_row(f"msg_{marker}")
+
+
+@pytest.mark.parametrize("row", tuple(_FOUNDRY_SHAPES))
+def test_azure_ai_messages_derive_the_beta_instead_of_forwarding_the_client_header(gateway: Gateway, row: str) -> None:
+    case: Final = _FOUNDRY_SHAPES[row]
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        response: Final = _post(
+            gateway, messages_body(model, marker, safeguards=case.sent, stream=case.stream), beta=case.client_beta
+        )
+        if case.stream:
+            _assert_streamed(response, marker)
+        else:
+            _assert_answered(response, marker)
+        observed: Final = _only(wire)
+        _expect_messages(
+            observed,
+            target=_FOUNDRY_TARGET,
+            auth=("x-api-key", _FOUNDRY_KEY),
+            beta=case.expected_beta,
+            safeguards=case.forwarded,
+        )
+        _expect_anthropic_version(observed)
+        _spend_row(f"msg_{marker}")
+
+
+def test_anthropic_sdk_sync_safeguards_derive_the_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        client: Final = anthropic.Anthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0)
+        reply: Final = client.messages.create(
+            model=model,
+            max_tokens=16,
+            messages=[{"role": "user", "content": f"Question marker-{marker}"}],
+            extra_body=_SDK_EXTRA,
+        )
+        assert reply.id == f"msg_{marker}", reply
+        _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=BETA)
+        _spend_row(f"msg_{marker}")
+
+
+async def test_anthropic_sdk_async_stream_safeguards_derive_the_beta_and_log_spend(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        client: Final = anthropic.AsyncAnthropic(
+            base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0
+        )
+        async with client.messages.with_streaming_response.create(
+            model=model,
+            max_tokens=16,
+            messages=[{"role": "user", "content": f"Question marker-{marker}"}],
+            stream=True,
+            extra_body=_SDK_EXTRA,
+        ) as streamed:
+            pieces: Final = [
+                event.delta.text
+                async for event in await streamed.parse()
+                if event.type == "content_block_delta" and event.delta.type == "text_delta"
+            ]
+        assert "".join(pieces) == f"answer marker-{marker}", pieces
+        _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=BETA)
+        _spend_row(f"msg_{marker}")
+
+
+def test_azure_ai_sdk_sync_safeguards_derive_the_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        client: Final = anthropic.Anthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0)
+        reply: Final = client.messages.create(
+            model=model,
+            max_tokens=16,
+            messages=[{"role": "user", "content": f"Question marker-{marker}"}],
+            extra_body=_SDK_EXTRA,
+        )
+        assert reply.id == f"msg_{marker}", reply
+        _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA)
+        _spend_row(f"msg_{marker}")
+
+
+@dataclass(frozen=True, slots=True, kw_only=True)
+class _ProviderCase:
+    parameters: Mapping[str, JsonValue]
+    auth: tuple[str, str] | None
+    expected_beta: str | None
+    target: str = "/v1/messages"
+    api_base_suffix: str = ""
+    model_info: Mapping[str, JsonValue] | None = None
+    client_beta: str | None = None
+    keys: frozenset[str] = _MESSAGES_KEYS
+    extra_headers: Mapping[str, str] = MappingProxyType({})
+    body_beta: list[str] | None = None
+
+
+_PROVIDERS: Final = MappingProxyType(
+    {
+        "D14_deepseek_with_claude_code_header": _ProviderCase(
+            parameters={"model": "deepseek/deepseek-chat", "api_key": "synthetic-deepseek-key"},
+            client_beta=_CLIENT_BETAS_WITH_DANGEROUS,
+            target="/anthropic/v1/messages",
+            auth=("x-api-key", "synthetic-deepseek-key"),
+            expected_beta=None,
+        ),
+        "D15_tencent_with_claude_code_header": _ProviderCase(
+            parameters={"model": "tencent/deepseek-v4-flash", "api_key": "synthetic-tencent-key"},
+            client_beta=_CLIENT_BETAS_WITH_DANGEROUS,
+            auth=("x-api-key", "synthetic-tencent-key"),
+            expected_beta=None,
+        ),
+        "D16_minimax_with_claude_code_header": _ProviderCase(
+            parameters={"model": "minimax/MiniMax-M2", "api_key": "synthetic-minimax-key"},
+            client_beta=_CLIENT_BETAS_WITH_DANGEROUS,
+            auth=("x-api-key", "synthetic-minimax-key"),
+            expected_beta=None,
+        ),
+        "D17_openai_compatible_native_passthrough": _ProviderCase(
+            parameters={"model": "openai/claude-sonnet-4-5", "api_key": "synthetic-openai-like-key"},
+            api_base_suffix="/v1",
+            model_info={"supported_endpoints": ["/v1/messages"]},
+            auth=("authorization", "Bearer synthetic-openai-like-key"),
+            expected_beta=None,
+        ),
+        "D18_sail_with_claude_code_header": _ProviderCase(
+            parameters={"model": "sail/sail-claude", "api_key": "synthetic-sail-key"},
+            client_beta=_CLIENT_BETAS_WITH_DANGEROUS,
+            auth=("authorization", "Bearer synthetic-sail-key"),
+            expected_beta=None,
+        ),
+        "D19_edenai": _ProviderCase(
+            parameters={"model": "edenai/claude-sonnet-4-5", "api_key": "synthetic-edenai-key"},
+            auth=("authorization", "Bearer synthetic-edenai-key"),
+            expected_beta=None,
+        ),
+        "D21_bedrock_claude_platform": _ProviderCase(
+            parameters={
+                "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}",
+                "api_key": "synthetic-platform-key",
+                "workspace_id": "ws-synthetic",
+                "aws_region_name": "us-east-1",
+            },
+            auth=("x-api-key", "synthetic-platform-key"),
+            expected_beta=BETA,
+            extra_headers={"anthropic-workspace-id": "ws-synthetic"},
+        ),
+        "D22_bedrock_claude_platform_with_claude_code_header": _ProviderCase(
+            parameters={
+                "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}",
+                "api_key": "synthetic-platform-key",
+                "workspace_id": "ws-synthetic",
+                "aws_region_name": "us-east-1",
+            },
+            client_beta=_CLIENT_BETAS_WITH_DANGEROUS,
+            auth=("x-api-key", "synthetic-platform-key"),
+            expected_beta=_MERGED_BETAS,
+            extra_headers={"anthropic-workspace-id": "ws-synthetic"},
+        ),
+        "D23_bedrock_invoke": _ProviderCase(
+            parameters={
+                "model": "bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0",
+                "api_key": "synthetic-bedrock-bearer",
+                "aws_region_name": "us-east-1",
+            },
+            target="/model/anthropic.claude-sonnet-4-5-20250929-v1:0/invoke",
+            auth=("authorization", "Bearer synthetic-bedrock-bearer"),
+            expected_beta=None,
+            keys=frozenset({"anthropic_beta", "anthropic_version", "max_tokens", "messages"}),
+            body_beta=[BETA],
+        ),
+        "D24_bedrock_mantle": _ProviderCase(
+            parameters={
+                "model": "bedrock_mantle/anthropic.claude-sonnet-5-v1:0",
+                "api_key": "synthetic-mantle-bearer",
+                "aws_region_name": "us-east-1",
+            },
+            target="/anthropic/v1/messages",
+            auth=("authorization", "Bearer synthetic-mantle-bearer"),
+            expected_beta=BETA,
+            keys=frozenset({"max_tokens", "messages", "model"}),
+        ),
+    }
+)
+
+
+@pytest.mark.parametrize("row", tuple(_PROVIDERS))
+def test_anthropic_compatible_providers_receive_the_beta_only_where_the_proxy_derives_it(
+    gateway: Gateway, row: str
+) -> None:
+    case: Final = _PROVIDERS[row]
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            model_info=case.model_info, api_base=wire.url + case.api_base_suffix, **case.parameters
+        )
+        response: Final = _post(gateway, messages_body(model, marker), beta=case.client_beta)
+        _assert_answered(response, marker)
+        observed: Final = _only(wire)
+        _expect_messages(observed, target=case.target, auth=case.auth, beta=case.expected_beta, keys=case.keys)
+        for name, value in case.extra_headers.items():
+            assert observed.headers.get(name) == value, observed.header_names
+        assert observed.body.get("anthropic_beta") == case.body_beta, observed.body
+        _spend_row(f"msg_{marker}")
+
+
+def test_github_copilot_messages_forward_safeguards_without_deriving_the_beta(
+    gateway: Gateway, tmp_path: Path
+) -> None:
+    marker: Final = uuid.uuid4().hex
+    token_dir: Final = tmp_path / "copilot"
+    token_dir.mkdir()
+    with wire_server(anthropic_peer) as wire:
+        (token_dir / "api-key.json").write_text(
+            json.dumps({"token": "synthetic-copilot-token", "expires_at": 4102444800, "endpoints": {"api": wire.url}})
+        )
+        with (
+            owned_proxy(gateway, tmp_path, {"GITHUB_COPILOT_TOKEN_DIR": str(token_dir)}) as owned,
+            owned.scenario() as scenario,
+        ):
+            model: Final = scenario.model(model="github_copilot/claude-sonnet-4-5", api_base=wire.url)
+            response: Final = _post(owned, messages_body(model, marker), beta=_CLIENT_BETAS_WITH_DANGEROUS)
+            _assert_answered(response, marker)
+            observed: Final = _only(wire)
+            _expect_messages(
+                observed, target="/v1/messages", auth=("authorization", "Bearer synthetic-copilot-token"), beta=None
+            )
+            assert observed.headers.get("openai-intent") == "messages-proxy", observed.header_names
+            _spend_row(f"msg_{marker}")
+
+
+def test_non_native_deployments_bridge_to_the_responses_api_without_safeguards_or_the_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(_responses_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            model="openai/gpt-4o-mini", api_base=wire.url + "/v1", api_key="synthetic-openai-key"
+        )
+        response: Final = _post(gateway, messages_body(model, marker), beta=_CLIENT_BETAS_WITH_DANGEROUS)
+        assert response.status_code == 200 and f"answer marker-{marker}" in response.text, response.text
+        observed: Final = _only(wire)
+        assert (observed.method, observed.target) == ("POST", "/v1/responses")
+        assert observed.headers.get("authorization") == "Bearer synthetic-openai-key", observed.header_names
+        assert observed.beta is None, observed.header_names
+        assert observed.keys == _RESPONSES_KEYS, observed.keys
+        _spend_row(str(_JSON_OBJECT.validate_json(response.content)["id"]))
+
+
+def test_chat_completions_forward_safeguards_verbatim_without_deriving_the_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        client: Final = openai.OpenAI(
+            base_url=str(gateway.client.base_url).rstrip("/") + "/v1", api_key=gateway.key, max_retries=0
+        )
+        completion: Final = client.chat.completions.create(
+            model=model, messages=[{"role": "user", "content": f"Question marker-{marker}"}], extra_body=_SDK_EXTRA
+        )
+        assert completion.choices[0].message.content == f"answer marker-{marker}", completion
+        _expect_messages(
+            _only(wire),
+            target="/v1/messages",
+            auth=("x-api-key", ANTHROPIC_KEY),
+            beta=None,
+            keys=frozenset({"max_tokens", "messages", "model"}),
+        )
+        _spend_row(completion.id)
+
+
+async def test_responses_stream_forwards_safeguards_verbatim_without_deriving_the_beta(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY)
+        client: Final = openai.AsyncOpenAI(
+            base_url=str(gateway.client.base_url).rstrip("/") + "/v1", api_key=gateway.key, max_retries=0
+        )
+        async with client.responses.with_streaming_response.create(
+            model=model, input=f"Question marker-{marker}", stream=True, extra_body=_SDK_EXTRA
+        ) as streamed:
+            events: Final = [event async for event in await streamed.parse()]
+        deltas: Final = [event.delta for event in events if event.type == "response.output_text.delta"]
+        assert "".join(deltas) == f"answer marker-{marker}", events
+        assert any(event.type == "response.completed" for event in events), events
+        _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=None)
+        _responses_spend_row(model)
+
+
+_FOUNDRY_REJECTED_SHAPES: Final[Mapping[str, JsonValue]] = MappingProxyType(
+    {"S1_int": 1, "S2_empty_string": "", "S3_five_kb_string": "x" * 5000}
+)
+
+
+@pytest.mark.parametrize("row", tuple(_FOUNDRY_REJECTED_SHAPES))
+def test_foundry_rejecting_a_non_array_safeguards_value_reaches_the_caller_after_one_attempt(
+    gateway: Gateway, row: str
+) -> None:
+    value: Final = _FOUNDRY_REJECTED_SHAPES[row]
+    marker: Final = uuid.uuid4().hex
+    with (
+        wire_server(_error_peer(400, "invalid_request_error", _FOUNDRY_ARRAY_ERROR)) as wire,
+        gateway.scenario() as scenario,
+    ):
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        response: Final = _post(gateway, messages_body(model, marker, safeguards=value))
+        assert response.status_code == 400 and _FOUNDRY_ARRAY_ERROR in response.text, response.text
+        _expect_messages(
+            _only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA, safeguards=value
+        )
+
+
+def test_duplicate_safeguards_keys_resolve_to_the_last_value(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        raw: Final = (
+            f'{{"model": "{model}", "max_tokens": 16, "num_retries": 0, "cache": {{"no-cache": true}}, '
+            f'"messages": [{{"role": "user", "content": "Question marker-{marker}"}}], '
+            f'"safeguards": {json.dumps(SAFEGUARDS)}, "safeguards": null}}'
+        )
+        response: Final = gateway.client.post(
+            "/v1/messages",
+            content=raw.encode(),
+            headers={
+                "Authorization": f"Bearer {gateway.key}",
+                "content-type": "application/json",
+                **_ANTHROPIC_VERSION,
+            },
+        )
+        _assert_answered(response, marker)
+        _expect_messages(
+            _only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=None, safeguards=OMITTED
+        )
+        _spend_row(f"msg_{marker}")
+
+
+def test_the_same_safeguards_sent_twice_are_two_upstream_calls_with_two_spend_rows(gateway: Gateway) -> None:
+    markers: Final = (uuid.uuid4().hex, uuid.uuid4().hex)
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        responses: Final = tuple(_post(gateway, messages_body(model, marker)) for marker in markers)
+        for marker, response in zip(markers, responses, strict=True):
+            _assert_answered(response, marker)
+        received: Final = tuple(_observe(request) for request in wire.drain())
+        assert len(received) == 2, received
+        for observed in received:
+            _expect_messages(observed, target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA)
+        assert sorted(item.marker for item in received) == sorted(markers)
+        for marker in markers:
+            _spend_row(f"msg_{marker}")
+
+
+_UPSTREAM_ERRORS: Final = MappingProxyType(
+    {
+        "S6_unauthorized_deployment": (401, "authentication_error", "invalid x-api-key"),
+        "S7_foundry_extra_inputs_rejection": (400, "invalid_request_error", _FOUNDRY_EXTRA_INPUT_ERROR),
+    }
+)
+
+
+@pytest.mark.parametrize("row", tuple(_UPSTREAM_ERRORS))
+def test_upstream_errors_reach_the_caller_with_the_beta_sent_once(gateway: Gateway, row: str) -> None:
+    status, kind, message = _UPSTREAM_ERRORS[row]
+    marker: Final = uuid.uuid4().hex
+    with wire_server(_error_peer(status, kind, message)) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        response: Final = _post(gateway, messages_body(model, marker))
+        assert response.status_code == status and message in response.text, response.text
+        _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA)
+
+
+def _post_noting_whether_upstream_was_called(
+    gateway: Gateway, body: Mapping[str, JsonValue], wire: Wire
+) -> tuple[httpx.Response, bool]:
+    before: Final = wire.received.qsize()
+    response: Final = _post(gateway, body)
+    assert response.status_code == 200, response.text
+    return response, wire.received.qsize() > before
+
+
+def _until_served_from_cache(gateway: Gateway, body: Mapping[str, JsonValue], wire: Wire) -> tuple[httpx.Response, int]:
+    deadline: Final = time.monotonic() + 20
+    for attempt in itertools.count(1):
+        response, called_upstream = _post_noting_whether_upstream_was_called(gateway, body, wire)
+        if not called_upstream:
+            return response, attempt
+        assert time.monotonic() < deadline, "the response cache never served the repeated request"
+    raise AssertionError("unreachable")
+
+
+def test_the_response_cache_serves_the_repeated_request_without_an_upstream_call(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY)
+        body: Final = messages_body(model, marker, no_cache=False)
+        first: Final = _post(gateway, body)
+        _assert_answered(first, marker)
+        _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA)
+        _spend_row(f"msg_{marker}")
+        hit, attempts = _until_served_from_cache(gateway, body, wire)
+        assert hit.json()["id"] == first.json()["id"], hit.text
+        assert hit.json()["content"] == first.json()["content"], hit.text
+        _cache_hit_spend_row(f"msg_{marker}")
+        misses: Final = tuple(_observe(request) for request in wire.drain())
+        assert len(misses) == attempts - 1, (attempts, misses)
+        for observed in misses:
+            _expect_messages(observed, target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA)
diff --git a/tests/integration/providers/test_databricks_chat_wire.py b/tests/integration/providers/test_databricks_chat_wire.py
index 614382a77f0..3d7f273279f 100644
--- a/tests/integration/providers/test_databricks_chat_wire.py
+++ b/tests/integration/providers/test_databricks_chat_wire.py
@@ -1,17 +1,27 @@
+import itertools
 import json
 import uuid
 from collections.abc import Mapping
-from typing import Final
+from concurrent.futures import ThreadPoolExecutor
+from pathlib import Path
+from typing import Final, Literal, TypeAlias
 
+import anthropic
+import openai
 import pytest
 from integration._support.client import Gateway, eventually
 from integration._support.database import read_rows
+from integration._support.process import owned_proxy_process
 from integration._support.wire import Reply, Request, wire_server
 from pydantic import BaseModel, ConfigDict, JsonValue, TypeAdapter
 
 _BACKEND: Final = "databricks-glm-5-2"
 _API_KEY: Final = "synthetic-databricks-key"
 _PROMPT: Final = "Summarise the cached briefing in one sentence."
+_JSON_SCHEMA_BACKEND: Final = "databricks-qwen35-122b-a10b"
+_CLAUDE_BACKEND: Final = "databricks-claude-haiku-4-5"
+_JSON_SCHEMA_PROMPT: Final = "Return the requested JSON."
+_JSON_CONTENT: Final = '{"p":{"name":"Ada"}}'
 _PROVIDER_USAGE: Final[Mapping[str, JsonValue]] = {
     "prompt_tokens": 12011,
     "completion_tokens": 8,
@@ -20,6 +30,67 @@ _PROVIDER_USAGE: Final[Mapping[str, JsonValue]] = {
     "cache_creation_input_tokens": 0,
 }
 _JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue])
+_PERSON_SCHEMA: Final[Mapping[str, JsonValue]] = {
+    "$defs": {
+        "Person": {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+            "required": ["name"],
+        }
+    },
+    "type": "object",
+    "properties": {"p": {"$ref": "#/$defs/Person"}},
+    "required": ["p"],
+}
+_JSON_SCHEMA_RESPONSE_FORMAT: Final[Mapping[str, JsonValue]] = {
+    "type": "json_schema",
+    "json_schema": {"name": "P", "strict": True, "schema": _PERSON_SCHEMA},
+}
+_MESSAGES_PERSON_SCHEMA: Final[Mapping[str, JsonValue]] = {
+    "$defs": {
+        "Person": {
+            "type": "object",
+            "properties": {"name": {"type": "string"}},
+            "required": ["name"],
+            "additionalProperties": False,
+        }
+    },
+    "type": "object",
+    "properties": {"p": {"$ref": "#/$defs/Person"}},
+    "required": ["p"],
+    "additionalProperties": False,
+}
+_MESSAGES_RESPONSE_FORMAT: Final[Mapping[str, JsonValue]] = {
+    "type": "json_schema",
+    "json_schema": {
+        "name": "structured_output",
+        "schema": _MESSAGES_PERSON_SCHEMA,
+        "strict": True,
+    },
+}
+_JSON_TOOL_CALL_MESSAGE: Final[dict[str, JsonValue]] = {
+    "role": "assistant",
+    "content": None,
+    "tool_calls": [
+        {
+            "id": "json-tool-call",
+            "type": "function",
+            "function": {"name": "json_tool_call", "arguments": _JSON_CONTENT},
+        }
+    ],
+}
+
+
+def _chat_completion_response(model: str, message: dict[str, JsonValue], finish_reason: str) -> bytes:
+    response: Final = {
+        "id": "databricks-json-schema-response",
+        "object": "chat.completion",
+        "created": 1,
+        "model": model,
+        "choices": [{"index": 0, "message": message, "finish_reason": finish_reason}],
+        "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+    }
+    return json.dumps(response).encode()
 
 
 class _PromptTokensDetails(BaseModel):
@@ -52,12 +123,17 @@ class _Chunk(BaseModel):
     usage: _Usage | None = None
 
 
-def _frame(identity: str, choices: list[Mapping[str, object]], usage: Mapping[str, JsonValue] | None = None) -> bytes:
+def _frame(
+    identity: str,
+    choices: list[Mapping[str, object]],
+    usage: Mapping[str, JsonValue] | None = None,
+    model: str = _BACKEND,
+) -> bytes:
     value: Final = {
         "id": identity,
         "object": "chat.completion.chunk",
         "created": 1,
-        "model": _BACKEND,
+        "model": model,
         "choices": choices,
         **({} if usage is None else {"usage": usage}),
     }
@@ -127,3 +203,1245 @@ def test_databricks_stream_final_usage_chunk_reaches_client_and_spend_log(gatewa
             seconds=70,
         )
         assert (rows[0]["prompt_tokens"], rows[0]["completion_tokens"], rows[0]["total_tokens"]) == (12011, 8, 12019)
+
+
+def _shape_reply(identity: str, stream: bool) -> Reply:
+    if stream:
+        chunks: Final = (
+            _frame(
+                identity,
+                [{"index": 0, "delta": {"role": "assistant", "content": "ok"}, "finish_reason": None}],
+            ),
+            _frame(identity, [{"index": 0, "delta": {}, "finish_reason": "stop"}]),
+            b"data: [DONE]\n\n",
+        )
+        return Reply(content_type="text/event-stream", chunks=chunks)
+
+    body: Final = {
+        "id": identity,
+        "object": "chat.completion",
+        "created": 1,
+        "model": _BACKEND,
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": "ok"},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+    }
+    return Reply(body=json.dumps(body).encode())
+
+
+@pytest.mark.parametrize(
+    "case,endpoint,provider_model,request_body,expected_messages,responses_mode,upstream_path",
+    [
+        pytest.param(
+            "chat_nonstream",
+            "/v1/chat/completions",
+            "databricks-meta-llama-3-3-70b-instruct",
+            {
+                "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+                "response_format": {"type": "json_object"},
+            },
+            [{"role": "user", "content": "Reply in JSON"}],
+            False,
+            "/chat/completions",
+            id="A1-chat-nonstream",
+        ),
+        pytest.param(
+            "chat_stream",
+            "/v1/chat/completions",
+            "databricks-meta-llama-3-3-70b-instruct",
+            {
+                "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+                "response_format": {"type": "json_object"},
+                "stream": True,
+            },
+            [{"role": "user", "content": "Reply in JSON"}],
+            False,
+            "/chat/completions",
+            id="A2-chat-stream",
+        ),
+        pytest.param(
+            "responses-mode-bridge",
+            "/v1/chat/completions",
+            "databricks-meta-llama-3-1-8b-instruct",
+            {
+                "messages": [{"role": "user", "content": "Reply in JSON"}],
+                "response_format": {"type": "json_object"},
+            },
+            [{"role": "user", "content": "Reply in JSON"}],
+            True,
+            "/chat/completions",
+            id="A3-responses-mode",
+        ),
+        pytest.param(
+            "responses-mode-bridge-unity-catalog",
+            "/v1/chat/completions",
+            "system.ai.deepseek-v4-1-flash",
+            {
+                "messages": [{"role": "user", "content": "Reply in JSON with key a. hi"}],
+                "response_format": {"type": "json_object"},
+            },
+            [{"role": "user", "content": "Reply in JSON with key a. hi"}],
+            True,
+            "/ai-gateway/mlflow/v1/chat/completions",
+            id="A3b-responses-mode-unity-catalog-model",
+        ),
+        pytest.param(
+            "messages-endpoint",
+            "/v1/messages",
+            "databricks-meta-llama-3-3-70b-instruct",
+            {
+                "max_tokens": 32,
+                "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            },
+            [{"role": "user", "content": "Reply in JSON"}],
+            False,
+            "/chat/completions",
+            id="A4-messages",
+        ),
+        pytest.param(
+            "responses-endpoint",
+            "/v1/responses",
+            "databricks-meta-llama-3-3-70b-instruct",
+            {"input": [{"role": "user", "content": [{"type": "input_text", "text": "Reply in JSON"}]}]},
+            [{"role": "user", "content": "Reply in JSON"}],
+            False,
+            "/chat/completions",
+            id="A5-responses-list-input",
+        ),
+    ],
+)
+def test_databricks_non_claude_single_text_block_reaches_upstream_as_string(
+    gateway: Gateway,
+    case: str,
+    endpoint: str,
+    provider_model: str,
+    request_body: dict[str, JsonValue],
+    expected_messages: list[JsonValue],
+    responses_mode: bool,
+    upstream_path: str,
+) -> None:
+    identity: Final = f"databricks-single-text-{case}-{uuid.uuid4().hex}"
+    streaming: Final = request_body.get("stream") is True
+
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["messages"] == expected_messages, body["messages"]
+        return _shape_reply(identity, streaming)
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            model=f"databricks/{provider_model}",
+            api_base=wire.url,
+            api_key=_API_KEY,
+            model_info={"mode": "responses"} if responses_mode else None,
+        )
+        headers: Final = {"anthropic-version": "2023-06-01"} if endpoint == "/v1/messages" else {}
+        body: Final = {"model": model, **request_body}
+        if streaming:
+            with gateway.client.stream(
+                "POST", endpoint, json=body, headers={"Authorization": f"Bearer {gateway.key}", **headers}
+            ) as response:
+                assert response.status_code == 200, response.read()
+                lines: Final = tuple(line for line in response.iter_lines() if line.startswith("data: "))
+            assert lines[-1] == "data: [DONE]", lines
+            assert any('"content":"ok"' in line for line in lines), lines
+        else:
+            response: Final = gateway.request("POST", endpoint, body, headers=headers)
+            assert response.status_code == 200, response.text
+            assert _JSON_OBJECT.validate_json(response.content)["id"]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", upstream_path)]
+
+
+@pytest.mark.parametrize(
+    "case,provider_model,content,expected_content",
+    [
+        pytest.param(
+            "cache-control",
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}],
+            [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}],
+            id="B1-cache-control-stays-list",
+        ),
+        pytest.param(
+            "two-text-blocks",
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}],
+            [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}],
+            id="B2-two-text-blocks-stays-list",
+        ),
+        pytest.param(
+            "text-and-image",
+            "databricks-meta-llama-3-3-70b-instruct",
+            [
+                {"type": "text", "text": "Reply in JSON"},
+                {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}},
+            ],
+            [
+                {"type": "text", "text": "Reply in JSON"},
+                {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}},
+            ],
+            id="B3-text-and-image-stays-list",
+        ),
+        pytest.param(
+            "claude",
+            "databricks-claude-opus-5-5",
+            [{"type": "text", "text": "Reply in JSON"}],
+            [{"type": "text", "text": "Reply in JSON"}],
+            id="B4-claude-stays-list",
+        ),
+    ],
+)
+def test_databricks_list_content_stays_list(
+    gateway: Gateway,
+    case: str,
+    provider_model: str,
+    content: list[JsonValue],
+    expected_content: list[JsonValue],
+) -> None:
+    identity: Final = f"databricks-list-content-{case}-{uuid.uuid4().hex}"
+    expected_messages: Final = [{"role": "user", "content": expected_content}]
+
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["messages"] == expected_messages, body["messages"]
+        return _shape_reply(identity, False)
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{provider_model}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {"model": model, "messages": [{"role": "user", "content": content}]},
+        )
+        assert response.status_code == 200, response.text
+        assert _JSON_OBJECT.validate_json(response.content)["id"]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_json_schema_refs_are_preserved_in_chat_completions(gateway: Gateway) -> None:
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _JSON_SCHEMA_BACKEND
+        assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}]
+        assert body["stream"] is False
+        assert body["response_format"] == _JSON_SCHEMA_RESPONSE_FORMAT
+        return Reply(
+            body=_chat_completion_response(
+                _JSON_SCHEMA_BACKEND,
+                {"role": "assistant", "content": _JSON_CONTENT},
+                "stop",
+            )
+        )
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "response_format": _JSON_SCHEMA_RESPONSE_FORMAT,
+            },
+        )
+        assert response.status_code == 200, response.text
+        body: Final = _JSON_OBJECT.validate_json(response.content)
+        assert body["choices"] == [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": _JSON_CONTENT},
+                "finish_reason": "stop",
+            }
+        ]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_streaming_json_schema_refs_are_preserved(gateway: Gateway) -> None:
+    identity: Final = f"databricks-json-schema-stream-{uuid.uuid4().hex}"
+    frames: Final = (
+        _frame(
+            identity,
+            [{"index": 0, "delta": {"role": "assistant", "content": '{"p":'}, "finish_reason": None}],
+            model=_JSON_SCHEMA_BACKEND,
+        ),
+        _frame(
+            identity,
+            [{"index": 0, "delta": {"content": '{"name":"Ada"}}'}, "finish_reason": None}],
+            model=_JSON_SCHEMA_BACKEND,
+        ),
+        _frame(identity, [{"index": 0, "delta": {}, "finish_reason": "stop"}], model=_JSON_SCHEMA_BACKEND),
+        b"data: [DONE]\n\n",
+    )
+
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _JSON_SCHEMA_BACKEND
+        assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}]
+        assert body["stream"] is True
+        assert body["response_format"] == _JSON_SCHEMA_RESPONSE_FORMAT
+        return Reply(content_type="text/event-stream", chunks=frames)
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        with gateway.client.stream(
+            "POST",
+            "/v1/chat/completions",
+            json={
+                "model": model,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "response_format": _JSON_SCHEMA_RESPONSE_FORMAT,
+                "stream": True,
+            },
+            headers={"Authorization": f"Bearer {gateway.key}"},
+        ) as response:
+            assert response.status_code == 200, response.read()
+            lines: Final = tuple(line for line in response.iter_lines() if line.startswith("data: "))
+        assert lines[-1] == "data: [DONE]", lines
+        chunks: Final = tuple(_Chunk.model_validate_json(line.removeprefix("data: ")) for line in lines[:-1])
+        choices: Final = tuple(itertools.chain.from_iterable(chunk.choices for chunk in chunks))
+        assert "".join(choice.delta.content or "" for choice in choices) == _JSON_CONTENT
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_claude_json_schema_refs_are_preserved_in_tool_parameters(gateway: Gateway) -> None:
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _CLAUDE_BACKEND
+        assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}]
+        assert "response_format" not in body
+        assert body["tools"] == [
+            {
+                "type": "function",
+                "function": {"name": "json_tool_call", "parameters": _PERSON_SCHEMA},
+            }
+        ]
+        assert body["tool_choice"] == {"type": "function", "function": {"name": "json_tool_call"}}
+        return Reply(body=_chat_completion_response(_CLAUDE_BACKEND, _JSON_TOOL_CALL_MESSAGE, "tool_calls"))
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_CLAUDE_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "response_format": _JSON_SCHEMA_RESPONSE_FORMAT,
+            },
+        )
+        assert response.status_code == 200, response.text
+        body: Final = _JSON_OBJECT.validate_json(response.content)
+        assert body["choices"] == [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": _JSON_CONTENT},
+                "finish_reason": "stop",
+            }
+        ]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_responses_json_schema_refs_are_preserved_in_chat_bridge(gateway: Gateway) -> None:
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _JSON_SCHEMA_BACKEND
+        assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}]
+        assert body["response_format"] == {
+            "type": "json_schema",
+            "json_schema": {"name": "P", "schema": _PERSON_SCHEMA, "strict": True},
+        }
+        return Reply(
+            body=_chat_completion_response(
+                _JSON_SCHEMA_BACKEND,
+                {"role": "assistant", "content": _JSON_CONTENT},
+                "stop",
+            )
+        )
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/responses",
+            {
+                "model": model,
+                "input": _JSON_SCHEMA_PROMPT,
+                "text": {
+                    "format": {
+                        "type": "json_schema",
+                        "name": "P",
+                        "strict": True,
+                        "schema": _PERSON_SCHEMA,
+                    }
+                },
+            },
+        )
+        assert response.status_code == 200, response.text
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_messages_json_schema_refs_are_preserved_for_qwen(gateway: Gateway) -> None:
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _JSON_SCHEMA_BACKEND
+        assert body["response_format"] == _MESSAGES_RESPONSE_FORMAT
+        return Reply(
+            body=_chat_completion_response(
+                _JSON_SCHEMA_BACKEND,
+                {"role": "assistant", "content": _JSON_CONTENT},
+                "stop",
+            )
+        )
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/messages",
+            {
+                "model": model,
+                "max_tokens": 64,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "output_format": {"type": "json_schema", "schema": _PERSON_SCHEMA},
+            },
+        )
+        assert response.status_code == 200, response.text
+        body: Final = _JSON_OBJECT.validate_json(response.content)
+        assert body["content"] == [{"type": "text", "text": _JSON_CONTENT}]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+def test_databricks_messages_claude_json_schema_refs_are_preserved_in_tool_parameters(gateway: Gateway) -> None:
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST"
+        assert request.target == "/chat/completions"
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        assert body["model"] == _CLAUDE_BACKEND
+        assert "response_format" not in body
+        assert body["tools"] == [
+            {
+                "type": "function",
+                "function": {"name": "json_tool_call", "parameters": _MESSAGES_PERSON_SCHEMA},
+            }
+        ]
+        assert body["tool_choice"] == {"type": "function", "function": {"name": "json_tool_call"}}
+        return Reply(body=_chat_completion_response(_CLAUDE_BACKEND, _JSON_TOOL_CALL_MESSAGE, "tool_calls"))
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_CLAUDE_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/messages",
+            {
+                "model": model,
+                "max_tokens": 64,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "output_format": {"type": "json_schema", "schema": _PERSON_SCHEMA},
+            },
+        )
+        assert response.status_code == 200, response.text
+        body: Final = _JSON_OBJECT.validate_json(response.content)
+        assert body["content"] == [{"type": "text", "text": _JSON_CONTENT}]
+        assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")]
+
+
+_Endpoint: TypeAlias = Literal["chat", "responses", "messages"]
+_PATHS: Final[Mapping[_Endpoint, str]] = {
+    "chat": "/v1/chat/completions",
+    "responses": "/v1/responses",
+    "messages": "/v1/messages",
+}
+_OUTAGE: Final = "upstream-outage"
+_OUTAGE_MESSAGE: Final = "The service is temporarily unavailable"
+_EXPECTED_JSON: Final[JsonValue] = _JSON_OBJECT.validate_json(_JSON_CONTENT)
+_CONTENT_DELTAS: Final[tuple[Mapping[str, JsonValue], ...]] = (
+    {"role": "assistant", "content": '{"p":'},
+    {"content": '{"name":"Ada"}}'},
+)
+_TOOL_CALL_DELTAS: Final[tuple[Mapping[str, JsonValue], ...]] = (
+    {
+        "role": "assistant",
+        "content": None,
+        "tool_calls": [
+            {
+                "index": 0,
+                "id": "json-tool-call",
+                "type": "function",
+                "function": {"name": "json_tool_call", "arguments": ""},
+            }
+        ],
+    },
+    {"tool_calls": [{"index": 0, "function": {"arguments": _JSON_CONTENT}}]},
+)
+
+
+class _ChatMessage(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    content: str | None = None
+
+
+class _ChatChoice(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    message: _ChatMessage
+
+
+class _ChatCompletion(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    choices: tuple[_ChatChoice, ...]
+
+
+class _OutputPart(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str
+    text: str | None = None
+
+
+class _OutputItem(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str
+    content: tuple[_OutputPart, ...] = ()
+    name: str | None = None
+    arguments: str | None = None
+
+
+class _ResponsesBody(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    output: tuple[_OutputItem, ...]
+
+
+class _ResponsesEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str
+    response: _ResponsesBody | None = None
+
+
+class _MessagesBlock(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str
+    text: str | None = None
+
+
+class _MessagesBody(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    content: tuple[_MessagesBlock, ...]
+
+
+class _MessagesDelta(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str | None = None
+    text: str | None = None
+    partial_json: str | None = None
+
+
+class _MessagesEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    type: str
+    delta: _MessagesDelta | None = None
+
+
+class _FunctionDelta(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    arguments: str | None = None
+
+
+class _ToolCallDelta(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    function: _FunctionDelta | None = None
+
+
+class _StreamDelta(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    content: str | None = None
+    tool_calls: tuple[_ToolCallDelta, ...] | None = None
+
+
+class _StreamChoice(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    delta: _StreamDelta
+
+
+class _StreamChunk(BaseModel):
+    model_config = ConfigDict(extra="ignore", frozen=True)
+    choices: tuple[_StreamChoice, ...]
+
+
+def _json_schema_format(schema: Mapping[str, JsonValue]) -> dict[str, JsonValue]:
+    return {"type": "json_schema", "json_schema": {"name": "P", "strict": True, "schema": dict(schema)}}
+
+
+def _client_body(
+    endpoint: _Endpoint,
+    model: str,
+    stream: bool,
+    prompt: str = _JSON_SCHEMA_PROMPT,
+) -> dict[str, JsonValue]:
+    match endpoint:
+        case "chat":
+            return {
+                "model": model,
+                "messages": [{"role": "user", "content": prompt}],
+                "response_format": _json_schema_format(_PERSON_SCHEMA),
+                "stream": stream,
+            }
+        case "responses":
+            return {
+                "model": model,
+                "input": prompt,
+                "text": {
+                    "format": {"type": "json_schema", "name": "P", "strict": True, "schema": dict(_PERSON_SCHEMA)}
+                },
+                "stream": stream,
+            }
+        case "messages":
+            return {
+                "model": model,
+                "max_tokens": 64,
+                "messages": [{"role": "user", "content": prompt}],
+                "output_format": {"type": "json_schema", "schema": dict(_PERSON_SCHEMA)},
+                "stream": stream,
+            }
+
+
+def _expected_outbound(endpoint: _Endpoint, backend: str) -> dict[str, JsonValue]:
+    schema: Final = dict(_MESSAGES_PERSON_SCHEMA if endpoint == "messages" else _PERSON_SCHEMA)
+    if "claude" in backend:
+        return _JSON_OBJECT.validate_python(
+            {
+                "tools": [{"type": "function", "function": {"name": "json_tool_call", "parameters": schema}}],
+                "tool_choice": {"type": "function", "function": {"name": "json_tool_call"}},
+            }
+        )
+    name: Final = "structured_output" if endpoint == "messages" else "P"
+    return _JSON_OBJECT.validate_python(
+        {"response_format": {"type": "json_schema", "json_schema": {"name": name, "schema": schema, "strict": True}}}
+    )
+
+
+def _assert_outbound(request: Request, endpoint: _Endpoint, backend: str, stream: bool) -> None:
+    assert (request.method, request.target) == ("POST", "/chat/completions")
+    body: Final = _JSON_OBJECT.validate_json(request.body)
+    expected: Final = _expected_outbound(endpoint, backend)
+    assert {key: body.get(key) for key in expected} == expected
+    assert (body["model"], body.get("stream") is True) == (backend, stream)
+    assert "claude" not in backend or "response_format" not in body
+
+
+def _upstream_reply(backend: str, stream: bool) -> Reply:
+    claude: Final = "claude" in backend
+    finish_reason: Final = "tool_calls" if claude else "stop"
+    if not stream:
+        message: Final[dict[str, JsonValue]] = (
+            _JSON_TOOL_CALL_MESSAGE if claude else {"role": "assistant", "content": _JSON_CONTENT}
+        )
+        return Reply(body=_chat_completion_response(backend, message, finish_reason))
+    identity: Final = f"databricks-json-schema-{uuid.uuid4().hex}"
+    deltas: Final = _TOOL_CALL_DELTAS if claude else _CONTENT_DELTAS
+    frames: Final = (
+        *(_frame(identity, [{"index": 0, "delta": delta, "finish_reason": None}], model=backend) for delta in deltas),
+        _frame(identity, [{"index": 0, "delta": {}, "finish_reason": finish_reason}], model=backend),
+        b"data: [DONE]\n\n",
+    )
+    return Reply(content_type="text/event-stream", chunks=frames)
+
+
+def _outage_or_reply(request: Request) -> Reply:
+    if _OUTAGE.encode() in request.body:
+        error: Final = {"error_code": "TEMPORARILY_UNAVAILABLE", "message": _OUTAGE_MESSAGE}
+        return Reply(status=503, body=json.dumps(error).encode())
+    body: Final = _JSON_OBJECT.validate_json(request.body)
+    return _upstream_reply(str(body["model"]), body.get("stream") is True)
+
+
+def _item_text(item: _OutputItem) -> str:
+    match item.type:
+        case "message":
+            return "".join(part.text or "" for part in item.content)
+        case "function_call" if item.name == "json_tool_call":
+            return item.arguments or ""
+        case _:
+            return ""
+
+
+def _responses_text(body: _ResponsesBody) -> str:
+    return "".join(_item_text(item) for item in body.output)
+
+
+def _chat_delta_text(delta: _StreamDelta) -> str:
+    calls: Final = delta.tool_calls or ()
+    return (delta.content or "") + "".join(call.function.arguments or "" for call in calls if call.function is not None)
+
+
+def _messages_delta_text(delta: _MessagesDelta) -> str:
+    match delta.type:
+        case "text_delta":
+            return delta.text or ""
+        case "input_json_delta":
+            return delta.partial_json or ""
+        case _:
+            return ""
+
+
+def _final_text(endpoint: _Endpoint, content: bytes) -> str:
+    match endpoint:
+        case "chat":
+            return _ChatCompletion.model_validate_json(content).choices[0].message.content or ""
+        case "responses":
+            return _responses_text(_ResponsesBody.model_validate_json(content))
+        case "messages":
+            return "".join(block.text or "" for block in _MessagesBody.model_validate_json(content).content)
+
+
+def _streamed_text(endpoint: _Endpoint, data: tuple[str, ...]) -> str:
+    match endpoint:
+        case "chat":
+            assert data[-1] == "[DONE]", data
+            chunks: Final = tuple(_StreamChunk.model_validate_json(line) for line in data[:-1])
+            choices: Final = tuple(itertools.chain.from_iterable(chunk.choices for chunk in chunks))
+            return "".join(_chat_delta_text(choice.delta) for choice in choices)
+        case "responses":
+            events: Final = tuple(_ResponsesEvent.model_validate_json(line) for line in data if line != "[DONE]")
+            completed: Final = tuple(event.response for event in events if event.type == "response.completed")
+            assert len(completed) == 1 and completed[0] is not None, data
+            return _responses_text(completed[0])
+        case "messages":
+            message_events: Final = tuple(_MessagesEvent.model_validate_json(line) for line in data)
+            assert message_events[-1].type == "message_stop", data
+            deltas: Final = tuple(event.delta for event in message_events if event.delta is not None)
+            return "".join(_messages_delta_text(delta) for delta in deltas)
+
+
+def _outcome(status: int, text: str) -> tuple[int, JsonValue]:
+    if status == 200:
+        return status, _JSON_OBJECT.validate_json(text)
+    return status, _OUTAGE_MESSAGE if _OUTAGE_MESSAGE in text else text
+
+
+def _call(gateway: Gateway, endpoint: _Endpoint, body: Mapping[str, JsonValue]) -> tuple[int, str]:
+    if body["stream"] is not True:
+        response: Final = gateway.request("POST", _PATHS[endpoint], body)
+        return response.status_code, _final_text(endpoint, response.content) if response.is_success else response.text
+    with gateway.client.stream(
+        "POST", _PATHS[endpoint], json=dict(body), headers={"Authorization": f"Bearer {gateway.key}"}
+    ) as streamed:
+        if not streamed.is_success:
+            return streamed.status_code, streamed.read().decode()
+        data: Final = tuple(line.removeprefix("data: ") for line in streamed.iter_lines() if line.startswith("data: "))
+    return 200, _streamed_text(endpoint, data)
+
+
+@pytest.mark.parametrize(
+    ("endpoint", "backend", "stream"),
+    [
+        pytest.param("chat", _CLAUDE_BACKEND, True, id="chat-stream-claude"),
+        pytest.param("responses", _CLAUDE_BACKEND, False, id="responses-claude"),
+        pytest.param("responses", _JSON_SCHEMA_BACKEND, True, id="responses-stream-qwen"),
+        pytest.param("responses", _CLAUDE_BACKEND, True, id="responses-stream-claude"),
+        pytest.param("messages", _JSON_SCHEMA_BACKEND, True, id="messages-stream-qwen"),
+        pytest.param("messages", _CLAUDE_BACKEND, True, id="messages-stream-claude"),
+    ],
+)
+def test_databricks_json_schema_refs_are_preserved_on_every_endpoint(
+    gateway: Gateway, endpoint: _Endpoint, backend: str, stream: bool
+) -> None:
+    with wire_server(lambda _request: _upstream_reply(backend, stream)) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{backend}", api_base=wire.url, api_key=_API_KEY)
+        status, text = _call(gateway, endpoint, _client_body(endpoint, model, stream))
+        received: Final = wire.drain()
+    assert len(received) == 1, received
+    _assert_outbound(received[0], endpoint, backend, stream)
+    assert _outcome(status, text) == (200, _EXPECTED_JSON), text
+
+
+@pytest.mark.parametrize(
+    "response_format",
+    [
+        pytest.param(
+            _json_schema_format(
+                {
+                    "definitions": {
+                        "Person": {"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]}
+                    },
+                    "type": "object",
+                    "properties": {"p": {"$ref": "#/definitions/Person"}},
+                    "required": ["p"],
+                }
+            ),
+            id="definitions-ref",
+        ),
+        pytest.param(
+            _json_schema_format(
+                {
+                    "type": "object",
+                    "properties": {
+                        "name": {"type": "string"},
+                        "children": {"type": "array", "items": {"$ref": "#"}},
+                    },
+                    "required": ["name", "children"],
+                }
+            ),
+            id="recursive-root-ref",
+        ),
+        pytest.param(
+            _json_schema_format({"type": "object", "properties": {"$ref": {"type": "string"}}, "required": ["$ref"]}),
+            id="property-named-ref",
+        ),
+        pytest.param(
+            _json_schema_format({"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]}),
+            id="flat-schema",
+        ),
+        pytest.param({"type": "json_object"}, id="json-object"),
+    ],
+)
+def test_databricks_response_format_reaches_upstream_as_sent(
+    gateway: Gateway, response_format: dict[str, JsonValue]
+) -> None:
+    with (
+        wire_server(lambda _request: _upstream_reply(_JSON_SCHEMA_BACKEND, False)) as wire,
+        gateway.scenario() as scenario,
+    ):
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "response_format": response_format,
+            },
+        )
+        received: Final = wire.drain()
+    assert response.status_code == 200, response.text
+    assert _final_text("chat", response.content) == _JSON_CONTENT
+    assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")]
+    assert _JSON_OBJECT.validate_json(received[0].body)["response_format"] == response_format
+
+
+def test_databricks_json_schema_without_schema_returns_the_upstream_error(gateway: Gateway) -> None:
+    response_format: Final[dict[str, JsonValue]] = {"type": "json_schema", "json_schema": {"name": "P", "strict": True}}
+    upstream_error: Final = {"error_code": "INVALID_PARAMETER_VALUE", "message": "json_schema.schema is required"}
+
+    def respond(_request: Request) -> Reply:
+        return Reply(status=400, body=json.dumps(upstream_error).encode())
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}],
+                "response_format": response_format,
+            },
+        )
+        received: Final = wire.drain()
+    assert (response.status_code, "json_schema.schema is required" in response.text) == (400, True), response.text
+    assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")]
+    assert _JSON_OBJECT.validate_json(received[0].body)["response_format"] == response_format
+
+
+def _assert_burst_outbound(request: Request) -> None:
+    body: Final = _JSON_OBJECT.validate_json(request.body)
+    endpoint: Final[_Endpoint] = "messages" if body["response_format"] == _MESSAGES_RESPONSE_FORMAT else "chat"
+    _assert_outbound(request, endpoint, _JSON_SCHEMA_BACKEND, body.get("stream") is True)
+
+
+def _burst_request(index: int) -> tuple[_Endpoint, bool, bool]:
+    endpoints: Final[tuple[_Endpoint, ...]] = ("chat", "responses", "messages")
+    return endpoints[index % 3], index % 2 == 1, index % 5 == 2
+
+
+def test_databricks_json_schema_burst_through_an_upstream_outage_keeps_every_ref(gateway: Gateway) -> None:
+    plan: Final = tuple(_burst_request(index) for index in range(24))
+    recovery: Final[tuple[_Endpoint, ...]] = ("chat", "responses", "messages")
+    with wire_server(_outage_or_reply) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        endpoints: Final = tuple(endpoint for endpoint, _stream, _down in plan)
+        bodies: Final = tuple(
+            _client_body(endpoint, model, stream, f"{_JSON_SCHEMA_PROMPT} {index} {_OUTAGE if down else ''}")
+            for index, (endpoint, stream, down) in enumerate(plan)
+        )
+        with ThreadPoolExecutor(max_workers=12) as pool:
+            results: Final = tuple(pool.map(_call, itertools.repeat(gateway), endpoints, bodies))
+        recovered: Final = tuple(
+            _call(gateway, endpoint, _client_body(endpoint, model, False)) for endpoint in recovery
+        )
+        received: Final = wire.drain()
+    assert len(received) == len(plan) + len(recovery), received
+    for request in received:
+        _assert_burst_outbound(request)
+    expected: Final = tuple(
+        (503, _OUTAGE_MESSAGE) if down else (200, _EXPECTED_JSON) for _endpoint, _stream, down in plan
+    )
+    assert tuple(_outcome(*result) for result in results) == expected
+    assert tuple(_outcome(*result) for result in recovered) == ((200, _EXPECTED_JSON),) * len(recovery)
+
+
+_LLAMA_BACKEND: Final = "databricks-meta-llama-3-3-70b-instruct"
+_NO_CACHE: Final[dict[str, JsonValue]] = {"no-cache": True}
+
+
+def _one_block(text: str) -> list[JsonValue]:
+    return [{"type": "text", "text": text}]
+
+
+def _plain_reply(_request: Request) -> Reply:
+    return _shape_reply(f"databricks-plain-{uuid.uuid4().hex}", False)
+
+
+def _sent_messages(request: Request) -> JsonValue:
+    return _JSON_OBJECT.validate_json(request.body)["messages"]
+
+
+def _tool_call(identity: str, city: str) -> dict[str, JsonValue]:
+    return {
+        "id": identity,
+        "type": "function",
+        "function": {"name": "get_weather", "arguments": json.dumps({"city": city})},
+    }
+
+
+@pytest.mark.parametrize(
+    "messages,expected_messages",
+    [
+        pytest.param(
+            [
+                {"role": "system", "content": _one_block("Alpha rule.")},
+                {"role": "system", "content": _one_block("Bravo rule.")},
+                {"role": "user", "content": _one_block("Reply in JSON")},
+            ],
+            [
+                {"role": "system", "content": "Alpha rule.\n\nBravo rule."},
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            id="C1-two-one-block-system-messages",
+        ),
+        pytest.param(
+            [
+                {"role": "system", "content": _one_block("Alpha rule.")},
+                {"role": "developer", "content": _one_block("Bravo rule.")},
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            [
+                {"role": "system", "content": "Alpha rule.\n\nBravo rule."},
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            id="C2-system-then-developer-one-block",
+        ),
+        pytest.param(
+            [
+                {"role": "system", "content": _one_block("Alpha rule.")},
+                {"role": "system", "content": "Bravo rule."},
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            [
+                {"role": "system", "content": "Alpha rule.\n\nBravo rule."},
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            id="C3-one-block-then-string-system",
+        ),
+        pytest.param(
+            [
+                {"role": "system", "content": _one_block("Alpha rule.")},
+                {
+                    "role": "system",
+                    "content": [{"type": "text", "text": "Bravo", "cache_control": {"type": "ephemeral"}}],
+                },
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            [
+                {
+                    "role": "system",
+                    "content": [
+                        {"type": "text", "text": "Alpha rule."},
+                        {"type": "text", "text": "Bravo", "cache_control": {"type": "ephemeral"}},
+                    ],
+                },
+                {"role": "user", "content": "Reply in JSON"},
+            ],
+            id="C4-one-block-then-cache-marked-system-stays-parts",
+        ),
+        pytest.param(
+            [
+                {"role": "user", "content": _one_block("Weather in Paris and Rome?")},
+                {
+                    "role": "assistant",
+                    "content": _one_block("Checking both."),
+                    "tool_calls": [_tool_call("call-paris", "Paris"), _tool_call("call-rome", "Rome")],
+                },
+                {"role": "tool", "tool_call_id": "call-paris", "content": _one_block("18C")},
+                {"role": "tool", "tool_call_id": "call-rome", "content": _one_block("22C")},
+            ],
+            [
+                {"role": "user", "content": "Weather in Paris and Rome?"},
+                {"role": "assistant", "content": "Checking both.", "tool_calls": [_tool_call("call-paris", "Paris")]},
+                {"role": "tool", "tool_call_id": "call-paris", "content": "18C"},
+                {"role": "assistant", "tool_calls": [_tool_call("call-rome", "Rome")]},
+                {"role": "tool", "tool_call_id": "call-rome", "content": "22C"},
+            ],
+            id="C5-parallel-tool-results-split-and-collapsed",
+        ),
+        pytest.param(
+            [
+                {"role": "user", "content": [{"type": "text", "text": "Reply in JSON", "cache_control": None}]},
+                {"role": "assistant", "content": [{"type": "text", "text": "ok", "annotations": []}]},
+                {"role": "user", "content": _one_block("   ")},
+                {"role": "user", "content": _one_block("x" * 5120)},
+            ],
+            [
+                {"role": "user", "content": [{"type": "text", "text": "Reply in JSON", "cache_control": None}]},
+                {"role": "assistant", "content": [{"type": "text", "text": "ok", "annotations": []}]},
+                {"role": "user"},
+                {"role": "user", "content": "x" * 5120},
+            ],
+            id="F1-extra-keys-stay-list-blank-dropped-5kb-collapsed",
+        ),
+    ],
+)
+def test_databricks_non_claude_message_shapes_reach_upstream(
+    gateway: Gateway, messages: list[JsonValue], expected_messages: list[JsonValue]
+) -> None:
+    with wire_server(_plain_reply) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {"model": model, "messages": messages, "cache": _NO_CACHE},
+        )
+        received: Final = wire.drain()
+    assert response.status_code == 200, response.text
+    assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")]
+    assert _sent_messages(received[0]) == expected_messages
+
+
+def test_databricks_responses_instructions_and_one_block_developer_reach_upstream_joined(gateway: Gateway) -> None:
+    with wire_server(_plain_reply) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/responses",
+            {
+                "model": model,
+                "instructions": "Alpha rule.",
+                "input": [
+                    {"role": "developer", "content": [{"type": "input_text", "text": "Bravo rule."}]},
+                    {"role": "user", "content": [{"type": "input_text", "text": "Reply in JSON"}]},
+                ],
+            },
+        )
+        received: Final = wire.drain()
+    assert response.status_code == 200, response.text
+    assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")]
+    assert _sent_messages(received[0]) == [
+        {"role": "system", "content": "Alpha rule.\n\nBravo rule."},
+        {"role": "user", "content": "Reply in JSON"},
+    ]
+
+
+def test_databricks_fallback_sends_the_collapsed_string_to_both_deployments(gateway: Gateway) -> None:
+    marker: Final = uuid.uuid4().hex
+    fallback_backend: Final = "databricks-meta-llama-3-1-8b-instruct"
+
+    def respond(request: Request) -> Reply:
+        if _JSON_OBJECT.validate_json(request.body)["model"] == _LLAMA_BACKEND:
+            return Reply(status=500, body=b'{"error_code": "INTERNAL_ERROR", "message": "primary deployment is down"}')
+        return _shape_reply(f"databricks-fallback-{marker}", False)
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        primary: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        fallback: Final = scenario.model(model=f"databricks/{fallback_backend}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": primary,
+                "messages": [{"role": "user", "content": _one_block(f"Reply in JSON {marker}")}],
+                "response_format": {"type": "json_object"},
+                "fallbacks": [fallback],
+                "num_retries": 0,
+                "cache": _NO_CACHE,
+            },
+        )
+        received: Final = wire.drain()
+    assert response.status_code == 200, response.text
+    assert _JSON_OBJECT.validate_json(response.content)["id"] == f"databricks-fallback-{marker}"
+    assert [_JSON_OBJECT.validate_json(request.body)["model"] for request in received] == [
+        _LLAMA_BACKEND,
+        fallback_backend,
+    ]
+    assert [_sent_messages(request) for request in received] == [
+        [{"role": "user", "content": f"Reply in JSON {marker}"}],
+    ] * 2
+
+
+def _proxy_root(gateway: Gateway) -> str:
+    return str(gateway.client.base_url).rstrip("/")
+
+
+def test_databricks_openai_sdk_sync_one_block_reaches_upstream_as_string_and_logs_spend(gateway: Gateway) -> None:
+    identity: Final = f"databricks-openai-sdk-{uuid.uuid4().hex}"
+    with (
+        wire_server(lambda _request: _shape_reply(identity, False)) as wire,
+        gateway.scenario() as scenario,
+        openai.OpenAI(base_url=f"{_proxy_root(gateway)}/v1", api_key=gateway.key, max_retries=0) as client,
+    ):
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        completion: Final = client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            response_format={"type": "json_object"},
+            extra_body={"cache": _NO_CACHE},
+        )
+        received: Final = wire.drain()
+    assert (completion.id, completion.choices[0].message.content) == (identity, "ok")
+    assert [_sent_messages(request) for request in received] == [[{"role": "user", "content": "Reply in JSON"}]]
+    rows: Final = eventually(
+        lambda: read_rows('SELECT status, call_type FROM "LiteLLM_SpendLogs" WHERE request_id=%s', (identity,)),
+        lambda values: len(values) == 1,
+        seconds=70,
+    )
+    assert (rows[0]["status"], rows[0]["call_type"]) == ("success", "acompletion")
+
+
+async def test_databricks_openai_sdk_async_stream_one_block_reaches_upstream_as_string(gateway: Gateway) -> None:
+    identity: Final = f"databricks-openai-async-{uuid.uuid4().hex}"
+    with wire_server(lambda _request: _shape_reply(identity, True)) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        async with openai.AsyncOpenAI(
+            base_url=f"{_proxy_root(gateway)}/v1", api_key=gateway.key, max_retries=0
+        ) as client:
+            stream: Final = await client.chat.completions.create(
+                model=model,
+                messages=[{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+                response_format={"type": "json_object"},
+                stream=True,
+                extra_body={"cache": _NO_CACHE},
+            )
+            chunks: Final = [chunk async for chunk in stream]
+        received: Final = wire.drain()
+    assert {chunk.id for chunk in chunks} == {identity}
+    assert "".join(chunk.choices[0].delta.content or "" for chunk in chunks if chunk.choices) == "ok"
+    assert [_sent_messages(request) for request in received] == [[{"role": "user", "content": "Reply in JSON"}]]
+
+
+async def test_databricks_anthropic_sdk_async_stream_one_block_system_and_user_reach_upstream_as_strings(
+    gateway: Gateway,
+) -> None:
+    identity: Final = f"databricks-anthropic-async-{uuid.uuid4().hex}"
+    with wire_server(lambda _request: _shape_reply(identity, True)) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        async with anthropic.AsyncAnthropic(
+            base_url=_proxy_root(gateway), api_key=gateway.key, max_retries=0
+        ) as client:
+            async with client.messages.stream(
+                model=model,
+                max_tokens=32,
+                system=[{"type": "text", "text": "Reply in JSON."}],
+                messages=[{"role": "user", "content": [{"type": "text", "text": "What is 2+2?"}]}],
+            ) as stream:
+                final: Final = await stream.get_final_message()
+        received: Final = wire.drain()
+    assert [block.text for block in final.content if block.type == "text"] == ["ok"]
+    assert [_sent_messages(request) for request in received] == [
+        [{"role": "system", "content": "Reply in JSON."}, {"role": "user", "content": "What is 2+2?"}]
+    ]
+
+
+def test_databricks_one_block_burst_through_an_upstream_outage_reaches_upstream_as_strings(gateway: Gateway) -> None:
+    plan: Final = tuple(_burst_request(index) for index in range(24))
+
+    def respond(request: Request) -> Reply:
+        if _OUTAGE.encode() in request.body:
+            error: Final = {"error_code": "TEMPORARILY_UNAVAILABLE", "message": _OUTAGE_MESSAGE}
+            return Reply(status=503, body=json.dumps(error).encode())
+        body: Final = _JSON_OBJECT.validate_json(request.body)
+        return _upstream_reply(_JSON_SCHEMA_BACKEND, body.get("stream") is True)
+
+    def one_block_body(endpoint: _Endpoint, model: str, stream: bool, prompt: str) -> dict[str, JsonValue]:
+        body: Final = _client_body(endpoint, model, stream, prompt)
+        match endpoint:
+            case "responses":
+                return {**body, "input": [{"role": "user", "content": [{"type": "input_text", "text": prompt}]}]}
+            case "chat" | "messages":
+                return {**body, "messages": [{"role": "user", "content": _one_block(prompt)}]}
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        prompts: Final = tuple(
+            f"{_JSON_SCHEMA_PROMPT} {index} {_OUTAGE if down else ''}".strip()
+            for index, (_e, _s, down) in enumerate(plan)
+        )
+        bodies: Final = tuple(
+            one_block_body(endpoint, model, stream, prompt) for (endpoint, stream, _down), prompt in zip(plan, prompts)
+        )
+        with ThreadPoolExecutor(max_workers=12) as pool:
+            results: Final = tuple(pool.map(_call, itertools.repeat(gateway), (e for e, _s, _d in plan), bodies))
+        received: Final = wire.drain()
+    assert sorted(json.dumps(_sent_messages(request)) for request in received) == sorted(
+        json.dumps([{"role": "user", "content": prompt}]) for prompt in prompts
+    )
+    expected: Final = tuple(
+        (503, _OUTAGE_MESSAGE) if down else (200, _EXPECTED_JSON) for _endpoint, _stream, down in plan
+    )
+    assert tuple(_outcome(*result) for result in results) == expected
+
+
+def test_databricks_transform_request_shows_the_collapsed_string(gateway: Gateway, tmp_path: Path) -> None:
+    environment: Final = {
+        "DATABRICKS_API_BASE": "https://databricks.invalid/serving-endpoints",
+        "DATABRICKS_API_KEY": _API_KEY,
+    }
+    with owned_proxy_process(gateway, tmp_path, environment) as owned:
+        response: Final = owned.gateway.request(
+            "POST",
+            "/utils/transform_request",
+            {
+                "call_type": "completion",
+                "request_body": {
+                    "model": f"databricks/{_LLAMA_BACKEND}",
+                    "messages": [{"role": "user", "content": _one_block("Reply in JSON")}],
+                },
+            },
+        )
+    assert response.status_code == 200, response.text
+    body: Final = _JSON_OBJECT.validate_json(response.content)
+    assert body["error"] is None, body
+    assert body["raw_request_api_base"] == "https://databricks.invalid/serving-endpoints/chat/completions"
+    sent: Final = body["raw_request_body"]
+    assert isinstance(sent, dict), body
+    assert sent["messages"] == [{"role": "user", "content": "Reply in JSON"}]
+
+
+def test_databricks_non_string_text_block_is_rejected_before_reaching_upstream(gateway: Gateway) -> None:
+    with wire_server(_plain_reply) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY)
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": [{"type": "text", "text": 42}]}],
+                "cache": _NO_CACHE,
+            },
+        )
+        received: Final = wire.drain()
+    assert response.status_code == 400, response.text
+    assert "'int' object has no attribute 'strip'" in response.text
+    assert received == ()
diff --git a/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py b/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py
new file mode 100644
index 00000000000..009679fa4b5
--- /dev/null
+++ b/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py
@@ -0,0 +1,186 @@
+import json
+import uuid
+from collections.abc import Iterator, Mapping
+from typing import Final
+
+import pytest
+from integration._support.wire import Reply, Request, wire_server
+from pydantic import BaseModel, ConfigDict, Field, JsonValue
+
+import litellm
+
+_QWEN_BACKEND: Final = "databricks-qwen35-122b-a10b"
+_CLAUDE_BACKEND: Final = "databricks-claude-haiku-4-5"
+_API_KEY: Final = "synthetic-databricks-key"
+_ORDER_JSON: Final = '{"buyer":{"name":"Ada"},"seller":{"name":"Bo"}}'
+_MESSAGES: Final[tuple[Mapping[str, str], ...]] = ({"role": "user", "content": "Return the order as JSON."},)
+
+
+class Person(BaseModel):
+    model_config = ConfigDict(frozen=True)
+    name: str
+
+
+class Order(BaseModel):
+    model_config = ConfigDict(frozen=True)
+    buyer: Person
+    seller: Person
+
+
+class _StrictObject(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    additional_properties: bool | None = Field(default=None, alias="additionalProperties")
+
+
+class _OrderSchema(_StrictObject):
+    defs: Mapping[str, _StrictObject] = Field(alias="$defs")
+
+
+class _JsonSchema(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    name: str
+    strict: bool | None = None
+    json_schema: dict[str, JsonValue] = Field(alias="schema")
+
+
+class _ResponseFormat(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    type: str
+    json_schema: _JsonSchema
+
+
+class _Function(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    name: str
+    parameters: dict[str, JsonValue]
+
+
+class _Tool(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    function: _Function
+
+
+class _Outbound(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    model: str
+    response_format: _ResponseFormat | None = None
+    tools: tuple[_Tool, ...] = ()
+
+
+class _CallerMessage(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    content: str
+
+
+class _CallerChoice(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    message: _CallerMessage
+
+
+class _CallerCompletion(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="ignore")
+    choices: tuple[_CallerChoice, ...]
+
+
+def _completion(backend: str) -> Reply:
+    claude: Final = "claude" in backend
+    tool_call: Final[dict[str, JsonValue]] = {
+        "id": "json-tool-call",
+        "type": "function",
+        "function": {"name": "json_tool_call", "arguments": _ORDER_JSON},
+    }
+    message: Final[dict[str, JsonValue]] = (
+        {"role": "assistant", "content": None, "tool_calls": [tool_call]}
+        if claude
+        else {"role": "assistant", "content": _ORDER_JSON}
+    )
+    body: Final[dict[str, JsonValue]] = {
+        "id": f"chatcmpl-{uuid.uuid4().hex}",
+        "object": "chat.completion",
+        "created": 1,
+        "model": backend,
+        "choices": [{"index": 0, "message": message, "finish_reason": "tool_calls" if claude else "stop"}],
+        "usage": {"prompt_tokens": 9, "completion_tokens": 7, "total_tokens": 16},
+    }
+    return Reply(body=json.dumps(body).encode())
+
+
+def _refs(node: JsonValue) -> Iterator[str]:
+    if isinstance(node, list):
+        for item in node:
+            yield from _refs(item)
+        return
+    if not isinstance(node, dict):
+        return
+    for key, value in node.items():
+        if key == "$ref" and isinstance(value, str):
+            yield value
+        else:
+            yield from _refs(value)
+
+
+def _sent_schema(backend: str, received: tuple[Request, ...]) -> dict[str, JsonValue]:
+    assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")]
+    outbound: Final = _Outbound.model_validate_json(received[0].body)
+    assert outbound.model == backend
+    if "claude" in backend:
+        assert outbound.response_format is None
+        assert [tool.function.name for tool in outbound.tools] == ["json_tool_call"]
+        return outbound.tools[0].function.parameters
+    assert outbound.response_format is not None
+    assert (outbound.response_format.type, outbound.response_format.json_schema.name) == ("json_schema", "Order")
+    assert outbound.response_format.json_schema.strict is True
+    return outbound.response_format.json_schema.json_schema
+
+
+def _assert_strict_order_schema(schema: dict[str, JsonValue]) -> None:
+    assert set(_refs(schema)) == {"#/$defs/Person"}, schema
+    parsed: Final = _OrderSchema.model_validate(schema)
+    assert (parsed.additional_properties, parsed.defs["Person"].additional_properties) == (False, False), schema
+
+
+def _caller_order(response: litellm.ModelResponse) -> Order:
+    return Order.model_validate_json(
+        _CallerCompletion.model_validate_json(response.model_dump_json()).choices[0].message.content
+    )
+
+
+_BACKENDS: Final = (
+    pytest.param(_QWEN_BACKEND, id="qwen"),
+    pytest.param(_CLAUDE_BACKEND, id="claude"),
+)
+_EXPECTED_ORDER: Final = Order(buyer=Person(name="Ada"), seller=Person(name="Bo"))
+
+
+@pytest.mark.parametrize("backend", _BACKENDS)
+def test_databricks_pydantic_response_format_sends_strict_defs_refs(backend: str) -> None:
+    with wire_server(lambda _request: _completion(backend)) as wire:
+        response: Final = litellm.completion(
+            model=f"databricks/{backend}",
+            api_base=wire.url,
+            api_key=_API_KEY,
+            messages=[dict(message) for message in _MESSAGES],
+            response_format=Order,
+            num_retries=0,
+        )
+        received: Final = wire.drain()
+    _assert_strict_order_schema(_sent_schema(backend, received))
+    assert isinstance(response, litellm.ModelResponse)
+    assert _caller_order(response) == _EXPECTED_ORDER
+
+
+@pytest.mark.parametrize("backend", _BACKENDS)
+async def test_databricks_pydantic_response_format_sends_strict_defs_refs_async(backend: str) -> None:
+    with wire_server(lambda _request: _completion(backend)) as wire:
+        response: Final = await litellm.acompletion(
+            model=f"databricks/{backend}",
+            api_base=wire.url,
+            api_key=_API_KEY,
+            messages=[dict(message) for message in _MESSAGES],
+            response_format=Order,
+            num_retries=0,
+        )
+        received: Final = wire.drain()
+    _assert_strict_order_schema(_sent_schema(backend, received))
+    assert isinstance(response, litellm.ModelResponse)
+    assert _caller_order(response) == _EXPECTED_ORDER
diff --git a/tests/integration/spend/test_batch_poll_starvation.py b/tests/integration/spend/test_batch_poll_starvation.py
index f68f10e3d8a..51f5f0871f5 100644
--- a/tests/integration/spend/test_batch_poll_starvation.py
+++ b/tests/integration/spend/test_batch_poll_starvation.py
@@ -1,14 +1,20 @@
 import json
 import os
+from datetime import datetime, timezone
+from functools import partial
 from hashlib import sha256
+from itertools import chain
 from typing import Final
+from uuid import uuid4
 
+import httpx
 import pytest
 from integration._support.client import JSON_OBJECT, Gateway, Scenario, eventually, object_value, string_value
-from integration._support.database import read_rows
-from integration._support.upstream import delete_scenario, register_scenario
+from integration._support.database import read_rows, write_rows
+from integration._support.prisma_clients import connected_proxy_prisma
+from integration._support.upstream import ScenarioHandle, delete_scenario, register_scenario
 from integration.cost_calculation.cost_tracking_case import JsonResponse, RoutedResponse, TextResponse
-from pydantic import JsonValue
+from pydantic import JsonValue, TypeAdapter
 
 from litellm.constants import MAX_OBJECTS_PER_POLL_CYCLE
 
@@ -59,17 +65,17 @@ def _accepting_routes() -> dict[str, JsonResponse | TextResponse]:
     }
 
 
-def _gone_at_provider_routes() -> RoutedResponse:
+def _gone_at_provider_routes(*, retryable: bool = False) -> RoutedResponse:
     return RoutedResponse(
         content_type="application/x-routed",
         routes={
             **_accepting_routes(),
             "GET /batches/batch-$REQUEST_ID": JsonResponse(
                 content_type="application/json",
-                status=404,
+                status=503 if retryable else 404,
                 body={
                     "error": {
-                        "message": "No batch found with id 'batch-$REQUEST_ID'.",
+                        "message": "Temporary failure" if retryable else "No batch found with id 'batch-$REQUEST_ID'.",
                         "type": "invalid_request_error",
                         "param": "id",
                         "code": "batch_not_found",
@@ -80,7 +86,7 @@ def _gone_at_provider_routes() -> RoutedResponse:
     )
 
 
-def _completed_routes() -> RoutedResponse:
+def _completed_routes(*, ready: bool = True) -> RoutedResponse:
     output_line: Final = {
         "id": "batch_req_1",
         "custom_id": "r1",
@@ -106,7 +112,8 @@ def _completed_routes() -> RoutedResponse:
         routes={
             **_accepting_routes(),
             "GET /batches/batch-$REQUEST_ID": JsonResponse(
-                content_type="application/json", body=_batch("completed", "file-out-$REQUEST_ID")
+                content_type="application/json",
+                body=_batch("completed", "file-out-$REQUEST_ID") if ready else _batch("in_progress", None),
             ),
             "GET /files/file-out-$REQUEST_ID/content": TextResponse(
                 content_type="application/jsonl", body=json.dumps(output_line, separators=(",", ":")) + "\n"
@@ -115,7 +122,37 @@ def _completed_routes() -> RoutedResponse:
     )
 
 
-def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse) -> str:
+def _batch_was_polled(upstream: ScenarioHandle) -> bool:
+    response: Final = httpx.get(f"{upstream.control_url}/__observations", timeout=15, trust_env=False)
+    response.raise_for_status()
+    observations: Final = TypeAdapter(dict[str, list[dict[str, JsonValue]]]).validate_json(response.content)
+    return any(
+        item.get("method") == "GET" and string_value(item["path"]).startswith(f"/{upstream.scenario_id}/batches/")
+        for item in observations["requests"]
+    )
+
+
+def _missing_output_routes() -> RoutedResponse:
+    return RoutedResponse(
+        content_type="application/x-routed",
+        routes={
+            **_completed_routes().routes,
+            "GET /files/file-out-$REQUEST_ID/content": JsonResponse(
+                content_type="application/json",
+                status=404,
+                body={
+                    "error": {
+                        "message": "No file found with id 'file-out-$REQUEST_ID'.",
+                        "type": "invalid_request_error",
+                        "code": "file_not_found",
+                    }
+                },
+            ),
+        },
+    )
+
+
+def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse) -> tuple[str, ScenarioHandle]:
     scenario_id: Final = f"poll-{marker}-{sha256(os.urandom(16)).hexdigest()[:12]}"
     handle: Final = register_scenario(scenario_id, routes)
     scenario.cleanups.callback(delete_scenario, handle)
@@ -133,7 +170,7 @@ def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse
         },
     )
     scenario.cleanups.callback(scenario.delete_model, string_value(object_value(created["model_info"])["id"]))
-    return string_value(created["model_name"])
+    return string_value(created["model_name"]), handle
 
 
 def _submitted_batch_id(gateway: Gateway, key: str, model_name: str) -> str:
@@ -173,20 +210,51 @@ def _managed_rows(batch_ids: tuple[str, ...]) -> list[dict[str, JsonValue]]:
     )
 
 
+@pytest.mark.parametrize(
+    ("retryable", "old_completed", "backlog"),
+    [(False, False, 0), (False, True, 0), (True, False, 0), (True, True, 0), (True, False, 1000)],
+)
 @pytest.mark.timeout(180)
 @pytest.mark.covers("quota_management.spend_tracking.batch_costs.uncostable_rows_retire_so_newer_batches_are_costed")
-def test_batches_gone_at_provider_do_not_starve_a_newer_batch_out_of_cost_polling(gateway: Gateway) -> None:
+def test_uncostable_batches_do_not_starve_billable_batches(
+    gateway: Gateway, retryable: bool, old_completed: bool, backlog: int
+) -> None:
     with gateway.scenario() as scenario:
-        key: Final = scenario.key()
+        owner: Final = f"batch-backlog-{uuid4().hex}"
+        if backlog:
+            _insert_scan_rows(owner, "old", backlog, datetime(2000, 1, 1, tzinfo=timezone.utc))
+            scenario.cleanups.callback(
+                write_rows, 'DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,)
+            )
+        team_id: Final = scenario.team()
+        key: Final = scenario.key(team_id=team_id)
         gone_batch_ids: Final = tuple(
             _submitted_batch_id(
-                gateway, key, _scripted_deployment(scenario, f"gone{index}", _gone_at_provider_routes())
+                gateway,
+                key,
+                _scripted_deployment(scenario, f"gone{index}", _gone_at_provider_routes(retryable=retryable))[0],
             )
             for index in range(MAX_OBJECTS_PER_POLL_CYCLE)
         )
-        costable_batch_id: Final = _submitted_batch_id(
-            gateway, key, _scripted_deployment(scenario, "costable", _completed_routes())
+        missing_output_id: Final = _submitted_batch_id(
+            gateway, key, _scripted_deployment(scenario, "missing-output", _missing_output_routes())[0]
         )
+        model, upstream = _scripted_deployment(scenario, "costable", _completed_routes(ready=False))
+        costable_batch_id: Final = _submitted_batch_id(gateway, key, model)
+        for batch_id in (*gone_batch_ids, missing_output_id, costable_batch_id):
+            scenario.cleanups.callback(
+                write_rows,
+                'DELETE FROM "LiteLLM_ManagedObjectTable" WHERE unified_object_id = %s',
+                (batch_id,),
+            )
+        if old_completed:
+            write_rows(
+                'UPDATE "LiteLLM_ManagedObjectTable" SET status = %s, '
+                "created_at = NOW() - INTERVAL '30 days' WHERE unified_object_id = %s",
+                ("completed", costable_batch_id),
+            )
+        assert eventually(lambda: _batch_was_polled(upstream), bool, seconds=120)
+        register_scenario(upstream.scenario_id, _completed_routes(), control_url=upstream.control_url)
         spend_rows: Final = eventually(
             lambda: read_rows(
                 'SELECT call_type, status, prompt_tokens, completion_tokens, spend FROM "LiteLLM_SpendLogs" '
@@ -209,4 +277,134 @@ def test_batches_gone_at_provider_do_not_starve_a_newer_batch_out_of_cost_pollin
             }
         ]
         assert _managed_rows((costable_batch_id,)) == [{"batch_processed": True}]
-        assert _managed_rows(gone_batch_ids) == [{"batch_processed": True}] * MAX_OBJECTS_PER_POLL_CYCLE
+        assert eventually(
+            lambda: _managed_rows((missing_output_id,)),
+            lambda rows: rows == [{"batch_processed": True}],
+            seconds=120,
+        ) == [{"batch_processed": True}]
+        expected_blockers: Final = [{"batch_processed": not retryable}] * MAX_OBJECTS_PER_POLL_CYCLE
+        blockers: Final = eventually(
+            lambda: _managed_rows(gone_batch_ids), lambda rows: rows == expected_blockers, seconds=120
+        )
+        assert blockers == expected_blockers
+
+        expected_spend: Final = BATCH_COST_SHARE * (
+            PROMPT_TOKENS * INPUT_COST_PER_TOKEN + COMPLETION_TOKENS * OUTPUT_COST_PER_TOKEN
+        )
+        for table, column, identity in (
+            ("LiteLLM_VerificationToken", "token", sha256(key.encode()).hexdigest()),
+            ("LiteLLM_TeamTable", "team_id", team_id),
+        ):
+            balance: Final = eventually(
+                partial(read_rows, f'SELECT spend FROM "{table}" WHERE {column} = %s', (identity,)),
+                lambda rows: len(rows) == 1 and rows[0]["spend"] == pytest.approx(expected_spend),
+                seconds=70,
+            )
+            assert balance == [{"spend": pytest.approx(expected_spend)}]
+
+
+def _insert_scan_rows(owner: str, group: str, size: int, created_at: datetime) -> tuple[str, ...]:
+    prefix: Final = f"{owner}-{group}-"
+    write_rows(
+        'INSERT INTO "LiteLLM_ManagedObjectTable" '
+        "(id, unified_object_id, model_object_id, file_object, file_purpose, status, created_by, created_at, updated_at) "
+        "SELECT %s || lpad(n::text, 8, '0'), %s || n, %s || n, '{}'::jsonb, 'batch', 'completed', %s, "
+        "%s::timestamptz, NOW() FROM generate_series(0, %s::int - 1) n",
+        (prefix, prefix, prefix, owner, created_at.isoformat(), str(size)),
+    )
+    return tuple(f"{prefix}{index:08}" for index in range(size))
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("count", [2 * MAX_OBJECTS_PER_POLL_CYCLE, 2 * MAX_OBJECTS_PER_POLL_CYCLE + 1, 1000])
+async def test_arrivals_progress_while_retry_scan_advances_and_wraps(count: int) -> None:
+    from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache
+    from litellm.proxy.utils import ProxyLogging
+    from litellm.router import Router
+    from litellm_enterprise.proxy.common_utils.check_batch_cost import CheckBatchCost
+
+    owner: Final = f"batch-scan-{uuid4().hex}"
+
+    try:
+        old_ids: Final = _insert_scan_rows(owner, "old", count, datetime(2000, 1, 1, tzinfo=timezone.utc))
+        async with connected_proxy_prisma() as prisma:
+            logging: Final = ProxyLogging(UserApiKeyCache())
+            router: Final = Router()
+            poller: Final = CheckBatchCost(logging, prisma, router)
+            where: Final = {"created_by": owner, "batch_processed": False}
+            first: Final = await poller._find_jobs(where)
+            assert tuple(row.id for row in first) == old_ids[:MAX_OBJECTS_PER_POLL_CYCLE]
+
+            recent_ids: Final = _insert_scan_rows(
+                owner, "recent", MAX_OBJECTS_PER_POLL_CYCLE + 1, datetime.now(timezone.utc)
+            )
+
+            async def poll_with_arrival(turn: int) -> tuple[str, ...]:
+                if turn % 4 == 0:
+                    _insert_scan_rows(owner, f"arrival-{turn}", 1, datetime.now(timezone.utc))
+                page: Final = await poller._find_jobs(where)
+                assert len(page) <= MAX_OBJECTS_PER_POLL_CYCLE
+                write_rows(
+                    'UPDATE "LiteLLM_ManagedObjectTable" SET batch_processed = true '
+                    "WHERE created_by = %s AND id = ANY(%s) AND id LIKE %s",
+                    (owner, [row.id for row in page], f"{owner}-arrival-%"),
+                )
+                return tuple(row.id for row in page)
+
+            pages: Final = tuple(
+                [await poll_with_arrival(turn) for turn in range(4 * (count // MAX_OBJECTS_PER_POLL_CYCLE + 2))]
+            )
+            selected: Final = tuple(chain.from_iterable(pages))
+            assert all(selected.count(identity) >= 2 for identity in recent_ids)
+            selected_old: Final = tuple(identity for identity in selected if identity in old_ids)
+            assert selected_old[: count - MAX_OBJECTS_PER_POLL_CYCLE] == old_ids[MAX_OBJECTS_PER_POLL_CYCLE:]
+            assert set(old_ids).issubset(selected_old)
+
+            latest_ids: Final = _insert_scan_rows(owner, "latest", 1, datetime.now(timezone.utc))
+            followups: Final = tuple([await poller._find_jobs(where) for _ in range(12)])
+            assert any(latest_ids[0] in tuple(row.id for row in page) for page in followups)
+
+            restarted: Final = CheckBatchCost(logging, prisma, router)
+            restart_page: Final = await restarted._find_jobs(where)
+            assert tuple(row.id for row in restart_page) == old_ids[:MAX_OBJECTS_PER_POLL_CYCLE]
+    finally:
+        write_rows('DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,))
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("steady_arrivals", [False, True])
+@pytest.mark.parametrize("backlog", [0, 1000])
+async def test_recent_batches_are_revisited_without_scanning_old_backlog(steady_arrivals: bool, backlog: int) -> None:
+    from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache
+    from litellm.proxy.utils import ProxyLogging
+    from litellm.router import Router
+    from litellm_enterprise.proxy.common_utils.check_batch_cost import CheckBatchCost
+
+    owner: Final = f"batch-repeat-{uuid4().hex}"
+    try:
+        _insert_scan_rows(owner, "old", backlog, datetime(2000, 1, 1, tzinfo=timezone.utc))
+        async with connected_proxy_prisma() as prisma:
+            poller: Final = CheckBatchCost(ProxyLogging(UserApiKeyCache()), prisma, Router())
+            where: Final = {"created_by": owner, "batch_processed": False}
+            await poller._find_jobs(where)
+            target: Final = _insert_scan_rows(owner, "target", 1, datetime.now(timezone.utc))[0]
+            assert target in tuple(row.id for row in await poller._find_jobs(where))
+            for cycle in range(3):
+                if steady_arrivals:
+                    _insert_scan_rows(owner, f"arrival-{cycle}", 1, datetime.now(timezone.utc))
+                pages: Final = tuple([await poller._find_jobs(where) for _ in range(4)])
+                assert any(target in tuple(row.id for row in page) for page in pages)
+                assert all(len(page) <= MAX_OBJECTS_PER_POLL_CYCLE for page in pages)
+            write_rows(
+                'UPDATE "LiteLLM_ManagedObjectTable" SET batch_processed = true WHERE created_by = %s AND id != %s',
+                (owner, target),
+            )
+            write_rows(
+                'UPDATE "LiteLLM_ManagedObjectTable" SET created_at = %s WHERE id = %s',
+                (datetime(2000, 1, 1, tzinfo=timezone.utc), target),
+            )
+            recovery: Final = tuple([await poller._find_jobs(where) for _ in range(4)])
+            assert any(target in tuple(row.id for row in page) for page in recovery)
+
+    finally:
+        write_rows('DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,))
diff --git a/tests/router_unit_tests/test_router_batch_utils.py b/tests/router_unit_tests/test_router_batch_utils.py
index 4336185a07f..c29205059a3 100644
--- a/tests/router_unit_tests/test_router_batch_utils.py
+++ b/tests/router_unit_tests/test_router_batch_utils.py
@@ -3,7 +3,7 @@ import pytest
 
 import json
 from io import BytesIO
-from typing import Dict, List
+from typing import Dict, List, Final
 from litellm.router_utils.batch_utils import (
     replace_model_in_jsonl,
     _get_router_metadata_variable_name,
@@ -333,3 +333,31 @@ def test_is_batch_retrieve_call_type_matches_only_batch_retrieves():
         assert is_batch_retrieve_call_type(call_type.value) is False
 
     assert is_batch_retrieve_call_type(None) is False
+
+
+@pytest.mark.parametrize(
+    ("call_type", "cost", "eligible"),
+    (("aretrieve_batch", 0.25, True), ("retrieve_batch", 0.25, True), ("acompletion", 0.25, False),
+     ("aretrieve_batch", 0, False), ("aretrieve_batch", -0.25, False)),
+)
+def test_batch_charge_identity_requires_a_cost_bearing_retrieval(call_type: str, cost: float, eligible: bool) -> None:
+    from openai.types import Batch
+    from litellm.router_utils.batch_utils import batch_id_to_charge_once
+
+    batch: Final = Batch(
+        id="batch-budget", completion_window="24h", created_at=1, endpoint="/v1/chat/completions",
+        input_file_id="file-budget", object="batch", status="completed",
+    )
+    assert batch_id_to_charge_once(call_type, batch, cost) == (batch.id if eligible else None)
+    assert batch_id_to_charge_once(call_type, {"id": batch.id}, cost) is None
+
+
+def test_batch_charge_markers_keep_counters_and_batches_independent() -> None:
+    from litellm.caching.in_memory_cache import InMemoryCache
+    from litellm.router_utils.batch_utils import batch_charged_once_marker_key
+
+    cache: Final = InMemoryCache()
+    cache.set_cache(batch_charged_once_marker_key("provider-spend", "first-batch"), 1)
+    assert cache.get_cache(batch_charged_once_marker_key("provider-spend", "first-batch")) == 1
+    assert cache.get_cache(batch_charged_once_marker_key("deployment-spend", "first-batch")) is None
+    assert cache.get_cache(batch_charged_once_marker_key("provider-spend", "second-batch")) is None
diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py
index eb51e4ffa36..1c68f1adf92 100644
--- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py
+++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py
@@ -2,6 +2,7 @@ import asyncio
 import json
 import logging
 from datetime import datetime
+from types import SimpleNamespace
 from typing import Final
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -2774,6 +2775,79 @@ async def test_track_cost_callback_failure_alert_never_carries_request_metadata_
     else:
         assert failure_debug_lines == []
 
+
+_BATCH_CALL_START: Final = datetime(2026, 1, 1)
+
+
+@pytest.mark.asyncio
+async def test_batch_accounting_failures_stay_with_their_originating_call() -> None:
+    from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting
+
+    logger: Final = _ProxyDBLogger()
+    dependency: Final = SimpleNamespace(failed_tracking_alert=AsyncMock())
+
+    async def fail_before_accounting(call_id: str) -> None:
+        await logger.async_log_success_event(
+            kwargs={
+                "litellm_call_id": call_id,
+                "call_type": "aretrieve_batch",
+                "model": "batch-model",
+                "stream": False,
+                "response_cost": None,
+            },
+            response_obj=None,
+            start_time=_BATCH_CALL_START,
+            end_time=_BATCH_CALL_START,
+        )
+
+    async def independent_batch() -> bool:
+        with track_batch_accounting("independent") as outcome:
+            await fail_before_accounting("independent")
+        return outcome.retryable_failure
+
+    with patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency):
+        with track_batch_accounting("outer") as outer:
+            await fail_before_accounting("unrelated")
+            assert outer.retryable_failure is False
+            with track_batch_accounting("inner") as inner:
+                await fail_before_accounting("inner")
+            assert inner.retryable_failure is True
+            assert outer.retryable_failure is False
+            independent, _ = await asyncio.gather(independent_batch(), fail_before_accounting("outer"))
+            assert independent is True
+            assert outer.retryable_failure is True
+            with pytest.raises(asyncio.CancelledError):
+                with track_batch_accounting("cancelled") as cancelled:
+                    raise asyncio.CancelledError
+            await fail_before_accounting("cancelled")
+            assert cancelled.retryable_failure is False
+
+
+@pytest.mark.asyncio
+async def test_batch_accounting_does_not_retry_after_settling_a_budget_reservation() -> None:
+    from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting
+
+    reservation: Final[dict[str, object]] = {"reserved_cost": 0.5, "entries": ()}
+    dependency: Final = SimpleNamespace(failed_tracking_alert=AsyncMock())
+    with patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency):
+        with track_batch_accounting("reserved") as outcome:
+            await _ProxyDBLogger().async_log_success_event(
+                kwargs={
+                    "litellm_call_id": "reserved",
+                    "call_type": "aretrieve_batch",
+                    "model": "batch-model",
+                    "stream": False,
+                    "response_cost": None,
+                    "litellm_params": {"metadata": {"user_api_key_budget_reservation": reservation}},
+                },
+                response_obj=None,
+                start_time=_BATCH_CALL_START,
+                end_time=_BATCH_CALL_START,
+            )
+    assert reservation["finalized"] is True
+    assert outcome.retryable_failure is False
+
+
 class _SharedCounter:
     def __init__(self) -> None:
         self.totals: dict[str, float] = {}
diff --git a/tests/unit/batches/test_batch_utils.py b/tests/unit/batches/test_batch_utils.py
index 398b6fb1aed..ba2efb84cf7 100644
--- a/tests/unit/batches/test_batch_utils.py
+++ b/tests/unit/batches/test_batch_utils.py
@@ -17,6 +17,7 @@ deterministic stand-ins so the arithmetic under test is the only variable.
 import json
 import logging
 from types import MappingProxyType
+from typing import Final, Literal
 
 import httpx
 import pytest
@@ -2447,3 +2448,30 @@ async def test_flag_sends_every_vertex_row_down_the_native_path_when_a_model_is_
 
     assert calls == []
     assert (result.successful_requests, result.failed_requests) == (0, 1)
+
+
+@pytest.mark.parametrize("provider", ("openai", "anthropic"))
+@pytest.mark.parametrize("envelope", (1, "invalid", [1], None, {}))
+@pytest.mark.parametrize("include_valid", (True, False))
+def test_invalid_batch_envelopes_preserve_recoverable_cost(
+    provider: Literal["openai", "anthropic"], envelope: object, include_valid: bool
+) -> None:
+    invalid: Final[dict[str, object]] = {"response" if provider == "openai" else "result": envelope}
+    valid: Final[dict[str, object]] = (
+        _success_row(model="batch-accounting-control", usage=_usage(100, 20))
+        if provider == "openai"
+        else {
+            "result": {
+                "type": "succeeded",
+                "message": {"model": "batch-accounting-control", "usage": {"input_tokens": 100, "output_tokens": 20}},
+            }
+        }
+    )
+    entries: Final = (valid, invalid, valid) if include_valid else (invalid,)
+    result: Final = bu._aggregate_batch_cost_usage_models(
+        entries, provider, model_info={"input_cost_per_token_batches": 0.001, "output_cost_per_token_batches": 0.002}
+    )
+    assert result.cost == pytest.approx(0.28 if include_valid else 0)
+    assert result.usage.prompt_tokens == (200 if include_valid else 0)
+    assert result.usage.completion_tokens == (40 if include_valid else 0)
+    assert (result.successful_requests, result.failed_requests) == (2 if include_valid else 0, 1)
diff --git a/tests/unit/enterprise/proxy/test_managed_files_access_check.py b/tests/unit/enterprise/proxy/test_managed_files_access_check.py
index ad46798b788..62f0d0797ef 100644
--- a/tests/unit/enterprise/proxy/test_managed_files_access_check.py
+++ b/tests/unit/enterprise/proxy/test_managed_files_access_check.py
@@ -9,6 +9,8 @@ with deployment credentials, bypassing the managed files access-control hooks.
 """
 
 import base64
+import json
+from typing import Final
 import pytest
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, MagicMock, patch
@@ -367,13 +369,14 @@ async def test_check_batch_cost_should_call_afile_content_directly_with_credenti
         # managed_files_obj.afile_content should NOT have been called
         mock_managed_files_hook.afile_content.assert_not_called()
 
-        # Verify the DB update writes batch_processed, status, and file_object
-        mock_prisma.db.litellm_managedobjecttable.update.assert_called_once()
-        update_call_kwargs = (
-            mock_prisma.db.litellm_managedobjecttable.update.call_args.kwargs
+        claim_data: Final = next(
+            call.kwargs["data"]
+            for call in mock_prisma.db.litellm_managedobjecttable.update_many.call_args_list
+            if call.kwargs["where"].get("id") == mock_job.id
         )
-        assert update_call_kwargs["data"]["batch_processed"] is True
-        assert update_call_kwargs["data"]["status"] == "complete"
-        assert (
-            "file_object" in update_call_kwargs["data"]
-        ), "file_object must be written to DB so list_batches reads updated status"
+        assert claim_data["batch_processed"] is True
+        assert claim_data["status"] == "complete"
+        persisted_batch: Final = json.loads(claim_data["file_object"])
+        assert persisted_batch["status"] == "completed"
+        assert persisted_batch["usage"]["prompt_tokens"] == 10
+        assert persisted_batch["usage"]["completion_tokens"] == 5
diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 38bea4b2a76..6c4f6e90c10 100644
--- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -3886,3 +3886,220 @@ def test_azure_gpt_5_6_alias_matches_sol_pricing(_local_model_cost_map, region_p
     assert shared_cost_fields
     for field in shared_cost_fields:
         assert alias[field] == sol[field], field
+
+
+# Per-token rates read 2026-10-07 from https://platform.claude.com/docs/en/about-claude/pricing (direct and
+# azure_ai, which Microsoft bills at Anthropic's rates per
+# https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models-billing) and from the
+# AmazonBedrockFoundationModels price list at
+# https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json (Bedrock)
+@pytest.mark.parametrize(
+    ("model", "custom_llm_provider", "prompt_tokens", "input_rate", "cache_read_rate", "output_rate"),
+    [
+        ("claude-haiku-5-5", "anthropic", 100_000, 1e-07, 1e-08, 5e-07),
+        ("claude-haiku-5-5", "anthropic", 100_001, 5e-07, 5e-08, 2.5e-06),
+        ("azure_ai/claude-haiku-5-5", "azure_ai", 100_000, 1e-07, 1e-08, 5e-07),
+        ("azure_ai/claude-haiku-5-5", "azure_ai", 100_001, 5e-07, 5e-08, 2.5e-06),
+        ("global.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1e-07, 1e-08, 5e-07),
+        ("global.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5e-07, 5e-08, 2.5e-06),
+        ("us.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.1e-07, 1.1e-08, 5.5e-07),
+        ("us.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5.5e-07, 5.5e-08, 2.75e-06),
+        ("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.2e-07, 1.2e-08, 6e-07),
+        ("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06),
+        ("bedrock_mantle/anthropic.claude-haiku-5-5", "bedrock_mantle", 100_001, 5.5e-07, 5.5e-08, 2.75e-06),
+        ("bedrock/us-gov-west-1/anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06),
+        ("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_000, 1e-07, 1e-08, 5e-07),
+        ("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_001, 5e-07, 5e-08, 2.5e-06),
+    ],
+)
+def test_generic_cost_per_token_claude_haiku_5_5_prompt_length_tiers(
+    _local_model_cost_map: None,
+    model: str,
+    custom_llm_provider: str,
+    prompt_tokens: int,
+    input_rate: float,
+    cache_read_rate: float,
+    output_rate: float,
+) -> None:
+    """Claude Haiku 5.5 bills every token at 5x the base rates once the prompt is over 100,000 tokens."""
+    cached_tokens: Final = 10_000
+    completion_tokens: Final = 1_000
+    usage: Final = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
+    )
+
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model,
+        usage=usage,
+        custom_llm_provider=custom_llm_provider,
+    )
+
+    assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate)
+    assert completion_cost == pytest.approx(completion_tokens * output_rate)
+
+
+def test_vertex_regional_endpoint_uplift_scales_claude_haiku_5_5_over_100k_rates(
+    _local_model_cost_map: None,
+) -> None:
+    """Vertex regional endpoints bill 1.1x the global rate on all token types
+    (https://cloud.google.com/vertex-ai/generative-ai/pricing, 2026-10-07: regional
+    over-100K input is $0.55/MTok), so the uplift scales the over-100k rates too."""
+    cached_tokens: Final = 10_000
+    prompt_tokens: Final = 100_001
+    completion_tokens: Final = 1_000
+    usage: Final = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
+    )
+
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model="vertex_ai/claude-haiku-5-5",
+        usage=usage,
+        custom_llm_provider="vertex_ai",
+        vertex_location="us-east5",
+    )
+
+    assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * 5.5e-07 + cached_tokens * 5.5e-08)
+    assert completion_cost == pytest.approx(completion_tokens * 2.75e-06)
+
+
+# Batch rates read 2026-10-07 from the Batch processing table at
+# https://platform.claude.com/docs/en/about-claude/pricing: $0.05 / $0.25 per MTok input and $0.25 / $1.25 output,
+# up to and over 100,000 prompt tokens
+@pytest.mark.parametrize(
+    ("prompt_tokens", "input_rate", "output_rate"),
+    [(100_000, 5e-08, 2.5e-07), (100_001, 2.5e-07, 1.25e-06)],
+)
+def test_batch_cost_calculator_claude_haiku_5_5_prompt_length_tiers(
+    _local_model_cost_map: None,
+    prompt_tokens: int,
+    input_rate: float,
+    output_rate: float,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    completion_tokens: Final = 1_000
+
+    prompt_cost, completion_cost = batch_cost_calculator(
+        usage=Usage(
+            prompt_tokens=prompt_tokens,
+            completion_tokens=completion_tokens,
+            total_tokens=prompt_tokens + completion_tokens,
+        ),
+        model="claude-haiku-5-5",
+        custom_llm_provider="anthropic",
+    )
+
+    assert prompt_cost == pytest.approx(prompt_tokens * input_rate)
+    assert completion_cost == pytest.approx(completion_tokens * output_rate)
+
+
+@pytest.mark.parametrize(
+    ("prompt_tokens", "expected"),
+    [
+        (100_000, (5e-08, 2.5e-07, 5e-09, 6.25e-08)),
+        (100_001, (2.5e-07, 1.25e-06, 2.5e-08, 3.125e-07)),
+    ],
+)
+def test_get_batch_cost_rates_claude_haiku_5_5_prompt_length_tiers(
+    _local_model_cost_map: None,
+    prompt_tokens: int,
+    expected: tuple[float, float, float, float],
+) -> None:
+    """Cache write and cache read batch rates are 50% of the standard rates; Anthropic's batch table omits them."""
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates: Final = get_batch_cost_rates(
+        litellm.get_model_info(model="claude-haiku-5-5", custom_llm_provider="anthropic"),
+        Usage(prompt_tokens=prompt_tokens, completion_tokens=1, total_tokens=prompt_tokens + 1),
+        "anthropic",
+    )
+
+    assert (rates.input, rates.output, rates.cache_read, rates.cache_creation) == expected
+
+
+@pytest.mark.parametrize(
+    "field", ("output_cost_per_token", "cache_read_input_token_cost", "cache_creation_input_token_cost")
+)
+def test_flat_input_price_keeps_other_token_thresholds(field: str) -> None:
+    from typing import Final, cast
+    from litellm.litellm_core_utils.llm_cost_calc.utils import _get_token_base_cost
+
+    info: Final = cast(
+        ModelInfo,
+        {
+            "input_cost_per_token": 0.001,
+            "output_cost_per_token": 0.002,
+            "cache_read_input_token_cost": 0.003,
+            "cache_creation_input_token_cost": 0.004,
+            f"{field}_above_300k_tokens": 0.005,
+        },
+    )
+    rates: Final = _get_token_base_cost(
+        model_info=info,
+        usage=Usage(prompt_tokens=300_001, completion_tokens=3, total_tokens=300_004),
+    )
+    assert rates[0] == 0.001
+    assert rates[1] == (0.005 if field == "output_cost_per_token" else 0.002)
+    assert rates[2] == (0.005 if field == "cache_creation_input_token_cost" else 0.004)
+    assert rates[4] == (0.005 if field == "cache_read_input_token_cost" else 0.003)
+
+
+@pytest.mark.parametrize("prompt_tokens", (200_000, 200_001, 512_000, 512_001))
+@pytest.mark.parametrize("higher_rate", (0.0, 0.009))
+def test_mixed_token_thresholds_preserve_each_crossed_rate(prompt_tokens: int, higher_rate: float) -> None:
+    from typing import Final, cast
+    from litellm.litellm_core_utils.llm_cost_calc.utils import _get_token_base_cost
+
+    info: Final = cast(
+        ModelInfo,
+        {
+            "input_cost_per_token": 0.001,
+            "output_cost_per_token": 0.002,
+            "cache_read_input_token_cost": 0.003,
+            "cache_creation_input_token_cost": 0.004,
+            "input_cost_per_token_above_200k_tokens": 0.005,
+            "output_cost_per_token_above_200k_tokens": 0.006,
+            "cache_creation_input_token_cost_above_200k_tokens": 0.007,
+            "cache_read_input_token_cost_above_512k_tokens": higher_rate,
+            "output_cost_per_token_above_512k_tokens": higher_rate,
+        },
+    )
+    rates: Final = _get_token_base_cost(
+        model_info=info,
+        usage=Usage(prompt_tokens=prompt_tokens, completion_tokens=3, total_tokens=prompt_tokens + 3),
+    )
+    assert rates[0] == (0.005 if prompt_tokens > 200_000 else 0.001)
+    assert rates[1] == (higher_rate if prompt_tokens > 512_000 else 0.006 if prompt_tokens > 200_000 else 0.002)
+    assert rates[2] == (0.007 if prompt_tokens > 200_000 else 0.004)
+    assert rates[4] == (higher_rate if prompt_tokens > 512_000 else 0.003)
+
+
+@pytest.mark.parametrize("rate", (0.0, 0.001))
+def test_token_breakdown_uses_supplied_pricing_without_catalog_lookup(rate: float) -> None:
+    model_info: Final[ModelInfo] = {
+        "input_cost_per_token": 0.01,
+        "output_cost_per_token": 0.02,
+        "cache_read_input_token_cost": rate,
+        "cache_creation_input_token_cost": rate,
+    }
+    usage: Final = Usage(
+        prompt_tokens=20, completion_tokens=3, total_tokens=23,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5), cache_creation_input_tokens=5,
+    )
+    prompt_cost, output_cost = generic_cost_per_token(
+        model="supplied-pricing-test", usage=usage, custom_llm_provider="bedrock", model_info=model_info,
+    )
+    breakdown: Final = get_token_type_cost_breakdown(
+        model="supplied-pricing-test", usage=usage, custom_llm_provider="bedrock", model_info=model_info,
+    )
+    assert breakdown.cache_read_cost == pytest.approx(5 * rate)
+    assert breakdown.cache_creation_cost == pytest.approx(5 * rate)
+    assert breakdown.rates is not None
+    assert prompt_cost == pytest.approx(10 * breakdown.rates.input_cost_per_token + breakdown.cache_read_cost + breakdown.cache_creation_cost)
+    assert output_cost == pytest.approx(3 * breakdown.rates.output_cost_per_token)
diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
index 41a2d19b8ab..58ee36d87ad 100644
--- a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
+++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
@@ -363,15 +363,15 @@ def test_web_search_provider_prefix_fallback_does_not_misprice_non_gemini_model(
     Regression for the provider-prefix fallback in _handle_web_search_cost. When the initial
     get_model_info lookup fails for a "/"-containing model, the retry re-resolves model_info from
     the prefix and must adopt that prefix's provider for routing. Otherwise an unrelated model
-    (here OpenRouter, which carries no web search pricing) is re-resolved but still routed through
+    (here Azure, which carries no web search pricing) is re-resolved but still routed through
     the request's vertex_ai Gemini calculator, which charges its $0.035 per_prompt default for a
     model that should cost nothing for web search.
     """
     from litellm.types.utils import PromptTokensDetailsWrapper, Usage
 
-    model = "openrouter/google/gemini-3.1-flash-lite"
+    model = "azure/gpt-4o"
     model_info = litellm.get_model_info(model)
-    assert model_info["litellm_provider"] == "openrouter"
+    assert model_info["litellm_provider"] == "azure"
     assert not model_info.get("search_context_cost_per_query")
 
     usage = Usage(
diff --git a/tests/unit/litellm_core_utils/test_fallback_generalizations.py b/tests/unit/litellm_core_utils/test_fallback_generalizations.py
index f70b52a7026..7b96a1d693c 100644
--- a/tests/unit/litellm_core_utils/test_fallback_generalizations.py
+++ b/tests/unit/litellm_core_utils/test_fallback_generalizations.py
@@ -970,19 +970,16 @@ def test_shipped_tool_search_rule_version_boundaries(shipped_cost_map, model, pr
 
 def test_shipped_tool_search_rule_fills_mapped_claude_entries_without_flag(shipped_cost_map):
     """A mapped Claude 4.5+ entry with no supports_tool_search key gets it from the rule
-    on Anthropic direct, Vertex and Bedrock, a mapped pre-4.5 entry stays without one,
-    and Azure Foundry and reseller copies of the same model are not touched."""
+    on Anthropic direct, Azure Foundry, Vertex and Bedrock, a mapped pre-4.5 entry stays
+    without one, and reseller copies of the same model are not touched."""
     for key, model, provider in (
         ("claude-opus-4-7", "claude-opus-4-7", "anthropic"),
+        ("azure_ai/claude-opus-5", "claude-opus-5", "azure_ai"),
         ("vertex_ai/claude-opus-5", "claude-opus-5", "vertex_ai"),
     ):
         assert "supports_tool_search" not in litellm.model_cost[key]
         assert litellm.get_model_info(model, custom_llm_provider=provider)["supports_tool_search"] is True
 
-    assert "supports_tool_search" not in litellm.model_cost["azure_ai/claude-opus-5"]
-    azure_opus_5_info = litellm.get_model_info("claude-opus-5", custom_llm_provider="azure_ai")
-    assert azure_opus_5_info.get("supports_tool_search") is None
-
     assert match_fill_missing_generalizations("claude-opus-5", "bedrock")["supports_tool_search"] is True
-    assert "supports_tool_search" not in match_fill_missing_generalizations("claude-opus-5", "azure_ai")
+    assert match_fill_missing_generalizations("claude-opus-5", "azure_ai")["supports_tool_search"] is True
     assert match_fill_missing_generalizations("claude-opus-5", "perplexity") is None
diff --git a/tests/unit/litellm_core_utils/test_get_model_cost_map.py b/tests/unit/litellm_core_utils/test_get_model_cost_map.py
index 00977d9c3ee..7a3cec592de 100644
--- a/tests/unit/litellm_core_utils/test_get_model_cost_map.py
+++ b/tests/unit/litellm_core_utils/test_get_model_cost_map.py
@@ -212,7 +212,6 @@ def test_shipped_backup_marks_claude_4_6_plus_adaptive_not_4_0():
         "anthropic.claude-opus-4-8",
         "vertex_ai/claude-opus-4-6@default",
         "us.anthropic.claude-sonnet-4-6",
-        "openrouter/anthropic/claude-opus-4.7",
         "azure_ai/claude-opus-4-7",
     ]:
         assert backup[adaptive]["supports_adaptive_thinking"] is True, adaptive
diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py
index 17bc284cc50..d9ddc3e950b 100644
--- a/tests/unit/litellm_core_utils/test_litellm_logging.py
+++ b/tests/unit/litellm_core_utils/test_litellm_logging.py
@@ -8987,3 +8987,86 @@ async def test_prompt_management_with_unchanged_variables_replays_a_byte_identic
     assert json.dumps(messages_n_plus_one[: len(messages_n)], sort_keys=True) == json.dumps(messages_n, sort_keys=True)
     assert messages_n[0] == {"role": "system", "content": "You are a pirate. Answer in one sentence."}
     assert len(messages_n_plus_one) == len(messages_n) + 2
+@pytest.mark.parametrize(
+    ("input_cost_per_token", "output_cost_per_token"),
+    [(1e-06, 2e-06), (0.0, 0.0)],
+    ids=["custom_price", "explicit_zero_price"],
+)
+def test_standard_logging_payload_reports_the_deployment_entry_the_request_was_billed_from(
+    input_cost_per_token: float, output_cost_per_token: float
+):
+    """A deployment with its own price keeps the catalog model as model_map_key but is logged at its own rates."""
+    deployment_id: Final = "lit9660-priced-deployment"
+    deployment_model_info: Final = {
+        "id": deployment_id,
+        "input_cost_per_token": input_cost_per_token,
+        "output_cost_per_token": output_cost_per_token,
+    }
+    litellm.register_model(
+        model_cost={
+            deployment_id: {
+                "litellm_provider": "openai",
+                "mode": "chat",
+                "input_cost_per_token": input_cost_per_token,
+                "output_cost_per_token": output_cost_per_token,
+            }
+        },
+        persist_across_reloads=False,
+    )
+    try:
+        logging_obj: Final = LitellmLogging(
+            model="gpt-5.4-nano",
+            messages=[{"role": "user", "content": "Hi"}],
+            stream=False,
+            call_type="completion",
+            start_time=time.time(),
+            litellm_call_id="lit9660",
+            function_id="fn",
+        )
+        litellm_params: Final = {
+            "metadata": {
+                "model_group": "lit9660-group",
+                "deployment": "openai/gpt-5.4-nano",
+                "model_info": deployment_model_info,
+            }
+        }
+        logging_obj.update_environment_variables(
+            model="gpt-5.4-nano", user="", optional_params={}, litellm_params=litellm_params, custom_llm_provider="openai"
+        )
+        response: Final = ModelResponse(
+            model="gpt-5.4-nano",
+            choices=[litellm.Choices(message=litellm.Message(role="assistant", content="hi"))],
+            usage=litellm.Usage(prompt_tokens=10, completion_tokens=6, total_tokens=16),
+        )
+
+        response_cost: Final = logging_obj._response_cost_calculator(result=response)
+        payload: Final = get_standard_logging_object_payload(
+            kwargs={
+                "model": "gpt-5.4-nano",
+                "custom_llm_provider": "openai",
+                "litellm_params": litellm_params,
+                "response_cost": response_cost,
+            },
+            init_response_obj=response,
+            start_time=datetime.datetime.now(),
+            end_time=datetime.datetime.now(),
+            logging_obj=logging_obj,
+            status="success",
+        )
+
+        assert response_cost == 10 * input_cost_per_token + 6 * output_cost_per_token
+        assert payload is not None
+        assert payload["model_map_information"] == {
+            "model_map_key": "openai/gpt-5.4-nano",
+            "model_map_value": litellm.get_model_info(model=f"openai/{deployment_id}", custom_llm_provider="openai"),
+        }
+        model_map_value: Final = payload["model_map_information"]["model_map_value"]
+        assert model_map_value is not None
+        assert (model_map_value["input_cost_per_token"], model_map_value["output_cost_per_token"]) == (
+            input_cost_per_token,
+            output_cost_per_token,
+        )
+    finally:
+        litellm.model_cost.pop(deployment_id, None)
+
+
diff --git a/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py b/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py
index 895b3b57f7b..92c51f39345 100644
--- a/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py
+++ b/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py
@@ -205,6 +205,23 @@ class TestTheNormalizedTierIsTheTierSent:
     ):
         assert _reasoning_effort_sent(model, provider, effort) == expected
 
+    @pytest.mark.parametrize(
+        "model, provider",
+        [
+            ("gpt-5.5", "azure_ai"),
+            ("azure_ai/gpt-5.5", "azure_ai"),
+            ("gpt-5.6", "azure"),
+            ("us/gpt-5.6", "azure"),
+        ],
+    )
+    def test_an_azure_hosted_deployment_without_the_flag_drops_to_the_tier_it_accepts(
+        self, local_model_cost_map, model, provider
+    ):
+        """Chat Completions answers ``max`` on gpt-5.6 with a 400 naming ``none`` through ``xhigh``
+        (OpenAI, 2026-10-01) and none of these Azure rows declares the level, so the adapter sends
+        the tier below instead of the rejected one."""
+        assert _reasoning_effort_sent(model, provider, "max") == "xhigh"
+
     @pytest.mark.parametrize(
         "model, provider",
         [
@@ -212,13 +229,16 @@ class TestTheNormalizedTierIsTheTierSent:
             ("azure_ai/gpt-6-astra", "azure_ai"),
             ("gpt-6-astra", "azure"),
             ("us/gpt-6-astra", "azure"),
+            ("eu/gpt-6-astra", "azure"),
         ],
     )
-    def test_an_azure_hosted_astra_deployment_drops_to_the_tier_it_accepts(
-        self, local_model_cost_map, model, provider
-    ):
-        """The deployment answers ``max`` with a 400 naming ``none`` through ``xhigh``, so the rows
-        say so and the adapter sends the tier below instead of the rejected one."""
+    def test_an_azure_hosted_astra_deployment_drops_to_the_tier_its_chat_route_accepts(
+        self, local_model_cost_map: None, model: str, provider: str
+    ) -> None:
+        """A Foundry gpt-6-astra answers a Chat Completions ``max`` with a 400 naming low through
+        xhigh while honoring the same level on the Responses route (2026-10-01). The row's flag is
+        route-blind, so it keeps max off and the adapter, which cannot know which route the call
+        takes, sends the tier below instead of the level chat rejects."""
         assert _reasoning_effort_sent(model, provider, "max") == "xhigh"
 
     def test_the_openai_hosted_twin_still_sends_max(self, local_model_cost_map):
diff --git a/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py b/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py
index 3b3ef1a9cd4..a72417ce113 100644
--- a/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py
+++ b/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py
@@ -1,3 +1,6 @@
+from collections.abc import Mapping
+from typing import Final
+
 import pytest
 
 import litellm
@@ -343,17 +346,22 @@ def test_azure_gpt_6_astra_takes_the_reasoning_series_request_shape():
         model="gpt-6-astra",
         custom_llm_provider="azure",
         max_tokens=100,
-        reasoning_effort="max",
+        reasoning_effort="xhigh",
     )
     assert params["max_completion_tokens"] == 100
     assert "max_tokens" not in params
-    assert params["reasoning_effort"] == "max"
+    assert params["reasoning_effort"] == "xhigh"
 
 
-@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra"])
-def test_azure_gpt6_astra_reasoning_effort_none_unlocks_temperature(config: AzureOpenAIGPT5Config, model: str):
-    """Foundry's gpt-6-astra accepts reasoning_effort='none' and, only then, a non-default
-    temperature (verified live against a Foundry deployment), unlike OpenAI's gpt-6-astra."""
+@pytest.mark.parametrize("model", ["azure/gpt-6-sol", "azure/us/gpt-6-sol"])
+def test_azure_reasoning_effort_none_unlocks_temperature_off_the_azure_row(
+    config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch, model: str
+):
+    """A deployment whose azure/ row takes none accepts a non-default temperature with it, read off
+    that row even when OpenAI's twin row says the model refuses none."""
+    monkeypatch.setitem(
+        litellm.model_cost, "gpt-6-sol", {**litellm.model_cost["gpt-6-sol"], "supports_none_reasoning_effort": False}
+    )
     params = config.map_openai_params(
         non_default_params={"temperature": 0.2, "reasoning_effort": "none"},
         optional_params={},
@@ -365,14 +373,127 @@ def test_azure_gpt6_astra_reasoning_effort_none_unlocks_temperature(config: Azur
     assert params["reasoning_effort"] == "none"
 
 
-@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra"])
-def test_azure_gpt6_astra_rejects_reasoning_effort_minimal(config: AzureOpenAIGPT5Config, model: str):
-    """Foundry's gpt-6-astra lists none, low, medium, high, xhigh and max but not minimal."""
-    with pytest.raises(litellm.utils.UnsupportedParamsError):
-        config.map_openai_params(
-            non_default_params={"reasoning_effort": "minimal"},
+def _azure_chat_row_forwards(row: Mapping[str, object], level: str) -> bool:
+    """Azure chat polarity: max is never gated, xhigh and none need an explicit true, every other
+    level only has to not be false."""
+    if level == "max":
+        return True
+    flag: Final = row.get(f"supports_{level}_reasoning_effort")
+    return flag is True if level in ("xhigh", "none") else flag is not False
+
+
+@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra", "azure/eu/gpt-6-astra"])
+@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+def test_azure_gpt6_astra_forwards_exactly_the_effort_levels_its_map_row_allows(
+    config: AzureOpenAIGPT5Config, model: str, level: str
+):
+    """The azure/ row is the whole contract for a Foundry deployment. A live Foundry gpt-6-astra
+    (model gpt-6-astra-2026-09-03) answered reasoning_effort none with a 400 naming low, medium,
+    high and xhigh on 2026-10-01, so its row turns none and minimal off. The row keeps max off too,
+    since chat refuses it, but no gate reads that flag: the Responses route honors max, so chat
+    forwards it for the bridge and a plain chat call gets the provider's own 400."""
+    forwarded: Final = _azure_chat_row_forwards(litellm.model_cost[model], level)
+    dropped: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": level},
+        optional_params={},
+        model=model,
+        drop_params=True,
+        api_version="2025-04-01-preview",
+    )
+    assert ("reasoning_effort" in dropped) is forwarded
+    if forwarded:
+        kept: Final = config.map_openai_params(
+            non_default_params={"reasoning_effort": level},
             optional_params={},
             model=model,
             drop_params=False,
             api_version="2025-04-01-preview",
         )
+        assert kept["reasoning_effort"] == level
+    else:
+        with pytest.raises(litellm.utils.UnsupportedParamsError):
+            config.map_openai_params(
+                non_default_params={"reasoning_effort": level},
+                optional_params={},
+                model=model,
+                drop_params=False,
+                api_version="2025-04-01-preview",
+            )
+
+
+@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra", "azure/eu/gpt-6-astra"])
+def test_azure_gpt6_astra_row_turns_none_and_minimal_off(model: str):
+    """Pinned on purpose so the row-derived test above cannot go vacuous: a Foundry gpt-6-astra
+    deployment refused none on chat and on Responses on 2026-10-01 (400 unsupported_value naming
+    low, medium, high, xhigh), and minimal the same way; max it refused on chat while honoring it
+    on Responses, so the route-blind flag stays off. When Azure adds a level, flip the row and
+    this assertion together."""
+    row: Final = litellm.model_cost[model]
+    assert row["supports_none_reasoning_effort"] is False
+    assert row["supports_minimal_reasoning_effort"] is False
+    assert row["supports_max_reasoning_effort"] is False
+
+
+def test_azure_chat_gate_reads_the_foundry_row_when_azure_ai_prefix_survives_provider_remap(
+    config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch
+):
+    """A Foundry deployment on an OpenAI-v1 host is re-routed to the azure provider with its
+    azure_ai/ prefix intact, and this config then gates it. The rows are made to disagree on low,
+    a level neither real row flags, so the prefixed name has to read azure_ai/gpt-6-sol while the
+    bare deployment name keeps reading azure/gpt-6-sol."""
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure_ai/gpt-6-sol",
+        {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False},
+    )
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure/gpt-6-sol",
+        {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True},
+    )
+    prefixed: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": "low"},
+        optional_params={},
+        model="azure_ai/gpt-6-sol",
+        drop_params=True,
+        api_version="2025-04-01-preview",
+    )
+    assert "reasoning_effort" not in prefixed
+    bare: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": "low"},
+        optional_params={},
+        model="gpt-6-sol",
+        drop_params=True,
+        api_version="2025-04-01-preview",
+    )
+    assert bare["reasoning_effort"] == "low"
+
+
+def test_azure_chat_gate_falls_back_to_the_azure_row_for_an_azure_ai_name_the_map_lacks(
+    config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch
+):
+    monkeypatch.delitem(litellm.model_cost, "azure_ai/gpt-6-sol")
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure/gpt-6-sol",
+        {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": False},
+    )
+    dropped: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": "low"},
+        optional_params={},
+        model="azure_ai/gpt-6-sol",
+        drop_params=True,
+        api_version="2025-04-01-preview",
+    )
+    assert "reasoning_effort" not in dropped
+
+
+@pytest.mark.parametrize("key", ["azure/gpt-6.1-sol", "azure/gpt-6.1-sol-2026-09-29", "azure_ai/gpt-6.1-sol"])
+def test_azure_gpt61_sol_rows_turn_none_off(key: str):
+    """Pinned on purpose, as the astra row above: a Foundry gpt-6.1-sol deployment (model
+    gpt-6.1-sol-2026-09-29) refused none on chat and on Responses on 2026-10-02 (400 unsupported_value
+    naming low, medium, high, xhigh, and max on Responses), and minimal the same way, while these rows
+    still said none was on. When Azure adds a level, flip the row and this assertion together."""
+    row: Final = litellm.model_cost[key]
+    assert row["supports_none_reasoning_effort"] is False
+    assert row["supports_minimal_reasoning_effort"] is False
diff --git a/tests/unit/llms/azure/response/test_azure_transformation.py b/tests/unit/llms/azure/response/test_azure_transformation.py
index 532c278e891..447efeee117 100644
--- a/tests/unit/llms/azure/response/test_azure_transformation.py
+++ b/tests/unit/llms/azure/response/test_azure_transformation.py
@@ -651,16 +651,21 @@ def local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> None:
     litellm.add_known_models(model_cost_map=litellm.model_cost)
 
 
-def test_azure_responses_gpt6_astra_reasoning_effort_none_unlocks_temperature(local_model_cost_map: None):
-    """Foundry's gpt-6-astra accepts reasoning.effort='none' with a non-default temperature
-    while OpenAI's gpt-6-astra does not, so the gate must read the azure/ cost-map entry
-    for the bare deployment name rather than OpenAI's."""
+def test_azure_responses_reasoning_effort_none_unlocks_temperature_off_the_azure_row(
+    local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+):
+    """The gate reads the azure/ cost-map entry for the bare deployment name rather than OpenAI's
+    twin: with OpenAI's gpt-6-sol row turned off for none, azure/gpt-6-sol's row still lets none
+    through and, only then, a non-default temperature."""
+    monkeypatch.setitem(
+        litellm.model_cost, "gpt-6-sol", {**litellm.model_cost["gpt-6-sol"], "supports_none_reasoning_effort": False}
+    )
     params = AzureOpenAIResponsesAPIConfig().map_openai_params(
         response_api_optional_params=ResponsesAPIOptionalRequestParams(
             temperature=0.2,
             reasoning={"effort": "none"},
         ),
-        model="gpt-6-astra",
+        model="gpt-6-sol",
         drop_params=False,
     )
     assert params["temperature"] == 0.2
@@ -679,6 +684,116 @@ def test_azure_responses_gpt6_astra_rejects_temperature_while_reasoning(local_mo
         )
 
 
+@pytest.mark.parametrize("model", ["gpt-6-astra", "gpt-6.1-sol"])
+@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+def test_azure_responses_gpt6_effort_levels_follow_the_azure_row(local_model_cost_map: None, model: str, level: str):
+    """A bare deployment name reads the azure/ row, opt-out for every level but max, so the none
+    and minimal Foundry refuses on this route (live 400s on 2026-10-01 for gpt-6-astra and 2026-10-02
+    for gpt-6.1-sol) are dropped or refused here while the max it honors goes through whatever the
+    route-blind flag says."""
+    forwarded = (
+        level == "max" or litellm.model_cost[f"azure/{model}"].get(f"supports_{level}_reasoning_effort") is not False
+    )
+    dropped = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}),
+        model=model,
+        drop_params=True,
+    )
+    assert ("reasoning" in dropped) is forwarded
+    if forwarded:
+        kept = AzureOpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}),
+            model=model,
+            drop_params=False,
+        )
+        assert kept["reasoning"] == {"effort": level}
+    else:
+        with pytest.raises(litellm.UnsupportedParamsError):
+            AzureOpenAIResponsesAPIConfig().map_openai_params(
+                response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}),
+                model=model,
+                drop_params=False,
+            )
+
+
+def test_azure_gpt6_astra_keeps_max_on_this_route_whatever_its_row_says(local_model_cost_map: None):
+    """Pinned on purpose: the row-derived test above exempts max by hand, so this one has to fail
+    if the gate ever reads the flag. A Foundry gpt-6-astra deployment answered reasoning.effort max
+    through /v1/responses with 200, the effort echoed back and reasoning tokens billed, on
+    2026-10-01, while chat refuses the same level, as OpenAI's chat does. The row keeps max off for
+    the adapter and the picker, and this gate still forwards it even under drop_params."""
+    assert litellm.model_cost["azure/gpt-6-astra"]["supports_max_reasoning_effort"] is False
+    kept = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "max"}),
+        model="gpt-6-astra",
+        drop_params=True,
+    )
+    assert kept["reasoning"] == {"effort": "max"}
+
+
+@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+def test_azure_responses_effort_gate_fires_when_azure_ai_prefix_survives_provider_remap(
+    local_model_cost_map: None, level: str
+):
+    """litellm.responses(model="azure_ai/gpt-6.1-sol", api_base=<Foundry host>) is re-routed to the
+    azure provider with the prefix intact, so this config sees the prefixed name. The gate used to
+    skip every prefixed name as another provider's pass-through, and a live Foundry gpt-6.1-sol
+    answered the forwarded none and minimal with 400 on 2026-10-02 even under drop_params. The
+    prefixed name reads the azure_ai/ row and drops or refuses exactly what that row turns off."""
+    forwarded = (
+        level == "max"
+        or litellm.model_cost["azure_ai/gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is not False
+    )
+    dropped = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=ResponsesAPIOptionalRequestParams(
+            max_output_tokens=60, reasoning={"effort": level}
+        ),
+        model="azure_ai/gpt-6.1-sol",
+        drop_params=True,
+    )
+    assert ("reasoning" in dropped) is forwarded
+    if forwarded:
+        return
+    with pytest.raises(litellm.UnsupportedParamsError):
+        AzureOpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params=ResponsesAPIOptionalRequestParams(
+                max_output_tokens=60, reasoning={"effort": level}
+            ),
+            model="azure_ai/gpt-6.1-sol",
+            drop_params=False,
+        )
+
+
+def test_azure_responses_prefixed_name_reads_the_foundry_row_not_the_azure_twin(
+    local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+):
+    """The rows are made to disagree on low, a level neither real row flags, so the prefixed name
+    proving it reads azure_ai/gpt-6-sol cannot pass by reading azure/gpt-6-sol, which the bare
+    deployment name keeps reading."""
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure_ai/gpt-6-sol",
+        {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False},
+    )
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure/gpt-6-sol",
+        {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True},
+    )
+    prefixed = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "low"}),
+        model="azure_ai/gpt-6-sol",
+        drop_params=True,
+    )
+    assert "reasoning" not in prefixed
+    bare = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "low"}),
+        model="gpt-6-sol",
+        drop_params=True,
+    )
+    assert bare["reasoning"] == {"effort": "low"}
+
+
 def test_azure_responses_sends_the_deployment_name_when_azure_ai_prefix_survives_provider_remap():
     request = AzureOpenAIResponsesAPIConfig().transform_responses_api_request(
         model="azure_ai/gpt-5.4-nano",
diff --git a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py
index 47609261a25..b229fb857d7 100644
--- a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py
+++ b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py
@@ -146,17 +146,30 @@ def _local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setattr(litellm, "model_cost", get_model_cost_map(url=litellm.model_cost_map_url))
 
 
-def test_foundry_gpt_6_astra_keeps_sampling_params_when_reasoning_effort_is_none(_local_model_cost_map):
+def test_foundry_gpt_6_sol_keeps_sampling_params_when_reasoning_effort_is_none(_local_model_cost_map):
+    """gpt-6-sol's Foundry row still says none, so the sampling params that ride on it stay. gpt-6-astra
+    used to be the model here until its row turned none off (a live Foundry deployment answered none
+    with a 400 naming low through xhigh on 2026-10-01); the test below pins that flip."""
     optional_params = AzureAIStudioConfig().map_openai_params(
         non_default_params={"reasoning_effort": "none", "temperature": 0.2, "top_p": 0.9},
         optional_params={},
-        model="gpt-6-astra",
+        model="gpt-6-sol",
         drop_params=False,
     )
 
     assert optional_params == {"reasoning_effort": "none", "temperature": 0.2, "top_p": 0.9}
 
 
+def test_foundry_gpt_6_astra_refuses_reasoning_effort_none_before_the_call(_local_model_cost_map):
+    with pytest.raises(litellm.utils.UnsupportedParamsError):
+        AzureAIStudioConfig().map_openai_params(
+            non_default_params={"reasoning_effort": "none"},
+            optional_params={},
+            model="gpt-6-astra",
+            drop_params=False,
+        )
+
+
 
 
 def test_azure_ai_grok_stop_parameter_handling():
diff --git a/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py b/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
index b78b2d0d842..121a4000155 100644
--- a/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
+++ b/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
@@ -7,13 +7,17 @@ sys.path.insert(
     0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../../.."))
 )
 
+from typing import Final
 from unittest.mock import patch
 
+import httpx
 import pytest
 
+import litellm
 from litellm.llms.azure_ai.anthropic.messages_transformation import (
     AzureAnthropicMessagesConfig,
 )
+from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
 from litellm.types.router import GenericLiteLLMParams
 
 
@@ -470,3 +474,51 @@ def test_azure_claude_4_8_plus_cost_map_entries_carry_mid_conversation_system_fl
         and info.get("supports_mid_conversation_system") is not True
     ]
     assert missing == []
+
+
+AUTO_MODE_SAFEGUARDS: Final = ({"type": "dangerous_tool_use", "classifier_context": {"v": 1, "permission_mode": "auto"}},)
+
+
+@pytest.mark.usefixtures("local_beta_headers_config")
+@pytest.mark.parametrize(
+    ("client_headers", "optional_params", "expected_beta"),
+    [
+        ({}, {"safeguards": AUTO_MODE_SAFEGUARDS}, "dangerous-tool-use-2026-09-03"),
+        (
+            {"anthropic-beta": "context-1m-2025-08-07"},
+            {"safeguards": AUTO_MODE_SAFEGUARDS},
+            "context-1m-2025-08-07,dangerous-tool-use-2026-09-03",
+        ),
+        ({"anthropic-beta": "context-1m-2025-08-07"}, {}, "context-1m-2025-08-07"),
+        ({}, {}, None),
+    ],
+)
+def test_safeguards_request_carries_the_dangerous_tool_use_beta_without_the_client_header(
+    client_headers: dict[str, str], optional_params: dict[str, object], expected_beta: str | None
+) -> None:
+    headers, _ = AzureAnthropicMessagesConfig().validate_anthropic_messages_environment(
+        headers=client_headers,
+        model="claude-sonnet-4-6",
+        messages=[{"role": "user", "content": "Run ls -la with the Bash tool"}],
+        optional_params=optional_params,
+        litellm_params={"api_key": "test-api-key"},
+    )
+    assert headers.get("anthropic-beta") == expected_beta, headers
+
+
+def _foundry_answer(request: httpx.Request) -> httpx.Response:
+    return httpx.Response(
+        status_code=200,
+        headers={"content-type": "application/json"},
+        json={
+            "id": "msg_safeguards",
+            "type": "message",
+            "role": "assistant",
+            "model": "claude-sonnet-4-6",
+            "content": [{"type": "text", "text": "hello from the gateway"}],
+            "stop_reason": "end_turn",
+            "stop_sequence": None,
+            "usage": {"input_tokens": 12, "output_tokens": 6},
+        },
+        request=request,
+    )
diff --git a/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py b/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py
index bae956eb061..26076f8bb34 100644
--- a/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py
+++ b/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py
@@ -1,12 +1,15 @@
 import json
+from typing import Final
 
 import httpx
 import pytest
 import respx
 
 import litellm
+from litellm.llms.azure.responses.transformation import AzureOpenAIResponsesAPIConfig
 from litellm.llms.azure_ai.responses.transformation import AzureAIResponsesAPIConfig
 from litellm.responses.main import _will_bridge_to_chat_completions
+from litellm.types.llms.openai import ResponsesAPIOptionalRequestParams
 from litellm.types.router import GenericLiteLLMParams
 from litellm.utils import ProviderConfigManager
 
@@ -309,3 +312,74 @@ async def test_aresponses_serverless_host_stays_on_chat_bridge():
     assert chat_route.called
     assert not responses_route.called
     assert chat_route.calls.last.request.headers["Authorization"] == "Bearer fake-key"
+
+
+def _responses_params(**fields: object) -> ResponsesAPIOptionalRequestParams:
+    return ResponsesAPIOptionalRequestParams(**fields)  # pyright: ignore[reportArgumentType]  # TypedDict kwargs from a test helper
+
+
+def test_foundry_responses_effort_gate_reads_the_azure_ai_row(
+    local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+):
+    """A Foundry deployment and its Azure OpenAI namesake are different products, so the Foundry
+    Responses route answers from the azure_ai/ row the Foundry chat route already reads, never from
+    the azure/ twin. The rows are made to disagree on low, a level neither real row flags, so a
+    leak from the wrong row cannot hide behind rows that happen to agree."""
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure_ai/gpt-6-sol",
+        {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False},
+    )
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure/gpt-6-sol",
+        {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True},
+    )
+
+    dropped: Final = AzureAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=_responses_params(reasoning={"effort": "low"}),
+        model="gpt-6-sol",
+        drop_params=True,
+    )
+    assert "reasoning" not in dropped
+
+    with pytest.raises(litellm.UnsupportedParamsError):
+        AzureAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params=_responses_params(reasoning={"effort": "low"}),
+            model="gpt-6-sol",
+            drop_params=False,
+        )
+
+    kept_by_azure_openai: Final = AzureOpenAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=_responses_params(reasoning={"effort": "low"}),
+        model="gpt-6-sol",
+        drop_params=True,
+    )
+    assert kept_by_azure_openai["reasoning"] == {"effort": "low"}
+
+
+def test_foundry_responses_none_unlocks_temperature_off_the_azure_ai_row(
+    local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+):
+    """The sampling-param unlock that rides on none reads the same azure_ai/ row as the effort gate:
+    with the azure/ twin turned off for none, the Foundry row still lets none through and, only
+    then, a non-default temperature."""
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure_ai/gpt-6-sol",
+        {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_none_reasoning_effort": True},
+    )
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "azure/gpt-6-sol",
+        {**litellm.model_cost["azure/gpt-6-sol"], "supports_none_reasoning_effort": False},
+    )
+
+    params: Final = AzureAIResponsesAPIConfig().map_openai_params(
+        response_api_optional_params=_responses_params(temperature=0.2, reasoning={"effort": "none"}),
+        model="gpt-6-sol",
+        drop_params=False,
+    )
+
+    assert params["temperature"] == 0.2
+    assert params["reasoning"] == {"effort": "none"}
diff --git a/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py b/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py
index 08bcac33a35..93320b62083 100644
--- a/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py
+++ b/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py
@@ -16,6 +16,8 @@ import pytest
 from botocore.credentials import Credentials
 from botocore.exceptions import ClientError
 
+import litellm
+
 from litellm.llms.bedrock.chat.converse_handler import BedrockConverseLLM
 from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
 from litellm.rust_bridge import configuration
@@ -273,3 +275,44 @@ def test_session_tags_sign_the_request_and_stay_out_of_the_body(monkeypatch):
     sent = client.post.call_args.kwargs
     assert "Credential=ASIACONVERSETAGGED/" in sent["headers"]["Authorization"]
     assert "aws_session_tags" not in sent["data"]
+
+
+@pytest.mark.parametrize("stream", (False, True))
+def test_converse_profile_override_records_cost_without_changing_response_model(
+    monkeypatch: pytest.MonkeyPatch, stream: bool
+) -> None:
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    monkeypatch.setenv("LITELLM_RUST", "0")
+    configuration.rust(False)
+    model: Final = "openai.gpt-5.6-sol"
+    profile: Final = f"us.{model}"
+    prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock")
+
+    def respond(request: httpx.Request) -> httpx.Response:
+        assert request.url.path == f"/model/{profile}/converse"
+        return httpx.Response(200, json=CONVERSE_RESPONSE)
+
+    with httpx.Client(transport=httpx.MockTransport(respond)) as transport:
+        response: Final = litellm.completion(
+            model=f"bedrock/converse/{model}",
+            model_id=profile,
+            messages=[{"role": "user", "content": "hi"}],
+            api_key="test-bearer",
+            aws_region_name="us-east-1",
+            client=HTTPHandler(client=transport),
+            stream=stream,
+            fake_stream=stream,
+            max_tokens=16,
+        )
+        result: Final = litellm.stream_chunk_builder(list(response)) if stream else response
+
+    assert result is not None
+    assert result.model == model
+    assert result.choices[0].message.content == "hi"
+    cost: Final = (
+        response.logging_obj._response_cost_calculator(result) if stream else result._hidden_params.get("response_cost")
+    )
+    assert cost == pytest.approx(
+        CONVERSE_RESPONSE["usage"]["inputTokens"] * prices["input_cost_per_token"]
+        + CONVERSE_RESPONSE["usage"]["outputTokens"] * prices["output_cost_per_token"]
+    )
diff --git a/tests/unit/llms/bedrock/chat/test_converse_transformation.py b/tests/unit/llms/bedrock/chat/test_converse_transformation.py
index 499096621c5..b31cb8693ba 100644
--- a/tests/unit/llms/bedrock/chat/test_converse_transformation.py
+++ b/tests/unit/llms/bedrock/chat/test_converse_transformation.py
@@ -5764,6 +5764,67 @@ def test_transform_response_finish_reason_stop_when_json_mode_filters_all_tools(
     assert result.choices[0].finish_reason == "stop"
 
 
+def test_transform_response_json_mode_truncated_tool_call_keeps_length_finish_reason():
+    """
+    When json_mode filters out the synthetic json_tool_call but Bedrock
+    stopped on max_tokens, finish_reason must stay "length", not be
+    downgraded to "stop" — otherwise truncated structured output looks
+    completed.
+    """
+    from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
+    from litellm.types.utils import ModelResponse
+
+    response_json = {
+        "metrics": {"latencyMs": 100},
+        "output": {
+            "message": {
+                "role": "assistant",
+                "content": [
+                    {
+                        "toolUse": {
+                            "toolUseId": "tooluse_001",
+                            "name": "json_tool_call",
+                            "input": {"a": "cut"},
+                        }
+                    }
+                ],
+            }
+        },
+        "stopReason": "max_tokens",
+        "usage": {
+            "inputTokens": 10,
+            "outputTokens": 60,
+            "totalTokens": 70,
+        },
+    }
+
+    class MockResponse:
+        def json(self) -> dict[str, object]:
+            return response_json
+
+        @property
+        def text(self) -> str:
+            return json.dumps(response_json)
+
+    config = AmazonConverseConfig()
+    model_response = ModelResponse()
+
+    result = config._transform_response(
+        model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        response=MockResponse(),
+        model_response=model_response,
+        stream=False,
+        logging_obj=None,
+        optional_params={"json_mode": True},
+        api_key=None,
+        data=None,
+        messages=[],
+        encoding=None,
+    )
+
+    assert result.choices[0].finish_reason == "length"
+
+
 def test_transform_response_citations_content_maps_to_annotations():
     from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
     from litellm.types.utils import ModelResponse
diff --git a/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py b/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py
index 20bf65ee385..a20444ceca5 100644
--- a/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py
+++ b/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py
@@ -634,4 +634,8 @@ class TestAgentCoreSearchEdgeCases:
         from litellm.search.cost_calculator import search_provider_cost_per_query
 
         monkeypatch.setattr(litellm, "model_cost", GetModelCostMap.load_local_model_cost_map())
-        assert search_provider_cost_per_query(model="agentcore/search", custom_llm_provider="agentcore") == (0.0, 0.0)
+        price_per_query = litellm.model_cost["agentcore/search"]["input_cost_per_query"]
+        assert price_per_query > 0
+        assert search_provider_cost_per_query(
+            model="agentcore/search", custom_llm_provider="agentcore", number_of_queries=3
+        ) == (3 * price_per_query, 0.0)
diff --git a/tests/unit/llms/custom_httpx/test_llm_http_handler.py b/tests/unit/llms/custom_httpx/test_llm_http_handler.py
index 1dc5f717b04..82d1f76a7eb 100644
--- a/tests/unit/llms/custom_httpx/test_llm_http_handler.py
+++ b/tests/unit/llms/custom_httpx/test_llm_http_handler.py
@@ -4302,3 +4302,45 @@ async def test_async_text_to_speech_handler_records_upstream_response_headers():
 
     assert response.content == b"audio-bytes"
     _assert_upstream_headers_recorded(response)
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("local_beta_headers_config")
+async def test_anthropic_messages_dropped_safeguards_send_neither_the_field_nor_its_beta() -> None:
+    received: Final[list[httpx.Request]] = []
+
+    def anthropic_answers(request: httpx.Request) -> httpx.Response:
+        received.append(request)
+        return httpx.Response(
+            status_code=200,
+            json={
+                "id": "msg_dropped_safeguards",
+                "type": "message",
+                "role": "assistant",
+                "model": "claude-sonnet-4-6",
+                "content": [{"type": "text", "text": "hi"}],
+                "stop_reason": "end_turn",
+                "stop_sequence": None,
+                "usage": {"input_tokens": 5, "output_tokens": 1},
+            },
+            request=request,
+        )
+
+    upstream: Final = AsyncHTTPHandler(transport=httpx.MockTransport(anthropic_answers))
+    try:
+        await litellm.anthropic.messages.acreate(
+            max_tokens=16,
+            messages=[{"role": "user", "content": "hi"}],
+            model="anthropic/claude-sonnet-4-6",
+            api_key="sk-ant-test",
+            safeguards=({"type": "dangerous_tool_use"},),
+            additional_drop_params=["safeguards"],
+            client=upstream,
+        )
+    finally:
+        await upstream.close()
+
+    assert len(received) == 1, received
+    sent: Final = received[0]
+    assert "safeguards" not in json.loads(sent.content)
+    assert "dangerous-tool-use-2026-09-03" not in sent.headers.get("anthropic-beta", ""), dict(sent.headers)
diff --git a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py
index 9cd17bd3580..dfa8538c387 100644
--- a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py
+++ b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py
@@ -1,7 +1,10 @@
+import copy
 import json
 
 import pytest
+from pydantic import TypeAdapter
 from fastapi.testclient import TestClient
+from pydantic import BaseModel, ConfigDict
 
 from unittest.mock import MagicMock, patch
 
@@ -16,11 +19,33 @@ from litellm.llms.databricks.chat.transformation import (
     DatabricksConfig,
     _sanitize_empty_content,
 )
+from litellm.types.llms.openai import AllMessageValues
 from typing import Final
 import httpx
 import respx
 
 
+JSON_SCHEMA_RESPONSE_FORMAT: Final = {
+    "type": "json_schema",
+    "json_schema": {
+        "name": "P",
+        "strict": True,
+        "schema": {
+            "$defs": {
+                "Person": {
+                    "type": "object",
+                    "properties": {"name": {"type": "string"}},
+                    "required": ["name"],
+                }
+            },
+            "type": "object",
+            "properties": {"p": {"$ref": "#/$defs/Person"}},
+            "required": ["p"],
+        },
+    },
+}
+
+
 @pytest.fixture()
 def _use_local_model_cost_map(monkeypatch):
     monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
@@ -283,6 +308,119 @@ def test_transform_request_preserves_unity_model_service_name():
     assert result["model"] == "system.ai.kimi-k3"
 
 
+@pytest.mark.parametrize(
+    "model,messages,optional_params,expected_content",
+    [
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            {"response_format": {"type": "json_object"}},
+            "Reply in JSON",
+            id="user",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"role": "system", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            {"response_format": {"type": "json_object"}},
+            "Reply in JSON",
+            id="system",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"role": "assistant", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            {"response_format": {"type": "json_object"}},
+            "Reply in JSON",
+            id="assistant",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [
+                {
+                    "role": "tool",
+                    "tool_call_id": "call_1",
+                    "content": [{"type": "text", "text": "Reply in JSON"}],
+                }
+            ],
+            {"response_format": {"type": "json_object"}},
+            "Reply in JSON",
+            id="tool",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [
+                {
+                    "role": "user",
+                    "content": [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}],
+                }
+            ],
+            {"response_format": {"type": "json_object"}},
+            [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}],
+            id="cache-control",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"role": "user", "content": [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}]}],
+            {"response_format": {"type": "json_object"}},
+            [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}],
+            id="multiple-text-blocks",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "Reply in JSON"},
+                        {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}},
+                    ],
+                }
+            ],
+            {"response_format": {"type": "json_object"}},
+            [
+                {"type": "text", "text": "Reply in JSON"},
+                {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}},
+            ],
+            id="text-and-image",
+        ),
+        pytest.param(
+            "databricks-meta-llama-3-3-70b-instruct",
+            [{"role": "user", "content": "Reply in JSON"}],
+            {"response_format": {"type": "json_object"}},
+            "Reply in JSON",
+            id="plain-string",
+        ),
+        pytest.param(
+            "databricks-claude-sonnet-5",
+            [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}],
+            {"response_format": {"type": "json_object"}},
+            [{"type": "text", "text": "Reply in JSON"}],
+            id="claude",
+        ),
+    ],
+)
+def test_transform_request_collapses_single_plain_text_block_for_non_claude_models(
+    model: str,
+    messages: list[AllMessageValues],
+    optional_params: dict[str, object],
+    expected_content: object,
+) -> None:
+    config: Final[DatabricksConfig] = DatabricksConfig()
+    result: Final[dict[str, object]] = TypeAdapter(dict[str, object]).validate_python(
+        config.transform_request(  # pyright: ignore[reportUnknownMemberType]  # inherited hook is untyped
+            model=model,
+            messages=messages,
+            optional_params=optional_params,
+            litellm_params={},
+            headers={},
+        )
+    )
+    outgoing_messages: Final[list[dict[str, object]]] = TypeAdapter(list[dict[str, object]]).validate_python(
+        result["messages"]
+    )
+
+    assert outgoing_messages == [{**messages[0], "content": expected_content}]
+
+
 def test_transform_request_strips_thinking_blocks_and_reasoning_content():
     """Regression for LIT-6762: replaying an assistant turn that litellm decorated with
     `thinking_blocks` / `reasoning_content` made Databricks 400 with
@@ -883,3 +1021,69 @@ def test_completion_merges_system_messages_when_one_has_empty_content(respx_mock
         {"role": "system", "content": "You are terse."},
         {"role": "user", "content": "Hello"},
     ]
+
+
+@pytest.mark.parametrize(
+    "model",
+    (
+        "databricks-meta-llama-3-3-70b-instruct",
+        "databricks-qwen35-122b-a10b",
+        "databricks-gpt-oss-120b",
+        "system.ai.deepseek-v4-1-flash",
+    ),
+)
+def test_databricks_non_claude_json_schema_preserves_refs(model: str) -> None:
+    optional_params: Final = litellm.utils.get_optional_params(
+        model=model,
+        custom_llm_provider="databricks",
+        response_format=copy.deepcopy(JSON_SCHEMA_RESPONSE_FORMAT),
+    )
+
+    assert optional_params["response_format"] == JSON_SCHEMA_RESPONSE_FORMAT
+
+
+def test_databricks_claude_json_schema_preserves_refs_in_tool_parameters() -> None:
+    optional_params: Final = litellm.utils.get_optional_params(
+        model="databricks-claude-haiku-4-5",
+        custom_llm_provider="databricks",
+        response_format=copy.deepcopy(JSON_SCHEMA_RESPONSE_FORMAT),
+    )
+
+    assert "response_format" not in optional_params
+    assert optional_params["tools"] == [
+        {
+            "type": "function",
+            "function": {
+                "name": "json_tool_call",
+                "parameters": JSON_SCHEMA_RESPONSE_FORMAT["json_schema"]["schema"],
+            },
+        }
+    ]
+
+
+def test_databricks_pydantic_json_schema_preserves_nested_refs() -> None:
+    class Person(BaseModel):
+        model_config = ConfigDict(frozen=True)
+
+        name: str
+
+    class Order(BaseModel):
+        model_config = ConfigDict(frozen=True)
+
+        person: Person
+
+    optional_params: Final = litellm.utils.get_optional_params(
+        model="databricks-meta-llama-3-3-70b-instruct",
+        custom_llm_provider="databricks",
+        response_format=Order,
+    )
+    schema: Final = optional_params["response_format"]["json_schema"]["schema"]
+
+    assert schema["properties"]["person"] == {"$ref": "#/$defs/Person"}
+    assert schema["$defs"]["Person"] == {
+        "additionalProperties": False,
+        "properties": {"name": {"title": "Name", "type": "string"}},
+        "required": ["name"],
+        "title": "Person",
+        "type": "object",
+    }
diff --git a/tests/unit/llms/databricks/test_databricks_cost_calculator.py b/tests/unit/llms/databricks/test_databricks_cost_calculator.py
index de0e547c0cd..494b99c1d11 100644
--- a/tests/unit/llms/databricks/test_databricks_cost_calculator.py
+++ b/tests/unit/llms/databricks/test_databricks_cost_calculator.py
@@ -16,6 +16,7 @@ NEW_MODELS: Final = (
     "databricks/databricks-claude-opus-4-7",
     "databricks/databricks-claude-opus-4-8",
     "databricks/databricks-claude-opus-5",
+    "databricks/databricks-claude-opus-5-5",
     "databricks/databricks-claude-sonnet-5",
     "databricks/databricks-claude-fable-5",
     "databricks/databricks-claude-fable-5-1",
@@ -32,6 +33,7 @@ PRICE_FIELDS: Final = (
     "cache_read_input_token_cost",
 )
 PUBLISHED_DBU_PER_MILLION: Final = {
+    "databricks/databricks-claude-opus-5-5": ("57.143", "285.714", "71.429", "2.857"),
     "databricks/databricks-claude-fable-5-1": ("142.858", "714.286", "178.572", "3.572"),
     "databricks/databricks-claude-fable-5": ("142.858", "714.286", "178.572", "14.286"),
     "databricks/databricks-claude-opus-5": ("71.429", "357.143", "89.286", "7.143"),
@@ -118,6 +120,7 @@ def _dollars_per_token(dbu_per_million: str) -> float:
     [
         "databricks/databricks-claude-opus-4-8",
         "databricks/databricks-claude-opus-5",
+        "databricks/databricks-claude-opus-5-5",
         "databricks/databricks-claude-sonnet-5",
     ],
 )
diff --git a/tests/unit/llms/openai/responses/test_openai_responses_transformation.py b/tests/unit/llms/openai/responses/test_openai_responses_transformation.py
index 0ef45501d91..3bc3d12db2b 100644
--- a/tests/unit/llms/openai/responses/test_openai_responses_transformation.py
+++ b/tests/unit/llms/openai/responses/test_openai_responses_transformation.py
@@ -1858,6 +1858,115 @@ class TestResponsesSurfaceSharesTheEffortRule:
         )
         assert ("top_p" in mapped) is top_p_survives
 
+    @pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+    def test_effort_levels_the_map_row_turns_off_are_dropped_or_refused(self, local_model_cost_map, level):
+        """Same row as the chat gate, read opt-out for every level but max. gpt-6.1-sol's row turns
+        none and minimal off: OpenAI lists low, medium, high, xhigh and max for it
+        (https://developers.openai.com/api/docs/models/gpt-6.1-sol, via #43910), and a local proxy
+        got OpenAI's 400 for none and minimal through /v1/responses on 2026-09-30."""
+        forwarded = (
+            level == "max" or litellm.model_cost["gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is not False
+        )
+        dropped = OpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params={"reasoning": {"effort": level}},
+            model="gpt-6.1-sol",
+            drop_params=True,
+        )
+        assert ("reasoning" in dropped) is forwarded
+        if forwarded:
+            kept = OpenAIResponsesAPIConfig().map_openai_params(
+                response_api_optional_params={"reasoning": {"effort": level}},
+                model="gpt-6.1-sol",
+                drop_params=False,
+            )
+            assert kept["reasoning"] == {"effort": level}
+        else:
+            with pytest.raises(litellm.UnsupportedParamsError):
+                OpenAIResponsesAPIConfig().map_openai_params(
+                    response_api_optional_params={"reasoning": {"effort": level}},
+                    model="gpt-6.1-sol",
+                    drop_params=False,
+                )
+
+    @pytest.mark.parametrize(
+        ("flags", "level", "forwarded"),
+        [
+            ({}, "none", True),
+            ({"supports_none_reasoning_effort": False}, "none", False),
+            ({"supports_none_reasoning_effort": True}, "none", True),
+            ({"supports_minimal_reasoning_effort": False}, "minimal", False),
+            ({"supports_max_reasoning_effort": False}, "max", True),
+            ({}, "xhigh", True),
+            ({"supports_xhigh_reasoning_effort": False}, "xhigh", False),
+            ({"supports_none_reasoning_effort": False}, "medium", True),
+        ],
+    )
+    def test_the_row_flags_alone_decide_whether_a_level_is_forwarded(
+        self, local_model_cost_map, monkeypatch, flags, level, forwarded
+    ):
+        """Same model name, rewritten row: this surface reads every level opt-out, xhigh included,
+        so the gate flips with the flags alone. max is the one level no flag can turn off here,
+        since the same model honors it on this route and refuses it on chat. The chat test module
+        pins the real row's facts."""
+        real_row = litellm.model_cost["gpt-6.1-sol"]
+        without_flags = {
+            field: value
+            for field, value in real_row.items()
+            if not (field.startswith("supports_") and field.endswith("_reasoning_effort"))
+        }
+        monkeypatch.setitem(litellm.model_cost, "gpt-6.1-sol", {**without_flags, **flags})
+        dropped = OpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params={"reasoning": {"effort": level}},
+            model="gpt-6.1-sol",
+            drop_params=True,
+        )
+        assert ("reasoning" in dropped) is forwarded
+        if not forwarded:
+            with pytest.raises(litellm.UnsupportedParamsError):
+                OpenAIResponsesAPIConfig().map_openai_params(
+                    response_api_optional_params={"reasoning": {"effort": level}},
+                    model="gpt-6.1-sol",
+                    drop_params=False,
+                )
+
+    def test_dropping_a_refused_effort_keeps_the_rest_of_the_reasoning_object(self, local_model_cost_map):
+        refused = next(
+            level
+            for level in ("none", "minimal", "low")
+            if litellm.model_cost["gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is False
+        )
+        mapped = OpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params={"reasoning": {"effort": refused, "summary": "auto"}},
+            model="gpt-6.1-sol",
+            drop_params=True,
+        )
+        assert mapped["reasoning"] == {"summary": "auto"}
+
+    @pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+    def test_gpt5_3_codex_forwards_exactly_the_effort_levels_its_map_row_allows(self, local_model_cost_map, level):
+        """The gate turns a stale false into a local refusal, so the Responses-only codex row has to
+        say what the route does. On 2026-10-01 /v1/responses answered gpt-5.3-codex none and xhigh
+        with 200 (effort echoed back) and minimal and max with 400 unsupported_value naming none,
+        low, medium, high and xhigh, so the row takes none and xhigh and turns minimal off."""
+        forwarded = (
+            level == "max" or litellm.model_cost["gpt-5.3-codex"].get(f"supports_{level}_reasoning_effort") is not False
+        )
+        mapped = OpenAIResponsesAPIConfig().map_openai_params(
+            response_api_optional_params={"reasoning": {"effort": level}},
+            model="gpt-5.3-codex",
+            drop_params=True,
+        )
+        assert ("reasoning" in mapped) is forwarded
+
+    def test_gpt5_3_codex_row_takes_none_and_xhigh(self, local_model_cost_map):
+        """Pinned on purpose so the row-derived test above cannot go vacuous: the live answers of
+        2026-10-01 listed above. When OpenAI changes the set, flip the row and this assertion
+        together."""
+        row = litellm.model_cost["gpt-5.3-codex"]
+        assert row["supports_none_reasoning_effort"] is True
+        assert row["supports_xhigh_reasoning_effort"] is True
+        assert row["supports_minimal_reasoning_effort"] is False
+
     def test_top_p_raises_without_drop_params(self, local_model_cost_map):
         with pytest.raises(litellm.UnsupportedParamsError):
             OpenAIResponsesAPIConfig().map_openai_params(
diff --git a/tests/unit/llms/openai/test_gpt5_transformation.py b/tests/unit/llms/openai/test_gpt5_transformation.py
index 41f5816600f..7b10411ba20 100644
--- a/tests/unit/llms/openai/test_gpt5_transformation.py
+++ b/tests/unit/llms/openai/test_gpt5_transformation.py
@@ -1,4 +1,6 @@
 import re
+from collections.abc import Mapping
+from typing import Final
 
 import pytest
 
@@ -431,6 +433,105 @@ def test_gpt5_drops_reasoning_effort_minimal_when_requested(config: OpenAIConfig
     assert "reasoning_effort" not in params
 
 
+def _chat_row_forwards(row: Mapping[str, object], level: str) -> bool:
+    """Chat polarity: max is never gated, xhigh needs an explicit true, every other level only has
+    to not be false."""
+    if level == "max":
+        return True
+    flag: Final = row.get(f"supports_{level}_reasoning_effort")
+    return flag is True if level == "xhigh" else flag is not False
+
+
+@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"])
+def test_gpt6_1_sol_forwards_exactly_the_effort_levels_its_map_row_allows(config: OpenAIConfig, level: str):
+    """The map row is the whole contract, so a new GPT-6 model is gated by its row with no code
+    change. gpt-6.1-sol's row turns none and minimal off: OpenAI lists low, medium, high, xhigh
+    and max for it (https://developers.openai.com/api/docs/models/gpt-6.1-sol, via #43910), and a
+    local proxy got OpenAI's 400 for none and minimal on both endpoints on 2026-09-30."""
+    forwarded: Final = _chat_row_forwards(litellm.model_cost["gpt-6.1-sol"], level)
+    dropped: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": level},
+        optional_params={},
+        model="gpt-6.1-sol",
+        drop_params=True,
+    )
+    assert ("reasoning_effort" in dropped) is forwarded
+    if forwarded:
+        kept: Final = config.map_openai_params(
+            non_default_params={"reasoning_effort": level},
+            optional_params={},
+            model="gpt-6.1-sol",
+            drop_params=False,
+        )
+        assert kept["reasoning_effort"] == level
+    else:
+        with pytest.raises(litellm.utils.UnsupportedParamsError):
+            config.map_openai_params(
+                non_default_params={"reasoning_effort": level},
+                optional_params={},
+                model="gpt-6.1-sol",
+                drop_params=False,
+            )
+
+
+def test_gpt6_1_sol_row_turns_none_and_minimal_off():
+    """Pinned on purpose so the row-derived test above cannot go vacuous: OpenAI lists low, medium,
+    high, xhigh and max for gpt-6.1-sol and neither none nor minimal
+    (https://developers.openai.com/api/docs/models/gpt-6.1-sol, read 2026-09-30 via #43910), and a
+    local proxy got OpenAI's 400 for both on 2026-09-30. When OpenAI adds a level, flip the row and
+    this assertion together."""
+    row: Final = litellm.model_cost["gpt-6.1-sol"]
+    assert row["supports_none_reasoning_effort"] is False
+    assert row["supports_minimal_reasoning_effort"] is False
+
+
+def _row_without_effort_flags(row: Mapping[str, object]) -> dict[str, object]:
+    return {
+        field: value
+        for field, value in row.items()
+        if not (field.startswith("supports_") and field.endswith("_reasoning_effort"))
+    }
+
+
+@pytest.mark.parametrize(
+    ("flags", "level", "forwarded"),
+    [
+        ({}, "none", True),
+        ({"supports_none_reasoning_effort": False}, "none", False),
+        ({"supports_none_reasoning_effort": True}, "none", True),
+        ({"supports_minimal_reasoning_effort": False}, "minimal", False),
+        ({"supports_max_reasoning_effort": False}, "max", True),
+        ({}, "max", True),
+        ({}, "xhigh", False),
+        ({"supports_xhigh_reasoning_effort": True}, "xhigh", True),
+        ({"supports_none_reasoning_effort": False}, "medium", True),
+    ],
+)
+def test_the_row_flags_alone_decide_whether_a_chat_level_is_forwarded(
+    config: OpenAIConfig, monkeypatch: pytest.MonkeyPatch, flags: dict[str, bool], level: str, forwarded: bool
+):
+    """Same model name, rewritten row: the gate flips with the flags and nothing else, so breaking the
+    gate fails here while the pinned test above catches the real row losing a flag."""
+    monkeypatch.setitem(
+        litellm.model_cost, "gpt-6.1-sol", {**_row_without_effort_flags(litellm.model_cost["gpt-6.1-sol"]), **flags}
+    )
+    dropped: Final = config.map_openai_params(
+        non_default_params={"reasoning_effort": level},
+        optional_params={},
+        model="gpt-6.1-sol",
+        drop_params=True,
+    )
+    assert ("reasoning_effort" in dropped) is forwarded
+    if not forwarded:
+        with pytest.raises(litellm.utils.UnsupportedParamsError):
+            config.map_openai_params(
+                non_default_params={"reasoning_effort": level},
+                optional_params={},
+                model="gpt-6.1-sol",
+                drop_params=False,
+            )
+
+
 def test_gpt5_minimal_dict_triggers_validation(config: OpenAIConfig):
     """Dict with effort='minimal' triggers minimal model-support validation."""
     with pytest.raises(litellm.utils.UnsupportedParamsError):
diff --git a/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py b/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
index 07f06c9084c..a5b2e76f3f6 100644
--- a/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
+++ b/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py
@@ -516,3 +516,26 @@ def test_request_strips_ttl_only_where_the_messages_api_defines_cache_control(co
     assert tool_result["content"][0]["cache_control"] == {"type": "ephemeral"}
     assert payload["messages"][1]["content"][1]["cache_control"] == {"type": "ephemeral"}
     assert payload["messages"][2] == {"role": "user", "content": "a plain string message"}
+
+
+@pytest.mark.usefixtures("local_beta_headers_config")
+@pytest.mark.parametrize(
+    ("client_headers", "expected_beta"),
+    [
+        ({}, None),
+        ({"anthropic-beta": "dangerous-tool-use-2026-09-03"}, "dangerous-tool-use-2026-09-03"),
+    ],
+)
+def test_safeguards_reach_an_openai_like_host_with_only_the_client_betas(
+    config: OpenAILikeAnthropicMessagesConfig, client_headers: dict[str, str], expected_beta: str | None
+) -> None:
+    headers, _ = config.validate_anthropic_messages_environment(
+        headers=client_headers,
+        model="some-model",
+        messages=[{"role": "user", "content": "hi"}],
+        optional_params={"safeguards": ({"type": "dangerous_tool_use"},)},
+        litellm_params={},
+        api_key="sk-test",
+        api_base="https://host/v1",
+    )
+    assert headers.get("anthropic-beta") == expected_beta, headers
diff --git a/tests/unit/proxy/common_utils/test_check_batch_cost.py b/tests/unit/proxy/common_utils/test_check_batch_cost.py
index 4e7effad3bf..46dbde82ded 100644
--- a/tests/unit/proxy/common_utils/test_check_batch_cost.py
+++ b/tests/unit/proxy/common_utils/test_check_batch_cost.py
@@ -9,12 +9,17 @@ ARN unified_object_id) batches with no managed unified id.
 import asyncio
 import json
 from contextlib import contextmanager
-from typing import TYPE_CHECKING
+from copy import copy
+from datetime import datetime, timezone
+from hashlib import sha256
+from typing import TYPE_CHECKING, Final
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 from fastapi import HTTPException
 
+from litellm.types.utils import LiteLLMBatch
+
 if TYPE_CHECKING:
     from litellm.batches.batch_utils import BatchCostUsageResult
 
@@ -201,7 +206,7 @@ class TestCheckBatchCost:
 
         find_call = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args
         assert find_call[1]["take"] == MAX_OBJECTS_PER_POLL_CYCLE
-        assert find_call[1]["order"] == {"created_at": "asc"}
+        assert find_call[1]["order"] == [{"created_at": "asc"}, {"id": "asc"}]
         not_in = find_call[1]["where"]["status"]["not_in"]
         assert "stale_expired" in not_in
         # "complete"/"completed" are intentionally NOT excluded from the
@@ -226,15 +231,13 @@ class TestCheckBatchCost:
         )
         # First find_many (primary query) raises with a schema error; second (fallback) returns empty
         mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock(
-            side_effect=[Exception("column batch_processed does not exist"), []]
+            side_effect=[Exception("column batch_processed does not exist"), [], []]
         )
 
         await check_batch_cost_instance.check_batch_cost()
 
-        calls = (
-            mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args_list
-        )
-        assert len(calls) == 2
+        calls = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args_list
+        assert len(calls) == 3
         fallback_where = calls[1][1]["where"]
         assert "batch_processed" not in fallback_where
         assert "stale_expired" in fallback_where["status"]["not_in"]
@@ -261,15 +264,8 @@ class TestCheckBatchCost:
 
         await check_batch_cost_instance.check_batch_cost()
 
-        # Only one find_many call — the fallback directly, no primary query attempt
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.find_many.call_count == 1
-        )
-        fallback_where = (
-            mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args[1][
-                "where"
-            ]
-        )
+        assert mock_prisma_client.db.litellm_managedobjecttable.find_many.call_count == 2
+        fallback_where = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args[1]["where"]
         assert "batch_processed" not in fallback_where
 
     @pytest.mark.asyncio
@@ -696,11 +692,15 @@ class TestCheckBatchCost:
             return_value=[mock_job]
         )
 
-        mock_response = MagicMock()
-        mock_response.status = "completed"
-        mock_response.output_file_id = "file-output-123"
-        mock_response.model_dump_json.return_value = (
-            '{"id":"batch-1","status":"completed"}'
+        mock_response: Final = LiteLLMBatch(
+            id="batch-1",
+            status="completed",
+            output_file_id="file-output-123",
+            created_at=1,
+            completion_window="24h",
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            object="batch",
         )
 
         mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response)
@@ -764,15 +764,13 @@ class TestCheckBatchCost:
 
             await check_batch_cost_instance.check_batch_cost()
 
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        ), "Expected update() to be called exactly once for the completed job"
-        update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[
-            1
-        ]["data"]
-        assert (
-            update_data["batch_processed"] is True
-        ), "update() must include batch_processed=True when column is present"
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, (
+            "Expected update() to be called exactly once for the completed job"
+        )
+        update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
+        assert update_data["batch_processed"] is True, (
+            "update() must include batch_processed=True when column is present"
+        )
         assert update_data["status"] == "complete"
 
     @pytest.mark.asyncio
@@ -899,7 +897,7 @@ class TestCheckBatchCost:
 
         mock_update_database.assert_awaited_once()
         assert mock_update_database.call_args.kwargs["response_cost"] == 0.01
-        assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1, (
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, (
             "the job must still be marked processed once cost tracking succeeds"
         )
 
@@ -1015,12 +1013,10 @@ class TestCheckBatchCost:
 
         await check_batch_cost_instance.check_batch_cost()
 
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        ), f"Expected update() to be called exactly once for a {terminal_status} job"
-        update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[
-            1
-        ]["data"]
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, (
+            f"Expected update() to be called exactly once for a {terminal_status} job"
+        )
+        update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["status"] == terminal_status
         assert (
             update_data["batch_processed"] is True
@@ -1126,9 +1122,13 @@ class TestCheckBatchCost:
             assert store_call.kwargs["user_api_key_dict"].user_id == "user-1"
             assert store_call.kwargs["user_api_key_dict"].team_id == "team-1"
 
-        assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        update_call = mock_prisma_client.db.litellm_managedobjecttable.update.call_args
-        assert update_call.kwargs["where"] == {"id": "job-terminal-mint-1"}
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2
+        update_call = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args
+        assert update_call.kwargs["where"] == {
+            "id": "job-terminal-mint-1",
+            "batch_processed": False,
+            "updated_at": mock_job.updated_at,
+        }
         update_data = update_call.kwargs["data"]
         assert update_data["status"] == terminal_status
         assert update_data["batch_processed"] is True
@@ -1203,12 +1203,10 @@ class TestCheckBatchCost:
         ) as mock_afile_content:
             await check_batch_cost_instance.check_batch_cost()
 
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        ), "a completed batch with no output file must be marked processed exactly once"
-        update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[
-            1
-        ]["data"]
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, (
+            "a completed batch with no output file must be marked processed exactly once"
+        )
+        update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["status"] == completed_status
         assert (
             update_data["batch_processed"] is True
@@ -1374,11 +1372,15 @@ class TestCheckBatchCost:
             return_value=[mock_job]
         )
 
-        mock_response = MagicMock()
-        mock_response.status = terminal_status
-        mock_response.output_file_id = "file-output-123"
-        mock_response.model_dump_json.return_value = (
-            f'{{"id":"batch-1","status":"{terminal_status}"}}'
+        mock_response: Final = LiteLLMBatch(
+            id="batch-1",
+            status=terminal_status,
+            output_file_id="file-output-123",
+            created_at=1,
+            completion_window="24h",
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            object="batch",
         )
 
         mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response)
@@ -1446,16 +1448,12 @@ class TestCheckBatchCost:
             mock_afile_content.await_count == 1
         ), f"{terminal_status} batch with an output file must fetch results and be billed"
         mock_logging_obj.async_success_handler.assert_awaited_once()
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        )
-        update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[
-            1
-        ]["data"]
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2
+        update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["batch_processed"] is True
-        assert (
-            update_data["status"] == terminal_status
-        ), f"billed {terminal_status} batch must keep its real terminal status in the DB"
+        assert update_data["status"] == terminal_status, (
+            f"billed {terminal_status} batch must keep its real terminal status in the DB"
+        )
 
     @pytest.mark.asyncio
     async def test_error_file_failures_add_to_failed_request_count(
@@ -1633,12 +1631,10 @@ class TestCheckBatchCost:
 
         assert mock_afile_content.await_count == 1
         mock_calculate.assert_not_awaited()
-        assert (
-            mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1
-        ), "a terminal batch with a 404ing output file must be retired, not retried forever"
-        update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[
-            1
-        ]["data"]
+        assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, (
+            "a terminal batch with a 404ing output file must be retired, not retried forever"
+        )
+        update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["status"] == "failed"
         assert update_data["batch_processed"] is True
 
@@ -1970,14 +1966,15 @@ class TestUnmanagedVertexRouting:
         router.resolve_model_name_from_model_id.return_value = "gemini-2.5-flash"
         router.get_model_ids.return_value = ["deploy-1"]
 
-        mock_response = MagicMock()
-        mock_response.status = "completed"
-        mock_response.output_file_id = "gs://bucket/out/predictions.jsonl"
-        mock_response.error_file_id = None
-        mock_response.completed_at = None
-        mock_response.created_at = None
-        mock_response.model_dump_json.return_value = (
-            '{"id":"8823717160934178816","status":"completed"}'
+        mock_response: Final = LiteLLMBatch(
+            id="8823717160934178816",
+            status="completed",
+            output_file_id="gs://bucket/out/predictions.jsonl",
+            created_at=1,
+            completion_window="24h",
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            object="batch",
         )
         router.aretrieve_batch = AsyncMock(return_value=mock_response)
         router.get_deployment_credentials_with_provider = MagicMock(
@@ -2050,8 +2047,8 @@ class TestUnmanagedVertexRouting:
         mock_logging_obj.async_success_handler.assert_awaited_once()
         assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.01
 
-        assert prisma.db.litellm_managedobjecttable.update.call_count == 1
-        update_data = prisma.db.litellm_managedobjecttable.update.call_args[1]["data"]
+        assert prisma.db.litellm_managedobjecttable.update_many.call_count == 2
+        update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["batch_processed"] is True
         assert update_data["status"] == "complete"
 
@@ -2202,14 +2199,15 @@ class TestUnmanagedBedrockRouting:
         router.resolve_model_name_from_model_id.return_value = "claude-sonnet-4"
         router.get_model_ids.return_value = ["deploy-1"]
 
-        mock_response = MagicMock()
-        mock_response.status = "completed"
-        mock_response.output_file_id = "s3://bucket/out/predictions.jsonl"
-        mock_response.error_file_id = None
-        mock_response.completed_at = None
-        mock_response.created_at = None
-        mock_response.model_dump_json.return_value = (
-            f'{{"id":"{self._ARN}","status":"completed"}}'
+        mock_response: Final = LiteLLMBatch(
+            id=self._ARN,
+            status="completed",
+            output_file_id="s3://bucket/out/predictions.jsonl",
+            created_at=1,
+            completion_window="24h",
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            object="batch",
         )
         router.aretrieve_batch = AsyncMock(return_value=mock_response)
         router.get_deployment_credentials_with_provider = MagicMock(
@@ -2280,8 +2278,8 @@ class TestUnmanagedBedrockRouting:
         mock_logging_obj.async_success_handler.assert_awaited_once()
         assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.02
 
-        assert prisma.db.litellm_managedobjecttable.update.call_count == 1
-        update_data = prisma.db.litellm_managedobjecttable.update.call_args[1]["data"]
+        assert prisma.db.litellm_managedobjecttable.update_many.call_count == 2
+        update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"]
         assert update_data["batch_processed"] is True
         assert update_data["status"] == "complete"
 
@@ -2860,9 +2858,10 @@ class TestPollPageStarvation:
         await self._instance(prisma, llm_router).check_batch_cost()
 
         llm_router.aretrieve_batch.assert_not_awaited()
-        prisma.db.litellm_managedobjecttable.update.assert_awaited_once()
-        call = prisma.db.litellm_managedobjecttable.update.call_args[1]
-        assert call["where"] == {"id": "job-no-model"}
+        prisma.db.litellm_managedobjecttable.update_many.assert_awaited()
+        call = prisma.db.litellm_managedobjecttable.update_many.call_args[1]
+        assert call["where"]["id"] == "job-no-model"
+        assert call["where"]["batch_processed"] is False
         assert call["data"] == {"batch_processed": True}
 
     @pytest.mark.asyncio
@@ -2890,10 +2889,8 @@ class TestPollPageStarvation:
 
         await self._instance(prisma, llm_router).check_batch_cost()
 
-        prisma.db.litellm_managedobjecttable.update.assert_awaited_once()
-        assert prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] == {
-            "batch_processed": True
-        }
+        prisma.db.litellm_managedobjecttable.update_many.assert_awaited()
+        assert prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] == {"batch_processed": True}
 
     @pytest.mark.asyncio
     async def test_provider_404_with_deployment_gone_keeps_job(self):
@@ -2954,26 +2951,7 @@ class TestPollPageStarvation:
 
         await instance.check_batch_cost()
 
-        assert prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] == {
-            "status": "stale_expired"
-        }
-
-    @pytest.mark.asyncio
-    async def test_stale_cleanup_gives_up_on_never_costed_completed_rows(self):
-        """A row already in a terminal status is never rewritten by the staleness sweep, so
-        it needs its own bound or it starves newer batches indefinitely."""
-        prisma = self._prisma([])
-
-        await self._instance(prisma, MagicMock()).check_batch_cost()
-
-        calls = prisma.db.litellm_managedobjecttable.update_many.call_args_list
-        assert len(calls) == 2, "expected the staleness sweep plus the never-costed sweep"
-        where = calls[1][1]["where"]
-        assert where["file_purpose"] == "batch"
-        assert where["batch_processed"] is False
-        assert where["status"] == {"in": ["complete", "completed"]}
-        assert "created_at" in where
-        assert calls[1][1]["data"] == {"batch_processed": True}
+        assert prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] == {"status": "stale_expired"}
 
     @pytest.mark.asyncio
     async def test_newer_batch_is_polled_once_dead_rows_are_retired(self):
@@ -3013,7 +2991,8 @@ class TestPollPageStarvation:
 
         retired = [
             call[1]["where"]["id"]
-            for call in prisma.db.litellm_managedobjecttable.update.call_args_list
+            for call in prisma.db.litellm_managedobjecttable.update_many.call_args_list
+            if "id" in call[1]["where"]
         ]
         assert retired == ["job-no-model", "job-gone"]
         assert (
@@ -3061,7 +3040,8 @@ class _FakeManagedObjectRow:
         self.team_id = None
         self.api_key = None
         self.request_tags = None
-        self.created_at = 1700000000
+        self.created_at = datetime(9999, 1, 1, tzinfo=timezone.utc)
+        self.updated_at = datetime(2000, 1, 1, tzinfo=timezone.utc)
         self.file_object = json.dumps(
             {"id": "batch-456", "status": "in_progress", "input_file_id": "file-input-1",
              "output_file_id": _CLAIM_OUTPUT_FILE_ID}
@@ -3087,7 +3067,9 @@ class _FakeManagedObjectTable:
     def _matches(self, where: dict) -> bool:
         for key, value in where.items():
             if key == "created_at":
-                return False
+                if "lt" in value and not self.row.created_at < value["lt"]:
+                    return False
+                continue
             if key == "status":
                 if self.row.status in value.get("not_in", []):
                     return False
@@ -3100,7 +3082,9 @@ class _FakeManagedObjectTable:
     async def _update_many(self, *, where: dict, data: dict) -> int:
         if not self._matches(where):
             return 0
-        if "batch_processed" in where:
+        if "updated_at" in where:
+            self.journal.append("finalize")
+        elif "batch_processed" in where:
             self.journal.append("claim" if data.get("batch_processed") else "release")
         for key, value in data.items():
             setattr(self.row, key, value)
@@ -3149,13 +3133,20 @@ class TestMultiPodBatchCostClaim:
 
     @staticmethod
     def _router():
-        response = MagicMock()
-        response.status = "completed"
-        response.output_file_id = _CLAIM_OUTPUT_FILE_ID
-        response.error_file_id = None
-        response.created_at = 1
-        response.completed_at = 2
-        response.model_dump_json.return_value = '{"id":"batch-456","status":"completed"}'
+        from litellm.types.utils import LiteLLMBatch
+
+        response: Final = LiteLLMBatch(
+            id="batch-456",
+            status="completed",
+            output_file_id=_CLAIM_OUTPUT_FILE_ID,
+            error_file_id=None,
+            created_at=1,
+            completed_at=2,
+            completion_window="24h",
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            object="batch",
+        )
 
         deployment = MagicMock()
         deployment.litellm_params.custom_llm_provider = "openai"
@@ -3226,6 +3217,351 @@ class TestMultiPodBatchCostClaim:
         ):
             yield logging_obj
 
+    @pytest.mark.asyncio
+    @pytest.mark.parametrize("failure_phase", ("before_write", "after_write", "external"))
+    @pytest.mark.parametrize("collector_enabled", (False, True))
+    async def test_builtin_accounting_retries_only_before_a_possible_charge(
+        self, failure_phase: str, collector_enabled: bool
+    ) -> None:
+        import base64
+        from datetime import datetime
+
+        import httpx
+        import litellm
+        import respx
+
+        from litellm.caching.caching import DualCache
+        from litellm.integrations.custom_logger import CustomLogger
+        from litellm.router_strategy.budget_limiter import RouterBudgetLimiting
+        from litellm.proxy.db.db_spend_update_writer import DBSpendUpdateWriter
+        from litellm.proxy.hooks.proxy_track_cost_callback import _ProxyDBLogger as ProxyDBLogger
+        from litellm.proxy.utils import PrismaClient
+        from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo
+        from litellm.types.utils import SpecialEnums
+
+        class AccountingDependency:
+            def __init__(self) -> None:
+                self.failure_phase = failure_phase
+                self.writer: Final = DBSpendUpdateWriter()
+                self.failed_tracking_alert = AsyncMock()
+                self.slack_alerting_instance = MagicMock()
+                self.slack_alerting_instance.customer_spend_alert = AsyncMock(
+                    side_effect=ConnectionError("Alert destination unavailable after charge")
+                    if failure_phase == "after_write"
+                    else None
+                )
+
+            @property
+            def db_spend_update_writer(self) -> DBSpendUpdateWriter:
+                if self.failure_phase == "before_write":
+                    raise ConnectionError("Accounting dependency temporarily unavailable")
+                return self.writer
+
+        class ExternalCallback(CustomLogger):
+            async def async_log_success_event(
+                self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime
+            ) -> None:
+                if failure_phase == "external":
+                    raise ConnectionError("External destination unavailable")
+
+        budget_cache: Final = DualCache()
+        RouterBudgetLimiting(
+            dual_cache=budget_cache,
+            provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}},
+            model_list=[
+                {
+                    "model_name": "batch-alias",
+                    "litellm_params": {"model": "openai/batch-test-model", "max_budget": 100, "budget_duration": "1d"},
+                    "model_info": {"id": "model-123"},
+                }
+            ],
+        )
+        dependency: Final = AccountingDependency()
+        spend_prisma: Final = PrismaClient(
+            database_url="postgresql://unused:unused@localhost:5432/unused", proxy_logging_obj=dependency
+        )
+        create_spend_rows: Final = AsyncMock(return_value=1)
+        input_rate: Final = 0.000002
+        litellm.register_model(
+            {
+                "batch-test-model": {
+                    "litellm_provider": "openai",
+                    "mode": "chat",
+                    "input_cost_per_token_batches": input_rate,
+                    "output_cost_per_token_batches": 0.000006,
+                }
+            }
+        )
+        content: Final = json.dumps(
+            {
+                "response": {
+                    "status_code": 200,
+                    "body": {
+                        "model": "batch-test-model",
+                        "usage": {"prompt_tokens": 100, "completion_tokens": 0, "total_tokens": 100},
+                    },
+                },
+                "error": None,
+            }
+        ).encode()
+        row: Final = _FakeManagedObjectRow()
+        original_status: Final = row.status
+        original_file_object: Final = row.file_object
+        row.unified_object_id = (
+            base64.urlsafe_b64encode(
+                SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode()
+            )
+            .decode()
+            .rstrip("=")
+        )
+        prisma: Final = self._prisma(row, [])
+        router: Final = self._router()
+        router.get_deployment.return_value = Deployment(
+            model_name="batch-alias",
+            litellm_params=LiteLLM_Params(model="openai/batch-test-model"),
+            model_info=ModelInfo(id="model-123"),
+        )
+        from litellm.proxy.spend_tracking.spend_event_producer import SpendEventProducer
+
+        producer: Final = MagicMock(spec=SpendEventProducer) if collector_enabled else None
+        litellm.logging_callback_manager.add_litellm_async_success_callback(
+            ProxyDBLogger(spend_event_producer=producer)
+        )
+        litellm.logging_callback_manager.add_litellm_async_success_callback(ExternalCallback())
+        with (
+            respx.mock,
+            patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency),
+            patch("litellm.proxy.proxy_server.prisma_client", spend_prisma),
+            patch.object(
+                spend_prisma.writer_db._original_prisma,
+                "litellm_spendlogs",
+                MagicMock(create_many=create_spend_rows),
+            ),
+        ):
+            respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content").mock(
+                return_value=httpx.Response(200, content=content)
+            )
+            worker: Final = self._instance(prisma, router)
+            await worker.check_batch_cost()
+            assert row.batch_processed is (failure_phase != "before_write")
+            if failure_phase == "before_write":
+                assert row.status == original_status
+                assert json.loads(row.file_object) == original_file_object
+            assert create_spend_rows.await_count == (0 if failure_phase == "before_write" else 1)
+            dependency.failure_phase = "recovered"
+            await worker.check_batch_cost()
+            await worker.check_batch_cost()
+
+        assert row.batch_processed is True
+        assert await budget_cache.async_get_cache("provider_spend:openai:1d") == pytest.approx(100 * input_rate)
+        assert await budget_cache.async_get_cache("deployment_spend:model-123:1d") == pytest.approx(100 * input_rate)
+        create_spend_rows.assert_awaited_once()
+        assert create_spend_rows.call_args.kwargs["data"][0]["spend"] == pytest.approx(100 * input_rate)
+        if producer is not None:
+            assert all(
+                json.loads(call.args[0])["call_type"] != "aretrieve_batch" for call in producer.publish.call_args_list
+            )
+
+    @pytest.mark.asyncio
+    @pytest.mark.parametrize(
+        ("deployment_model", "successes", "failures", "expected_model"),
+        (
+            ("openai/", 0, 2, "openai/"),
+            ("", 0, 2, "model-123"),
+            ("openai/", 2, 1, "batch-test-model"),
+            ("openai/batch-test-model", 2, 1, "batch-test-model"),
+            ("openai/batch-test-model", 2, 0, "batch-test-model"),
+        ),
+    )
+    @pytest.mark.parametrize("failure_envelope", (None, 1, "invalid", [1]))
+    async def test_batch_accounting_preserves_models_and_mixed_results(
+        self, deployment_model: str, successes: int, failures: int, expected_model: str, failure_envelope: object
+    ) -> None:
+        import base64
+        from datetime import datetime
+
+        import httpx
+        import litellm
+        import respx
+
+        from litellm.integrations.custom_logger import CustomLogger
+        from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo
+        from litellm.types.utils import LiteLLMBatch, SpecialEnums
+
+        input_rate: Final = 0.000002
+        output_rate: Final = 0.000006
+        litellm.register_model(
+            {
+                "batch-test-model": {
+                    "litellm_provider": "openai",
+                    "mode": "chat",
+                    "input_cost_per_token_batches": input_rate,
+                    "output_cost_per_token_batches": output_rate,
+                }
+            }
+        )
+        success: Final = {
+            "response": {
+                "status_code": 200,
+                "body": {
+                    "model": "batch-test-model",
+                    "usage": {"prompt_tokens": 100, "completion_tokens": 20, "total_tokens": 120},
+                },
+            },
+            "error": None,
+        }
+        failure: Final = {"response": failure_envelope, "error": {"code": "batch_expired", "message": "expired"}}
+        rows: Final = (success,) * successes + (failure,) * failures
+        content: Final = b"\n".join(json.dumps(row).encode() for row in rows)
+
+        class BatchSpendRecorder(CustomLogger):
+            def __init__(self) -> None:
+                super().__init__()
+                self.calls: tuple[dict[str, object], ...] = ()
+
+            async def async_log_success_event(
+                self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime
+            ) -> None:
+                if kwargs["call_type"] == "aretrieve_batch":
+                    self.calls += (kwargs,)
+
+        callback: Final = BatchSpendRecorder()
+        litellm.logging_callback_manager.add_litellm_async_success_callback(callback)
+        row: Final = _FakeManagedObjectRow()
+        row.unified_object_id = (
+            base64.urlsafe_b64encode(
+                SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode()
+            )
+            .decode()
+            .rstrip("=")
+        )
+        prisma: Final = self._prisma(row, [])
+        router: Final = self._router()
+        router.get_deployment.return_value = Deployment(
+            model_name="batch-alias",
+            litellm_params=LiteLLM_Params(model=deployment_model, custom_llm_provider="openai"),
+            model_info=ModelInfo(id="model-123"),
+        )
+        router.aretrieve_batch.return_value = LiteLLMBatch(
+            id="batch-456",
+            completion_window="24h",
+            created_at=1,
+            endpoint="/v1/chat/completions",
+            input_file_id="file-input-1",
+            output_file_id=_CLAIM_OUTPUT_FILE_ID,
+            object="batch",
+            status="completed",
+        )
+        router.get_deployment_credentials_with_provider.return_value = {
+            "api_key": "synthetic-key",
+            "custom_llm_provider": "openai",
+        }
+        with respx.mock:
+            respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content").mock(
+                return_value=httpx.Response(200, content=content)
+            )
+            instance: Final = self._instance(prisma, router)
+            await instance.check_batch_cost()
+            await instance.check_batch_cost()
+
+        assert row.batch_processed is True
+        assert row.status == "complete"
+        router.aretrieve_batch.assert_awaited_once()
+        assert len(callback.calls) == 1
+        payload: Final = callback.calls[0]["standard_logging_object"]
+        assert payload["model"] == expected_model
+        assert payload["response_cost"] == pytest.approx(successes * (100 * input_rate + 20 * output_rate))
+        assert payload["prompt_tokens"] == successes * 100
+        assert payload["completion_tokens"] == successes * 20
+        assert payload["hidden_params"]["batch_successful_requests"] == successes
+        assert payload["hidden_params"]["batch_failed_requests"] == failures
+        assert payload["hidden_params"]["batch_models"] == (
+            ["batch-test-model"] if deployment_model == "openai/batch-test-model" else ["batch-test-model"] * successes
+        )
+
+    @pytest.mark.asyncio
+    @pytest.mark.parametrize("error_source", ("batch", "output"))
+    async def test_a_404_for_another_identifier_preserves_recovery(self, error_source: str) -> None:
+        import base64
+
+        import httpx
+        import litellm
+        import respx
+
+        from litellm.integrations.custom_logger import CustomLogger
+        from litellm.types.utils import SpecialEnums
+
+        class SpendRecorder(CustomLogger):
+            def __init__(self) -> None:
+                super().__init__()
+                self.costs: tuple[float, ...] = ()
+
+            async def async_log_success_event(
+                self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime
+            ) -> None:
+                if kwargs["call_type"] == "aretrieve_batch":
+                    cost: Final = kwargs["response_cost"]
+                    assert isinstance(cost, float)
+                    self.costs += (cost,)
+
+        recorder: Final = SpendRecorder()
+        litellm.logging_callback_manager.add_litellm_async_success_callback(recorder)
+        litellm.register_model(
+            {
+                "batch-recovery-model": {
+                    "litellm_provider": "openai",
+                    "mode": "chat",
+                    "input_cost_per_token_batches": 0.01,
+                    "output_cost_per_token_batches": 0.02,
+                }
+            }
+        )
+        row: Final = _FakeManagedObjectRow()
+        row.unified_object_id = (
+            base64.urlsafe_b64encode(
+                SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode()
+            )
+            .decode()
+            .rstrip("=")
+        )
+        router: Final = self._router()
+        response: Final = router.aretrieve_batch.return_value
+        error: Final = litellm.NotFoundError(
+            message=f"No object found with id '{'batch-456' if error_source == 'batch' else _CLAIM_OUTPUT_FILE_ID}0'.",
+            model="gpt-4",
+            llm_provider="openai",
+        )
+        router.aretrieve_batch.side_effect = (error, response) if error_source == "batch" else (response, response)
+        prisma: Final = self._prisma(row, [])
+        output: Final = json.dumps(
+            {
+                "response": {
+                    "status_code": 200,
+                    "body": {
+                        "model": "batch-recovery-model",
+                        "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15},
+                    },
+                },
+                "error": None,
+            }
+        ).encode()
+        with respx.mock:
+            route: Final = respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content")
+            route.mock(
+                side_effect=error if error_source == "output" else None,
+                return_value=None if error_source == "output" else httpx.Response(200, content=output),
+            )
+            await self._instance(prisma, router).check_batch_cost()
+            assert row.batch_processed is False
+            assert recorder.costs == ()
+            route.mock(return_value=httpx.Response(200, content=output))
+            await self._instance(prisma, router).check_batch_cost()
+            await self._instance(prisma, router).check_batch_cost()
+
+        assert row.batch_processed is True
+        assert row.status == "complete"
+        assert recorder.costs == (pytest.approx(10 * 0.01 + 5 * 0.02),)
+
     @staticmethod
     def _claim_calls(prisma) -> list:
         return [
@@ -3249,6 +3585,30 @@ class TestMultiPodBatchCostClaim:
         with patch("litellm.proxy.proxy_server.scheduler", scheduler):
             await guard._check_file_deletion_allowed(file_id)
 
+    @pytest.mark.asyncio
+    @pytest.mark.parametrize("status", ("completed", "failed", "expired", "cancelled"))
+    @pytest.mark.parametrize("metadata_text", ("before\x00after", r"\u0000"))
+    async def test_cost_claim_persists_terminal_metadata_without_a_later_write(
+        self, status: str, metadata_text: str
+    ) -> None:
+        row: Final = _FakeManagedObjectRow()
+        journal: Final = []
+        prisma: Final = self._prisma(row, journal)
+        router: Final = self._router()
+        router.aretrieve_batch.return_value = router.aretrieve_batch.return_value.model_copy(
+            update={"status": status, "metadata": {"annotation": metadata_text}}
+        )
+        prisma.db.litellm_managedobjecttable.update.side_effect = RuntimeError("final write unavailable")
+        worker: Final = self._instance(prisma, router)
+        with self._billing_patches(journal) as logging_obj:
+            await worker.check_batch_cost()
+            await worker.check_batch_cost()
+        assert row.batch_processed is True
+        assert row.status == ("complete" if status == "completed" else status)
+        assert json.loads(row.file_object)["status"] == status
+        assert json.loads(row.file_object)["metadata"] == {"annotation": metadata_text.replace("\x00", "")}
+        assert logging_obj.async_success_handler.await_count == 1
+
     @pytest.mark.asyncio
     async def test_winning_pod_claims_the_row_between_fetching_and_billing(self):
         """The claim flips batch_processed false -> true after the results are in hand and
@@ -3260,13 +3620,9 @@ class TestMultiPodBatchCostClaim:
         with self._billing_patches(journal) as logging_obj:
             await self._instance(prisma, self._router()).check_batch_cost()
 
-        assert journal == ["fetch", "claim", "bill", "finalize"]
-        assert self._claim_calls(prisma) == [
-            {
-                "where": {"id": "job-claim-1", "batch_processed": False},
-                "data": {"batch_processed": True},
-            }
-        ]
+        assert journal == ["fetch", "claim", "bill"]
+        assert row.status == "complete"
+        assert json.loads(row.file_object)["usage"] == {"prompt_tokens": 10, "completion_tokens": 5}
         logging_obj.async_success_handler.assert_awaited_once()
         assert row.batch_processed is True
 
@@ -3286,30 +3642,28 @@ class TestMultiPodBatchCostClaim:
 
         assert journal == ["fetch"]
         logging_obj.async_success_handler.assert_not_awaited()
-        assert self._claim_calls(prisma) == [
-            {
-                "where": {"id": "job-claim-1", "batch_processed": False},
-                "data": {"batch_processed": True},
-            }
-        ]
+        assert row.status == "in_progress"
+        assert json.loads(row.file_object)["status"] == "in_progress"
 
     @pytest.mark.asyncio
-    async def test_a_failed_spend_log_write_releases_the_claim(self):
-        """A transient failure while billing a claimed batch must hand the row back, or its
-        spend is silently lost instead of being retried on the next cycle."""
-        row = _FakeManagedObjectRow()
-        journal = []
-        prisma = self._prisma(row, journal)
+    @pytest.mark.parametrize("stored_as_json_string", (True, False))
+    async def test_an_unclassified_logging_failure_keeps_the_claim(self, stored_as_json_string: bool) -> None:
+        row: Final = _FakeManagedObjectRow()
+        row.file_object = row.file_object if stored_as_json_string else json.loads(row.file_object)
+        journal: Final = []
+        prisma: Final = self._prisma(row, journal)
 
-        with self._billing_patches(journal, bill_error=Exception("spend log write failed")):
+        with self._billing_patches(journal, bill_error=Exception("Accounting outcome unknown")):
             await self._instance(prisma, self._router()).check_batch_cost()
 
-        assert journal == ["fetch", "claim", "bill", "release"]
-        assert row.batch_processed is False
-        assert self._claim_calls(prisma)[-1] == {
-            "where": {"id": "job-claim-1", "batch_processed": True},
-            "data": {"batch_processed": False},
-        }
+        assert journal == ["fetch", "claim", "bill"]
+        assert row.batch_processed is True
+
+        with self._billing_patches(journal) as logging_obj:
+            await self._instance(prisma, self._router()).check_batch_cost()
+            await self._instance(prisma, self._router()).check_batch_cost()
+
+        logging_obj.async_success_handler.assert_not_awaited()
 
     @pytest.mark.asyncio
     async def test_a_worker_interrupted_mid_costing_leaves_the_batch_billable(self):
@@ -3343,7 +3697,7 @@ class TestMultiPodBatchCostClaim:
         with self._billing_patches(survivor_journal) as survivor_logging:
             await self._instance(survivor_prisma, self._router()).check_batch_cost()
 
-        assert survivor_journal == ["fetch", "claim", "bill", "finalize"]
+        assert survivor_journal == ["fetch", "claim", "bill"]
         survivor_logging.async_success_handler.assert_awaited_once()
         assert row.batch_processed is True
 
@@ -3376,7 +3730,7 @@ class TestMultiPodBatchCostClaim:
             finish_fetch.set()
             await asyncio.wait_for(costing, timeout=5)
 
-        assert journal == ["fetch", "claim", "bill", "finalize"]
+        assert journal == ["fetch", "claim", "bill"]
         assert row.batch_processed is True
         await self._run_deletion_guard(prisma, _CLAIM_OUTPUT_FILE_ID)
 
diff --git a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py
index 2b33034f060..b9f68e6d128 100644
--- a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py
+++ b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py
@@ -4382,11 +4382,11 @@ class TestEnsureOutputItemContentPartAdded:
         namespace_map.assert_called_once_with(request["tools"])
 
 
-    def test_emit_response_completed_uses_stream_finish_reason(self):
+    def test_emit_terminal_event_uses_stream_finish_reason(self):
         """
-        When the assembled model response carries finish_reason="content_filter"
-        (snapshotted from the underlying stream before any pending events fire),
-        _emit_response_completed_event must produce status="incomplete".
+        The terminal stream event type must track the assembled response
+        status: finish_reason="content_filter" yields response.incomplete,
+        finish_reason="stop" yields response.completed.
         """
         from unittest.mock import Mock
 
@@ -4394,6 +4394,7 @@ class TestEnsureOutputItemContentPartAdded:
         from litellm.responses.litellm_completion_transformation.streaming_iterator import (
             LiteLLMCompletionStreamingIterator,
         )
+        from litellm.types.llms.openai import ResponsesAPIStreamEvents
 
         mock_stream_wrapper = Mock(spec=litellm.CustomStreamWrapper)
         mock_stream_wrapper.logging_obj = Mock()
@@ -4406,28 +4407,32 @@ class TestEnsureOutputItemContentPartAdded:
             custom_llm_provider="anthropic",
         )
 
-        litellm_model_response = ModelResponse(
-            id="chatcmpl-test",
-            created=1234567890,
-            model="anthropic/claude-sonnet-4-6",
-            object="chat.completion",
-            choices=[
-                Choices(
-                    finish_reason="content_filter",
-                    index=0,
-                    message=Message(content="", role="assistant"),
-                )
-            ],
-            usage=Usage(prompt_tokens=10, completion_tokens=1, total_tokens=11),
-        )
+        def _response(finish_reason: str) -> ModelResponse:
+            return ModelResponse(
+                id="chatcmpl-test",
+                created=1234567890,
+                model="anthropic/claude-sonnet-4-6",
+                object="chat.completion",
+                choices=[
+                    Choices(
+                        finish_reason=finish_reason,
+                        index=0,
+                        message=Message(content="", role="assistant"),
+                    )
+                ],
+                usage=Usage(prompt_tokens=10, completion_tokens=1, total_tokens=11),
+            )
 
-        completed_event = iterator._emit_response_completed_event(
-            litellm_model_response
-        )
+        incomplete_event = iterator._emit_terminal_response_event(_response("content_filter"))
+        assert incomplete_event is not None
+        assert incomplete_event.type == ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE
+        assert incomplete_event.response.status == "incomplete"
+        assert incomplete_event.response.output[0].status == "incomplete"
 
+        completed_event = iterator._emit_terminal_response_event(_response("stop"))
         assert completed_event is not None
-        assert completed_event.response.status == "incomplete"
-        assert completed_event.response.output[0].status == "incomplete"
+        assert completed_event.type == ResponsesAPIStreamEvents.RESPONSE_COMPLETED
+        assert completed_event.response.status == "completed"
 
     def test_reasoning_item_does_not_emit_content_part_added(self):
         """Reasoning items should not get a content_part.added event."""
@@ -5016,7 +5021,7 @@ class TestStreamingSnapshotItemIds:
         )
         assert streamed_event is not None
 
-        completed_event = iterator._emit_response_completed_event(
+        completed_event = iterator._emit_terminal_response_event(
             _bridged_chat_completion_response()
         )
 
@@ -5031,7 +5036,7 @@ class TestStreamingSnapshotItemIds:
             self._make_chunk("apple")
         )
 
-        completed_event = iterator._emit_response_completed_event(
+        completed_event = iterator._emit_terminal_response_event(
             _bridged_chat_completion_response()
         )
 
@@ -5088,7 +5093,7 @@ class TestStreamingSnapshotItemIds:
         )
         assert streamed_event is not None
 
-        completed_event = iterator._emit_response_completed_event(
+        completed_event = iterator._emit_terminal_response_event(
             self._reasoning_chat_completion_response()
         )
 
@@ -5159,6 +5164,140 @@ def test_transform_chat_completion_response_incomplete_details():
     assert result_existing.incomplete_details == existing_details
 
 
+def test_transform_chat_completion_response_null_finish_reason_is_incomplete():
+    """
+    A choice with no finish signal (e.g. Gemini thinking consuming the whole
+    output budget, or a provider that never sent one) must not report
+    status "completed". Output at the requested cap reads as
+    max_output_tokens; below it, no reason can be claimed.
+    """
+    choice_at_cap = Choices.model_construct(
+        index=0,
+        finish_reason=None,
+        message=Message(content="", role="assistant"),
+    )
+    resp_at_cap = ModelResponse(
+        id="resp-null-cap",
+        choices=[choice_at_cap],
+        model="gemini-2.5-pro",
+        usage=Usage(prompt_tokens=10, completion_tokens=60, total_tokens=70),
+    )
+    result_at_cap = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request={"max_output_tokens": 60},
+        chat_completion_response=resp_at_cap,
+    )
+    assert result_at_cap.status == "incomplete"
+    assert result_at_cap.incomplete_details is not None
+    assert result_at_cap.incomplete_details.reason == "max_output_tokens"
+
+    choice_under_cap = Choices.model_construct(
+        index=0,
+        finish_reason=None,
+        message=Message(content="", role="assistant"),
+    )
+    resp_under_cap = ModelResponse(
+        id="resp-null-under",
+        choices=[choice_under_cap],
+        model="gemini-2.5-pro",
+        usage=Usage(prompt_tokens=10, completion_tokens=30, total_tokens=40),
+    )
+    result_under_cap = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request={"max_output_tokens": 60},
+        chat_completion_response=resp_under_cap,
+    )
+    assert result_under_cap.status == "incomplete"
+    assert result_under_cap.incomplete_details is None
+
+    resp_empty = ModelResponse(id="resp-empty", choices=[], model="gemini-2.5-pro")
+    result_empty = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request={},
+        chat_completion_response=resp_empty,
+    )
+    assert result_empty.status == "incomplete"
+
+
+def test_transform_chat_completion_response_echoes_request_params():
+    """
+    A chat completion response never carries the caller's request fields, so
+    the bridged response echoes them from the request. Before this fix
+    temperature reported 0 and the rest reported None or empty defaults.
+    """
+    resp = ModelResponse(
+        id="resp-echo",
+        choices=[Choices(index=0, finish_reason="stop", message=Message(content="hi", role="assistant"))],
+        model="gpt-4o",
+    )
+    result = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request={
+            "temperature": 0.7,
+            "top_p": 0.9,
+            "max_output_tokens": 128,
+            "instructions": "be terse",
+            "metadata": {"trace": "abc"},
+            "user": "user-123",
+            "truncation": "disabled",
+            "store": True,
+            "parallel_tool_calls": True,
+        },
+        chat_completion_response=resp,
+    )
+    assert result.temperature == 0.7
+    assert result.top_p == 0.9
+    assert result.max_output_tokens == 128
+    assert result.instructions == "be terse"
+    assert result.metadata == {"trace": "abc"}
+    assert result.user == "user-123"
+    assert result.truncation == "disabled"
+    assert result.store is True
+    assert result.parallel_tool_calls is True
+
+    # Fields the request never set fall back to the response defaults.
+    result_unset = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request={},
+        chat_completion_response=resp,
+    )
+    assert result_unset.temperature is None
+    assert result_unset.metadata == {}
+    assert result_unset.parallel_tool_calls is False
+    assert result_unset.tools == []
+    assert result_unset.text == {}
+
+
+@pytest.mark.parametrize(
+    ("field", "invalid_value", "expected"),
+    [
+        ("user", 123, None),
+        ("instructions", 5, None),
+        ("text", "plain", {}),
+        ("truncation", "bogus", None),
+        ("parallel_tool_calls", "maybe", False),
+    ],
+)
+def test_transform_drops_request_params_the_response_cannot_echo(
+    field: str, invalid_value: object, expected: object
+) -> None:
+    request: Final[dict[str, object]] = {"temperature": 0.7, field: invalid_value}
+    response: Final = ModelResponse(
+        id="resp-invalid-echo",
+        choices=[Choices(index=0, finish_reason="stop", message=Message(content="hi", role="assistant"))],
+        model="gpt-4o",
+    )
+
+    result: Final = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+        request_input="test prompt",
+        responses_api_request=request,
+        chat_completion_response=response,
+    )
+
+    assert getattr(result, field) == expected, f"invalid {field} value {invalid_value!r}"
+    assert result.temperature == 0.7, f"valid temperature was dropped with invalid {field}"
+
+
 @pytest.mark.parametrize("stream", [True, False])
 async def test_bridge_rejects_untranslatable_tool_choice_with_a_400(stream: bool):
     with pytest.raises(litellm.BadRequestError) as exc_info:
diff --git a/tests/unit/responses/test_responses_api_bridge_flag.py b/tests/unit/responses/test_responses_api_bridge_flag.py
index 642495fab86..01bce88e372 100644
--- a/tests/unit/responses/test_responses_api_bridge_flag.py
+++ b/tests/unit/responses/test_responses_api_bridge_flag.py
@@ -355,11 +355,8 @@ class TestUseResponsesApiBridgeFlag:
         assert upstream.call_count == 1
         request_body: Final = json.loads(upstream.calls[0].request.read())
         assert request_body["messages"] == [
-            {
-                "role": "system",
-                "content": [{"type": "text", "text": "You are terse."}, {"type": "text", "text": "Skills: none."}],
-            },
-            {"role": "user", "content": [{"type": "text", "text": "Hello"}]},
+            {"role": "system", "content": "You are terse.\n\nSkills: none."},
+            {"role": "user", "content": "Hello"},
         ]
         assert "client_metadata" not in request_body
         assert request_body["chat_template_kwargs"] == {"thinking": True}
diff --git a/tests/unit/responses/test_responses_websocket_all_providers.py b/tests/unit/responses/test_responses_websocket_all_providers.py
index 6f346a25d9c..222cc641b6b 100644
--- a/tests/unit/responses/test_responses_websocket_all_providers.py
+++ b/tests/unit/responses/test_responses_websocket_all_providers.py
@@ -8,6 +8,7 @@ Tests that:
 """
 
 import json
+from typing import Final
 from unittest.mock import MagicMock
 
 import pytest
@@ -283,6 +284,91 @@ class TestManagedWebSocketHandlerIntegration:
 
         assert captured["model"] == "bedrock_mantle/openai.gpt-5.5"
 
+    @pytest.mark.parametrize("terminal_type", ["response.completed", "response.incomplete"])
+    @pytest.mark.asyncio
+    async def test_truncated_turn_is_kept_as_history_for_the_next_turn(self, monkeypatch, terminal_type: str):
+        from unittest.mock import AsyncMock, MagicMock
+
+        import litellm
+        from litellm.litellm_core_utils.litellm_logging import Logging
+        from litellm.responses.streaming_iterator import ManagedResponsesWebSocketHandler
+
+        terminal_response: Final = {
+            "type": terminal_type,
+            "response": {
+                "id": "resp_turn1",
+                "status": "incomplete" if terminal_type == "response.incomplete" else "completed",
+                "output": [
+                    {
+                        "type": "message",
+                        "role": "assistant",
+                        "content": [{"type": "output_text", "text": "PELICAN noted"}],
+                    }
+                ],
+            },
+        }
+
+        async def first_stream():
+            yield terminal_response
+
+        async def empty_stream():
+            return
+            yield {}
+
+        aresponses_mock: Final = AsyncMock(side_effect=(first_stream(), empty_stream()))
+        monkeypatch.setattr(litellm, "aresponses", aresponses_mock)
+
+        websocket: Final = MagicMock()
+        websocket.send_text = AsyncMock()
+        handler: Final = ManagedResponsesWebSocketHandler(
+            websocket=websocket,
+            model="bedrock_mantle/openai.gpt-5.5",
+            logging_obj=Logging(
+                model="bedrock_mantle/openai.gpt-5.5",
+                messages=[],
+                stream=True,
+                call_type="aresponses",
+                start_time=0,
+                litellm_call_id="test-id",
+                function_id="test-func",
+            ),
+            litellm_metadata={"model_group": "gpt-5.5-mantle"},
+        )
+
+        turn_one_user: Final[dict[str, object]] = {
+            "type": "message",
+            "role": "user",
+            "content": [{"type": "input_text", "text": "My secret word is PELICAN"}],
+        }
+        turn_two_user: Final[dict[str, object]] = {
+            "type": "message",
+            "role": "user",
+            "content": [{"type": "input_text", "text": "What is my secret word?"}],
+        }
+        turn_one_frame: Final = json.dumps({"type": "response.create", "input": [turn_one_user]})
+        turn_two_frame: Final = json.dumps(
+            {
+                "type": "response.create",
+                "previous_response_id": "resp_turn1",
+                "input": [turn_two_user],
+            }
+        )
+
+        await handler._process_response_create(turn_one_frame)
+        await handler._process_response_create(turn_two_frame)
+
+        expected_input: Final[list[dict[str, object]]] = [
+            turn_one_user,
+            {
+                "type": "message",
+                "role": "assistant",
+                "content": [{"type": "output_text", "text": "PELICAN noted"}],
+            },
+            turn_two_user,
+        ]
+        second_call_input: Final = aresponses_mock.call_args_list[1].kwargs["input"]
+        assert second_call_input == expected_input, terminal_type
+
     @pytest.mark.asyncio
     async def test_warmup_frame_skips_provider_and_sends_synthetic_ack(
         self, monkeypatch
diff --git a/tests/unit/router_strategy/test_budget_limiter.py b/tests/unit/router_strategy/test_budget_limiter.py
new file mode 100644
index 00000000000..3b1fa2ac577
--- /dev/null
+++ b/tests/unit/router_strategy/test_budget_limiter.py
@@ -0,0 +1,227 @@
+"""
+Spend tracking in RouterBudgetLimiting.async_log_success_event.
+
+Only chat completions puts custom_llm_provider into litellm_params. The responses,
+anthropic_messages, embedding and rerank surfaces leave it unset, which used to make
+the callback raise before any spend was recorded, so those budgets never moved.
+"""
+
+import asyncio
+from typing import Final
+
+import pytest
+
+import litellm
+from litellm.caching.caching import DualCache
+from litellm.router_strategy.budget_limiter import RouterBudgetLimiting
+
+
+@pytest.fixture
+def disable_budget_sync(monkeypatch):
+    async def noop(*args, **kwargs):
+        return None
+
+    monkeypatch.setattr(
+        "litellm.router_strategy.budget_limiter.RouterBudgetLimiting.periodic_sync_in_memory_spend_with_redis",
+        noop,
+    )
+
+
+def _success_kwargs(
+    *,
+    provider_in_litellm_params: str | None,
+    provider_in_payload: str | None,
+    call_type: str = "aresponses",
+    response_cost: float = 0.25,
+    model_id: str = "deployment-1",
+) -> dict[str, object]:
+    provider_params: Final[dict[str, str]] = (
+        {} if provider_in_litellm_params is None else {"custom_llm_provider": provider_in_litellm_params}
+    )
+    litellm_params: Final[dict[str, str]] = {"model": "openai/gpt-4o", **provider_params}
+
+    return {
+        "call_type": call_type,
+        "litellm_params": litellm_params,
+        "standard_logging_object": {
+            "response_cost": response_cost,
+            "model_id": model_id,
+            "custom_llm_provider": provider_in_payload,
+        },
+    }
+
+
+async def _log_success(limiter: RouterBudgetLimiting, kwargs: dict[str, object]) -> None:
+    await limiter.async_log_success_event(kwargs=kwargs, response_obj=None, start_time=None, end_time=None)
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("call_type", ["aresponses", "anthropic_messages", "aembedding", "arerank"])
+async def test_provider_spend_tracked_when_litellm_params_omits_provider(disable_budget_sync, call_type):
+    """Non-chat surfaces carry the provider only on the standard logging payload."""
+    limiter = RouterBudgetLimiting(
+        dual_cache=DualCache(),
+        provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}},
+    )
+
+    await _log_success(
+        limiter,
+        _success_kwargs(
+            provider_in_litellm_params=None,
+            provider_in_payload="openai",
+            call_type=call_type,
+        ),
+    )
+
+    assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") == 0.25
+
+
+@pytest.mark.asyncio
+async def test_chat_completions_spend_still_tracked(disable_budget_sync):
+    """Chat completions fills in both sources and must keep accumulating."""
+    limiter = RouterBudgetLimiting(
+        dual_cache=DualCache(),
+        provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}},
+    )
+
+    await _log_success(
+        limiter,
+        _success_kwargs(
+            provider_in_litellm_params="openai",
+            provider_in_payload="openai",
+            call_type="acompletion",
+        ),
+    )
+
+    assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") == 0.25
+
+
+@pytest.mark.asyncio
+async def test_budget_of_other_provider_is_untouched(disable_budget_sync):
+    """A provider without its own budget must not bleed into a configured one."""
+    limiter = RouterBudgetLimiting(
+        dual_cache=DualCache(),
+        provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}},
+    )
+
+    await _log_success(
+        limiter,
+        _success_kwargs(provider_in_litellm_params=None, provider_in_payload="anthropic"),
+    )
+
+    assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") in (None, 0.0)
+
+
+@pytest.mark.asyncio
+async def test_deployment_budget_tracked_when_provider_is_unresolvable(disable_budget_sync):
+    """An unresolvable provider must not abort the deployment and tag budgets that follow it."""
+    limiter = RouterBudgetLimiting(
+        dual_cache=DualCache(),
+        provider_budget_config=None,
+        model_list=[
+            {
+                "model_name": "some-model",
+                "litellm_params": {
+                    "model": "openai/gpt-4o",
+                    "max_budget": 10.0,
+                    "budget_duration": "1d",
+                },
+                "model_info": {"id": "deployment-1"},
+            }
+        ],
+    )
+
+    await _log_success(
+        limiter,
+        _success_kwargs(provider_in_litellm_params=None, provider_in_payload=None),
+    )
+
+    assert await limiter.dual_cache.async_get_cache("deployment_spend:deployment-1:1d") == 0.25
+
+
+def _completed_budget_batch(batch_id: str):
+    from litellm.types.utils import LiteLLMBatch
+
+    return LiteLLMBatch(
+        id=batch_id,
+        completion_window="24h",
+        created_at=1,
+        endpoint="/v1/chat/completions",
+        input_file_id="file-budget",
+        object="batch",
+        status="completed",
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("call_type", ("aretrieve_batch", "retrieve_batch"))
+async def test_batch_polls_charge_each_router_budget_once(monkeypatch, call_type):
+    monkeypatch.setattr(litellm, "tag_budget_config", {"release": {"budget_limit": 100, "time_period": "1d"}})
+    monkeypatch.setattr("litellm.proxy.proxy_server.premium_user", True)
+    cache: Final = DualCache()
+    limiter: Final = RouterBudgetLimiting(
+        dual_cache=cache,
+        provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}},
+        model_list=[
+            {
+                "model_name": "batch-budget",
+                "litellm_params": {"model": "openai/batch-budget", "max_budget": 100, "budget_duration": "1d"},
+                "model_info": {"id": "deployment-1"},
+            }
+        ],
+    )
+    kwargs: Final = {
+        **_success_kwargs(provider_in_litellm_params=None, provider_in_payload="openai", call_type=call_type),
+        "metadata": {"tags": ["release"]},
+    }
+    response: Final = _completed_budget_batch("batch-first")
+    await asyncio.gather(*(limiter.async_log_success_event(kwargs, response, None, None) for _ in range(10)))
+    keys: Final = ("provider_spend:openai:1d", "deployment_spend:deployment-1:1d", "tag_spend:release:1d")
+    assert tuple([await cache.async_get_cache(key) for key in keys]) == (0.25, 0.25, 0.25)
+    await limiter.async_log_success_event(kwargs, _completed_budget_batch("batch-second"), None, None)
+    await limiter.async_log_success_event({**kwargs, "call_type": "acompletion"}, response, None, None)
+    await limiter.async_log_success_event({**kwargs, "call_type": "acompletion"}, response, None, None)
+    assert tuple([await cache.async_get_cache(key) for key in keys]) == (1.0, 1.0, 1.0)
+    await limiter.async_log_success_event({**kwargs, "call_type": "_arealtime"}, response, None, None)
+    assert tuple([await cache.async_get_cache(key) for key in keys]) == (1.0, 1.0, 1.0)
+
+
+@pytest.mark.asyncio
+async def test_batch_charge_is_shared_across_workers_and_requires_redis_confirmation():
+    from fakeredis import FakeServer, FakeRedis as FakeSyncRedis
+    from redis.exceptions import ConnectionError as RedisConnectionError
+    from fakeredis.aioredis import FakeRedis
+    from litellm.caching.redis_cache import RedisCache
+
+    server: Final = FakeServer()
+    client: Final = FakeRedis(server=server)
+    sync_client: Final = FakeSyncRedis(server=server)
+    redis_cache: Final = RedisCache(host="router-batch-fixture", connection_pool=sync_client.connection_pool)
+    litellm.in_memory_llm_clients_cache.set_cache(key=redis_cache._get_async_client_cache_key(), value=client)
+    first: Final = RouterBudgetLimiting(
+        dual_cache=DualCache(redis_cache=redis_cache),
+        provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}},
+    )
+    second: Final = RouterBudgetLimiting(
+        dual_cache=DualCache(redis_cache=redis_cache),
+        provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}},
+    )
+    kwargs: Final = _success_kwargs(
+        provider_in_litellm_params=None, provider_in_payload="openai", call_type="aretrieve_batch"
+    )
+    response: Final = _completed_budget_batch("batch-shared")
+    await asyncio.gather(
+        first.async_log_success_event(kwargs, response, None, None),
+        second.async_log_success_event(kwargs, response, None, None),
+    )
+    await first._push_in_memory_increments_to_redis()
+    await second._push_in_memory_increments_to_redis()
+    assert float(await client.get("provider_spend:openai:1d")) == 0.25
+    server.connected = False
+    with pytest.raises(RedisConnectionError):
+        await second.async_log_success_event(kwargs, _completed_budget_batch("batch-unconfirmed"), None, None)
+    server.connected = True
+    await second.async_log_success_event(kwargs, _completed_budget_batch("batch-unconfirmed"), None, None)
+    await second._push_in_memory_increments_to_redis()
+    assert float(await client.get("provider_spend:openai:1d")) == 0.5
+    await client.aclose()
diff --git a/tests/unit/router_utils/test_reasoning_effort_capability.py b/tests/unit/router_utils/test_reasoning_effort_capability.py
index 2f23320a8ad..787444c96c1 100644
--- a/tests/unit/router_utils/test_reasoning_effort_capability.py
+++ b/tests/unit/router_utils/test_reasoning_effort_capability.py
@@ -395,22 +395,25 @@ class TestGpt6AstraAdvertisesItsDocumentedLevels:
         [
             ("azure/gpt-6-astra", "azure"),
             ("azure/us/gpt-6-astra", "azure"),
+            ("azure/eu/gpt-6-astra", "azure"),
             ("azure_ai/gpt-6-astra", "azure_ai"),
         ],
     )
-    def test_an_azure_hosted_deployment_advertises_none_but_not_max(
+    def test_an_azure_hosted_deployment_advertises_the_levels_both_its_routes_accept(
         self, local_model_cost_map, model, custom_llm_provider
     ):
-        """Microsoft hosts the same model with a different level set than OpenAI does. Verified live
-        on both Azure routes: none returns 200 with zero reasoning tokens and unlocks temperature,
-        which OpenAI's API rejects, while max returns 400 unsupported_value naming none through
-        xhigh as the levels it does take."""
+        """Verified live on 2026-10-01 against a Foundry gpt-6-astra deployment (model
+        gpt-6-astra-2026-09-03): none returns 400 unsupported_value on chat and on Responses, naming
+        low, medium, high and xhigh as the levels it takes; Responses also honors max with reasoning
+        tokens billed while chat refuses it, as OpenAI's chat does. The flag is route-blind, so the
+        row keeps max off and the advertised set stops at the level every route accepts.
+        Earlier evidence (2026-09-05, commit e79f3ec5205) had none accepted on chat; the deployment
+        no longer behaves that way."""
         from litellm.utils import _get_model_info_helper
 
         model_info = dict(_get_model_info_helper(model=model, custom_llm_provider=custom_llm_provider))
 
         assert resolve_supported_reasoning_efforts(model_info, deployment_is_mapped=True) == (
-            "none",
             "low",
             "medium",
             "high",
diff --git a/tests/unit/test_claude_haiku_5_5_config.py b/tests/unit/test_claude_haiku_5_5_config.py
new file mode 100644
index 00000000000..770014952e4
--- /dev/null
+++ b/tests/unit/test_claude_haiku_5_5_config.py
@@ -0,0 +1,128 @@
+"""
+Validate Claude Haiku 5.5 model configuration entries.
+
+Haiku 5.5 ships with adaptive thinking on by default, but unlike Sonnet 5.5 /
+Opus 5.5 thinking can still be turned off (``thinking: disabled`` at high
+effort or below) and it accepts a forced ``tool_choice`` (``any`` or a named
+tool). Its cost-map rows therefore carry ``thinking_always_on: false`` and
+``supports_forced_tool_use: true``.
+"""
+
+import json
+import os
+from collections.abc import Iterator
+from typing import Final, cast
+
+import pytest
+
+import litellm
+from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap
+from litellm.llms.anthropic.common_utils import AnthropicModelInfo
+
+REPO_ROOT: Final = os.path.join(os.path.dirname(__file__), "../..")
+
+GET_WEATHER_TOOL: Final = {
+    "type": "function",
+    "function": {
+        "name": "get_weather",
+        "description": "Get the weather",
+        "parameters": {
+            "type": "object",
+            "properties": {"city": {"type": "string"}},
+        },
+    },
+}
+
+
+@pytest.fixture(autouse=True)
+def local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
+    monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
+    litellm.get_model_info.cache_clear()
+    yield
+    litellm.get_model_info.cache_clear()
+
+
+def _load_root_cost_map() -> dict[str, dict[str, object]]:
+    json_path: Final = os.path.join(REPO_ROOT, "model_prices_and_context_window.json")
+    with open(json_path) as f:
+        return cast(dict[str, dict[str, object]], json.load(f))
+
+
+HAIKU_5_5_VARIANTS: Final = (
+    "claude-haiku-5-5",
+    "anthropic.claude-haiku-5-5",
+    "apac.anthropic.claude-haiku-5-5",
+    "au.anthropic.claude-haiku-5-5",
+    "eu.anthropic.claude-haiku-5-5",
+    "global.anthropic.claude-haiku-5-5",
+    "jp.anthropic.claude-haiku-5-5",
+    "us.anthropic.claude-haiku-5-5",
+    "us-gov.anthropic.claude-haiku-5-5",
+    "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5",
+    "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5",
+    "bedrock_mantle/anthropic.claude-haiku-5-5",
+    "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5",
+    "vertex_ai/claude-haiku-5-5",
+    "vertex_ai/claude-haiku-5-5@default",
+)
+
+
+@pytest.mark.parametrize("model_name", HAIKU_5_5_VARIANTS)
+def test_haiku_5_5_rows_allow_disabling_thinking_and_forced_tools(
+    model_name: str,
+) -> None:
+    root: Final = _load_root_cost_map()
+    backup: Final = GetModelCostMap.load_local_model_cost_map()
+    assert model_name in root
+    row: Final = root[model_name]
+    # https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5 (2026-10-07):
+    # thinking can be disabled, forced tool_choice accepted
+    assert row["thinking_always_on"] is False
+    assert row["supports_forced_tool_use"] is True
+    assert backup[model_name] == row
+
+
+@pytest.mark.parametrize(
+    ("model", "provider"),
+    [
+        ("claude-haiku-5-5", "anthropic"),
+        ("anthropic/claude-haiku-5-5", "anthropic"),
+        ("vertex_ai/claude-haiku-5-5", "vertex_ai"),
+    ],
+)
+def test_haiku_5_5_runtime_profile(local_model_cost_map: None, model: str, provider: str) -> None:
+    assert AnthropicModelInfo._is_adaptive_thinking_model(model, provider) is True
+    assert AnthropicModelInfo._is_always_on_thinking_model(model, provider) is False
+    assert AnthropicModelInfo.forced_tool_use_unsupported(model.removeprefix("anthropic/")) is False
+
+
+def test_haiku_5_5_anthropic_tool_choice_required_maps_to_any(
+    local_model_cost_map: None,
+) -> None:
+    optional_params: Final = litellm.AnthropicConfig().map_openai_params(
+        non_default_params={
+            "tools": [dict(GET_WEATHER_TOOL)],
+            "tool_choice": "required",
+        },
+        optional_params={},
+        model="claude-haiku-5-5",
+        drop_params=False,
+    )
+    assert optional_params["tool_choice"] == {"type": "any"}
+
+
+def test_haiku_5_5_bedrock_tool_choice_required_maps_to_any(
+    local_model_cost_map: None,
+) -> None:
+    optional_params: Final = litellm.AmazonConverseConfig().map_openai_params(
+        non_default_params={
+            "tools": [dict(GET_WEATHER_TOOL)],
+            "tool_choice": "required",
+        },
+        optional_params={},
+        model="us.anthropic.claude-haiku-5-5",
+        drop_params=False,
+    )
+    assert optional_params["tool_choice"] == {"any": {}}
diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py
index 237740cf9e6..407da680006 100644
--- a/tests/unit/test_cost_calculator.py
+++ b/tests/unit/test_cost_calculator.py
@@ -1,10 +1,13 @@
 import datetime
+import json
 import time
 from pathlib import Path
 from types import MappingProxyType, SimpleNamespace
 from typing import Final, cast
 
+import httpx
 import pytest
+import respx
 from pydantic import BaseModel
 
 import litellm
@@ -962,9 +965,9 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
     router: Final = Router(
         model_list=[
             {
-                "model_name": "semantic-ranker-default-004",
+                "model_name": "semantic-ranker-custom-test",
                 "litellm_params": {
-                    "model": "vertex_ai/semantic-ranker-default-004",
+                    "model": "vertex_ai/semantic-ranker-custom-test",
                     "vertex_project": "test-project",
                     "vertex_location": "us-east5",
                 },
@@ -973,7 +976,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
         ]
     )
     router_model_id: Final = router.model_list[0]["model_info"]["id"]
-    assert litellm.model_cost["vertex_ai/semantic-ranker-default-004"].get("input_cost_per_query") is None
+    assert litellm.model_cost.get("vertex_ai/semantic-ranker-custom-test", {}).get("input_cost_per_query") is None
 
     response: Final = RerankResponse(
         id="vertex_ai_rerank_test",
@@ -983,7 +986,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
 
     cost: Final = completion_cost(
         completion_response=response,
-        model="vertex_ai/semantic-ranker-default-004",
+        model="vertex_ai/semantic-ranker-custom-test",
         custom_llm_provider="vertex_ai",
         call_type="arerank",
         custom_pricing=True,
@@ -5343,3 +5346,620 @@ def test_completion_cost_is_zero_when_explicit_rates_are_zero(monkeypatch: pytes
     )
 
     assert cost == 0.0
+
+
+@pytest.fixture
+def isolated_pricing_registry(local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
+    monkeypatch.setattr(litellm, "open_ai_chat_completion_models", set(litellm.open_ai_chat_completion_models))
+    monkeypatch.setattr(litellm, "models_by_provider", dict(litellm.models_by_provider))
+
+
+_CUSTOM_PRICING_MODEL: Final = "migration-custom-pricing-chat"
+
+
+_CUSTOM_PRICING_RATES: Final = MappingProxyType(
+    {"input_cost_per_token": 0.0000008, "output_cost_per_token": 0.0000032}
+)
+
+
+_CUSTOM_PRICING_EXPECTED_COST: Final = 7 * 0.0000008 + 4 * 0.0000032
+
+
+def _custom_pricing_chunk(choices: list[dict[str, object]], usage: dict[str, int] | None = None) -> str:
+    chunk: Final = {
+        "id": "chatcmpl-custom-pricing",
+        "object": "chat.completion.chunk",
+        "created": 1,
+        "model": _CUSTOM_PRICING_MODEL,
+        "choices": choices,
+        **({"usage": usage} if usage is not None else {}),
+    }
+    return f"data: {json.dumps(chunk)}\n\n"
+
+
+def _custom_pricing_upstream(request: httpx.Request) -> httpx.Response:
+    if json.loads(request.content).get("stream") is True:
+        body: Final = "".join(
+            (
+                _custom_pricing_chunk(
+                    [{"index": 0, "delta": {"role": "assistant", "content": "I am ready to help."}, "finish_reason": None}]
+                ),
+                _custom_pricing_chunk([{"index": 0, "delta": {}, "finish_reason": "stop"}]),
+                _custom_pricing_chunk([], {"prompt_tokens": 7, "completion_tokens": 4, "total_tokens": 11}),
+                "data: [DONE]\n\n",
+            )
+        )
+        return httpx.Response(200, text=body, headers={"content-type": "text/event-stream"})
+    return httpx.Response(
+        200,
+        json={
+            "id": "chatcmpl-custom-pricing",
+            "object": "chat.completion",
+            "created": 1,
+            "model": _CUSTOM_PRICING_MODEL,
+            "choices": [
+                {"index": 0, "message": {"role": "assistant", "content": "I am ready to help."}, "finish_reason": "stop"}
+            ],
+            "usage": {"prompt_tokens": 7, "completion_tokens": 4, "total_tokens": 11},
+        },
+    )
+
+
+@pytest.mark.parametrize("rate", (0.0, 0.001))
+@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost"))
+@pytest.mark.usefixtures("isolated_pricing_registry")
+@respx.mock
+def test_router_cache_only_pricing_preserves_uncached_token_charges(rate: float, cache_field: str) -> None:
+    litellm.register_model(
+        {_CUSTOM_PRICING_MODEL: {**_CUSTOM_PRICING_RATES, "litellm_provider": "openai", "mode": "chat"}},
+        persist_across_reloads=False,
+    )
+    respx.post("https://api.openai.com/v1/chat/completions").mock(side_effect=_custom_pricing_upstream)
+    router: Final = litellm.Router(
+        model_list=[
+            {
+                "model_name": "cache-priced-deployment",
+                "litellm_params": {
+                    "model": f"openai/{_CUSTOM_PRICING_MODEL}",
+                    "api_key": "sk-test",
+                    cache_field: rate,
+                },
+                "model_info": {"id": "cache-only-deployment"},
+            }
+        ]
+    )
+
+    response: Final = router.completion(
+        model="cache-priced-deployment", messages=[{"role": "user", "content": "How are you?"}]
+    )
+
+    assert response._hidden_params["response_cost"] == pytest.approx(_CUSTOM_PRICING_EXPECTED_COST)
+
+
+@pytest.mark.parametrize("profile_prefix", ("us", "global"))
+@pytest.mark.parametrize(
+    "model_name",
+    ("gpt-5.6-sol", "gpt-5.6-luna", "gpt-5.6-terra", "gpt-6-sol", "gpt-6-luna", "gpt-6-astra"),
+)
+@pytest.mark.parametrize("arn", (False,))
+def test_bedrock_converse_cost_uses_invoked_profile(
+    _local_model_cost_map: None, model_name: str, profile_prefix: str, arn: bool
+) -> None:
+    model: Final = f"openai.{model_name}"
+    profile: Final = f"{profile_prefix}.{model}"
+    invoked: Final = f"arn:aws:bedrock:us-east-1:123456789012:inference-profile/{profile}" if arn else profile
+    response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15))
+    prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock")
+
+    cost: Final = completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": invoked},
+    )
+
+    assert cost == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"])
+    assert response.model == model
+
+
+@pytest.mark.parametrize("custom_pricing", (False, True))
+def test_bedrock_converse_profile_preserves_explicit_base_and_custom_pricing(
+    _local_model_cost_map: None, custom_pricing: bool
+) -> None:
+    model: Final = "openai.gpt-6-sol"
+    response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15))
+    prices: Final = litellm.get_model_info(model, custom_llm_provider="bedrock")
+
+    cost: Final = completion_cost(
+        completion_response=response,
+        model=model,
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": f"us.{model}"},
+        custom_pricing=custom_pricing,
+        base_model=None if custom_pricing else model,
+    )
+
+    assert cost == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"])
+
+
+@pytest.mark.parametrize("stream", (False, True))
+def test_bedrock_converse_cost_retains_profile_after_dispatch_consumes_optional_params(
+    _local_model_cost_map: None, stream: bool
+) -> None:
+    from litellm.cost_calculator import pricing_entry_for_cost_calc
+
+    model: Final = "openai.gpt-5.6-sol"
+    profile: Final = f"us.{model}"
+    logging_obj: Final = Logging(
+        model=model,
+        messages=[{"role": "user", "content": "hi"}],
+        stream=stream,
+        call_type="completion",
+        start_time=datetime.datetime(2026, 1, 1),
+        litellm_call_id="bedrock-profile-cost",
+        function_id="bedrock-profile-cost",
+    )
+    logging_obj.update_environment_variables(
+        litellm_params={}, optional_params={"model_id": profile}, custom_llm_provider="bedrock"
+    )
+    logging_obj.optional_params.pop("model_id")
+    response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15))
+    prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock")
+
+    assert logging_obj._response_cost_calculator(response) == pytest.approx(
+        10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"]
+    )
+    entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj)
+    assert entry is not None
+    assert entry[0] == prices["key"]
+
+
+@pytest.mark.parametrize(
+    "invoked_model_id",
+    (None, "", 123, "unmapped-profile", "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/opaque"),
+)
+def test_bedrock_converse_cost_keeps_configured_rates_when_target_has_no_prices(
+    _local_model_cost_map: None, invoked_model_id: object
+) -> None:
+    model: Final = "openai.gpt-6-sol"
+    response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15))
+    expected: Final = completion_cost(completion_response=response, model=model, custom_llm_provider="bedrock")
+
+    assert (
+        completion_cost(
+            completion_response=response,
+            model=model,
+            custom_llm_provider="bedrock",
+            optional_params={"model_id": invoked_model_id},
+        )
+        == expected
+    )
+
+
+def test_non_bedrock_cost_ignores_bedrock_model_id(_local_model_cost_map: None) -> None:
+    response: Final = ModelResponse(
+        model="gpt-6-sol", usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)
+    )
+    expected: Final = completion_cost(completion_response=response, custom_llm_provider="openai")
+
+    assert (
+        completion_cost(
+            completion_response=response,
+            custom_llm_provider="openai",
+            optional_params={"model_id": "us.openai.gpt-6-sol"},
+        )
+        == expected
+    )
+
+
+@pytest.mark.parametrize("rate", (0.0, 0.001))
+@pytest.mark.parametrize("persist_across_reloads", (True, False))
+@pytest.mark.parametrize("routed_response", (True, False))
+@pytest.mark.parametrize("metadata_prefix", ("bedrock/", "bedrock/converse/"))
+def test_bedrock_converse_profile_preserves_registered_price_override(
+    _local_model_cost_map: None,
+    monkeypatch: pytest.MonkeyPatch,
+    rate: float,
+    persist_across_reloads: bool,
+    routed_response: bool,
+    metadata_prefix: str,
+) -> None:
+    import litellm.utils as model_utils
+    from litellm.cost_calculator import pricing_entry_for_cost_calc
+
+    monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {})
+    catalog: Final = dict(litellm.model_cost)
+    model: Final = "openai.gpt-5.6-sol"
+    litellm.register_model(
+        {f"{metadata_prefix}{model}": {"supports_function_calling": True}},
+        persist_across_reloads=persist_across_reloads,
+    )
+    litellm.register_model(
+        {
+            model: {
+                "input_cost_per_token": rate,
+                "output_cost_per_token": rate,
+                "litellm_provider": "bedrock_converse",
+                "mode": "chat",
+            }
+        },
+        persist_across_reloads=persist_across_reloads,
+    )
+    litellm.register_model(
+        {model: {"supports_function_calling": True, "input_cost_per_token": None}},
+        persist_across_reloads=persist_across_reloads,
+    )
+    response: Final = ModelResponse(
+        model=f"bedrock/converse/{model}" if routed_response else model,
+        usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15),
+    )
+
+    logging_obj: Final = Logging(
+        model=model,
+        messages=[],
+        stream=False,
+        call_type="completion",
+        start_time=datetime.datetime(2026, 1, 1),
+        litellm_call_id="registered-pricing",
+        function_id="registered-pricing",
+    )
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": f"us.{model}"},
+        litellm_logging_obj=logging_obj,
+    ) == pytest.approx(15 * rate)
+
+    assert logging_obj.billed_token_rates is not None
+    assert logging_obj.billed_token_rates.input_cost_per_token == rate
+    assert logging_obj.billed_token_rates.output_cost_per_token == rate
+    entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, None)
+    assert entry is not None
+    assert entry[0] == model
+    assert entry[1]["input_cost_per_token"] == rate
+    assert entry[1]["output_cost_per_token"] == rate
+
+    updated_rate: Final = rate + 0.002
+    litellm.register_model(
+        {model: {"input_cost_per_token": str(updated_rate)}}, persist_across_reloads=persist_across_reloads
+    )
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": f"us.{model}"},
+    ) == pytest.approx(10 * updated_rate + 5 * rate)
+
+    monkeypatch.setattr(litellm, "model_cost", catalog)
+    model_utils._invalidate_model_cost_lowercase_map()
+    model_utils.reapply_runtime_model_cost_registrations()
+    profile_prices: Final = litellm.get_model_info(f"us.{model}", custom_llm_provider="bedrock")
+    expected_after_reload: Final = (
+        10 * updated_rate + 5 * rate
+        if persist_across_reloads
+        else 10 * profile_prices["input_cost_per_token"] + 5 * profile_prices["output_cost_per_token"]
+    )
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": f"us.{model}"},
+    ) == pytest.approx(expected_after_reload)
+
+
+def test_bedrock_converse_profile_ignores_registered_capabilities_without_prices(
+    _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    import litellm.utils as model_utils
+
+    monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {})
+    model: Final = "openai.gpt-6-sol"
+    litellm.register_model({model: {"supports_function_calling": True}})
+    response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15))
+    prices: Final = litellm.get_model_info(f"us.{model}", custom_llm_provider="bedrock")
+
+    assert completion_cost(
+        completion_response=response,
+        model=model,
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": f"us.{model}"},
+    ) == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"])
+
+
+@pytest.mark.parametrize("rate", (0.0, 0.001))
+@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost"))
+@pytest.mark.parametrize("has_base_rates", (False, True))
+@pytest.mark.parametrize("persist_across_reloads", (False, True))
+@pytest.mark.parametrize("profile_prefix", ("us", "global"))
+@pytest.mark.parametrize("provider", (None, "bedrock"))
+def test_bedrock_converse_profile_preserves_cache_only_registered_prices(
+    _local_model_cost_map: None,
+    monkeypatch: pytest.MonkeyPatch,
+    rate: float,
+    cache_field: str,
+    has_base_rates: bool,
+    persist_across_reloads: bool,
+    profile_prefix: str,
+    provider: str | None,
+) -> None:
+    import litellm.utils as model_utils
+    from litellm.cost_calculator import pricing_entry_for_cost_calc
+
+    monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {})
+    model: Final = "openai.cache-overlay-test"
+    profile: Final = f"{profile_prefix}.{model}"
+    catalog: Final = {
+        **litellm.model_cost,
+        model: {
+            "litellm_provider": "bedrock",
+            "mode": "chat",
+            **({"input_cost_per_token": 0.01, "output_cost_per_token": 0.02} if has_base_rates else {}),
+        },
+        profile: {
+            "litellm_provider": "bedrock",
+            "mode": "chat",
+            "input_cost_per_token": 0.02,
+            "output_cost_per_token": 0.04,
+            "cache_read_input_token_cost": 0.005,
+            "cache_creation_input_token_cost": 0.025,
+        },
+    }
+    profile_before: Final = dict(catalog[profile])
+    monkeypatch.setattr(litellm, "model_cost", dict(catalog))
+    model_utils._invalidate_model_cost_lowercase_map()
+    litellm.register_model({model: {cache_field: rate}}, persist_across_reloads=persist_across_reloads)
+    response: Final = ModelResponse(
+        model=model,
+        usage=Usage(
+            prompt_tokens=15,
+            completion_tokens=3,
+            total_tokens=18,
+            prompt_tokens_details=PromptTokensDetailsWrapper(
+                cached_tokens=5 if cache_field == "cache_read_input_token_cost" else 0
+            ),
+            cache_creation_input_tokens=5 if cache_field == "cache_creation_input_token_cost" else 0,
+        ),
+    )
+    logging_obj: Final = Logging(
+        model=model,
+        messages=[],
+        stream=False,
+        call_type="completion",
+        start_time=datetime.datetime(2026, 1, 1),
+        litellm_call_id="cache-overlay",
+        function_id="cache-overlay",
+    )
+    logging_obj.model_call_details["model_id"] = profile
+    expected: Final = 10 * 0.02 + 3 * 0.04 + 5 * rate
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider=provider,
+        optional_params={"model_id": profile},
+        litellm_logging_obj=logging_obj,
+    ) == pytest.approx(expected)
+    breakdown_key: Final = "cache_read_cost" if cache_field == "cache_read_input_token_cost" else "cache_creation_cost"
+    assert logging_obj.cost_breakdown is not None
+    assert logging_obj.cost_breakdown.get(breakdown_key, 0.0) == pytest.approx(5 * rate)
+    assert logging_obj.billed_token_rates is not None
+    assert (
+        logging_obj.billed_token_rates.cache_read_input_token_cost
+        if cache_field == "cache_read_input_token_cost"
+        else logging_obj.billed_token_rates.cache_creation_input_token_cost
+    ) == rate
+    entry: Final = pricing_entry_for_cost_calc(
+        f"bedrock/converse/{model}", response, provider, False, None, None, None, logging_obj
+    )
+    assert entry is not None
+    assert entry[1]["input_cost_per_token"] == 0.02
+    assert entry[1]["output_cost_per_token"] == 0.04
+    assert entry[1][cache_field] == rate
+    assert litellm.model_cost[profile] == profile_before
+
+    monkeypatch.setattr(litellm, "model_cost", dict(catalog))
+    model_utils._invalidate_model_cost_lowercase_map()
+    model_utils.reapply_runtime_model_cost_registrations()
+    expected_after_reload: Final = (
+        10 * 0.02 + 3 * 0.04 + 5 * (rate if persist_across_reloads else catalog[profile][cache_field])
+    )
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider=provider,
+        optional_params={"model_id": profile},
+        litellm_logging_obj=logging_obj,
+    ) == pytest.approx(expected_after_reload)
+
+
+@pytest.mark.parametrize("profile", ("us.openai.missing-profile-test", "us.openai.unpriced-profile-test"))
+def test_bedrock_cache_registration_with_unpriced_profile_keeps_registered_rates(
+    _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch, profile: str
+) -> None:
+    import litellm.utils as model_utils
+
+    model: Final = "openai.registered-cache-test"
+    monkeypatch.setattr(
+        litellm,
+        "model_cost",
+        {
+            **litellm.model_cost,
+            model: {
+                "litellm_provider": "bedrock",
+                "mode": "chat",
+                "input_cost_per_token": 0.01,
+                "output_cost_per_token": 0.02,
+            },
+            "us.openai.unpriced-profile-test": {"litellm_provider": "bedrock", "mode": "chat"},
+        },
+    )
+    model_utils._invalidate_model_cost_lowercase_map()
+    litellm.register_model({model: {"cache_read_input_token_cost": 0.001}}, persist_across_reloads=False)
+    response: Final = ModelResponse(
+        model=model,
+        usage=Usage(
+            prompt_tokens=15,
+            completion_tokens=3,
+            total_tokens=18,
+            prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5),
+        ),
+    )
+    assert completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": profile},
+    ) == pytest.approx(10 * 0.01 + 3 * 0.02 + 5 * 0.001)
+
+
+@pytest.mark.parametrize("direction", ("input", "output"))
+@pytest.mark.parametrize("rate", (0.0, 0.004))
+@pytest.mark.parametrize("prompt_tokens", (100, 300_001))
+def test_bedrock_partial_registration_overrides_only_its_profile_direction(
+    _local_model_cost_map: None,
+    monkeypatch: pytest.MonkeyPatch,
+    direction: str,
+    rate: float,
+    prompt_tokens: int,
+) -> None:
+    from litellm.cost_calculator import pricing_entry_for_cost_calc
+
+    model: Final = "openai.partial-pricing-test"
+    profile: Final = f"us.{model}"
+    profile_entry: Final = {
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "input_cost_per_token": 0.01,
+        "output_cost_per_token": 0.02,
+        "input_cost_per_token_above_300k_tokens": 0.03,
+        "output_cost_per_token_above_300k_tokens": 0.06,
+        "cache_read_input_token_cost": 0.001,
+    }
+    monkeypatch.setattr(litellm, "model_cost", {**litellm.model_cost, profile: dict(profile_entry)})
+    litellm.register_model({model: {f"{direction}_cost_per_token": rate}}, persist_across_reloads=False)
+    response: Final = ModelResponse(
+        model=model,
+        usage=Usage(
+            prompt_tokens=prompt_tokens,
+            completion_tokens=3,
+            total_tokens=prompt_tokens + 3,
+            prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5),
+        ),
+    )
+    logging_obj: Final = Logging(
+        model=model,
+        messages=[],
+        stream=False,
+        call_type="completion",
+        start_time=datetime.datetime(2026, 1, 1),
+        litellm_call_id="partial-pricing",
+        function_id="partial-pricing",
+    )
+    logging_obj.model_call_details["model_id"] = profile
+    input_rate: Final = rate if direction == "input" else (0.03 if prompt_tokens > 300_000 else 0.01)
+    output_rate: Final = rate if direction == "output" else (0.06 if prompt_tokens > 300_000 else 0.02)
+    assert completion_cost(
+        completion_response=response,
+        model=model,
+        custom_llm_provider="bedrock",
+        litellm_logging_obj=logging_obj,
+    ) == pytest.approx((prompt_tokens - 5) * input_rate + 3 * output_rate + 5 * 0.001)
+    assert logging_obj.billed_token_rates is not None
+    assert logging_obj.billed_token_rates.input_cost_per_token == input_rate
+    assert logging_obj.billed_token_rates.output_cost_per_token == output_rate
+    assert logging_obj.cost_breakdown is not None
+    assert logging_obj.cost_breakdown["cache_read_cost"] == pytest.approx(5 * 0.001)
+    entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj)
+    assert entry is not None
+    assert entry[1][f"{direction}_cost_per_token"] == rate
+    assert litellm.model_cost[profile] == profile_entry
+
+
+@pytest.mark.parametrize("prompt_tokens", (299_999, 300_000, 300_001))
+@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost"))
+@pytest.mark.parametrize("tier_override", (None, 0.0, 0.003))
+def test_bedrock_registered_cache_prices_preserve_dynamic_threshold_rates(
+    _local_model_cost_map: None,
+    monkeypatch: pytest.MonkeyPatch,
+    prompt_tokens: int,
+    cache_field: str,
+    tier_override: float | None,
+) -> None:
+    import litellm.utils as model_utils
+    from litellm.cost_calculator import pricing_entry_for_cost_calc
+
+    model: Final = "openai.threshold-overlay-test"
+    profile: Final = f"us.{model}"
+    tier_field: Final = f"{cache_field}_above_300k_tokens"
+    monkeypatch.setattr(
+        litellm,
+        "model_cost",
+        {
+            **litellm.model_cost,
+            profile: {
+                "litellm_provider": "bedrock",
+                "mode": "chat",
+                "input_cost_per_token": 0.01,
+                "output_cost_per_token": 0.02,
+                "input_cost_per_token_above_300k_tokens": 0.03,
+                "output_cost_per_token_above_300k_tokens": 0.06,
+                tier_field: 0.007,
+            },
+        },
+    )
+    model_utils._invalidate_model_cost_lowercase_map()
+    litellm.register_model(
+        {
+            model: {
+                cache_field: 0.001,
+                **({tier_field: tier_override} if tier_override is not None else {}),
+            }
+        },
+        persist_across_reloads=False,
+    )
+    usage: Final = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=3,
+        total_tokens=prompt_tokens + 3,
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            cached_tokens=5 if cache_field == "cache_read_input_token_cost" else 0
+        ),
+        cache_creation_input_tokens=5 if cache_field == "cache_creation_input_token_cost" else 0,
+    )
+    response: Final = ModelResponse(model=model, usage=usage)
+    logging_obj: Final = Logging(
+        model=model,
+        messages=[],
+        stream=False,
+        call_type="completion",
+        start_time=datetime.datetime(2026, 1, 1),
+        litellm_call_id="threshold-overlay",
+        function_id="threshold-overlay",
+    )
+    logging_obj.model_call_details["model_id"] = profile
+    expected_input_rate: Final = 0.03 if prompt_tokens > 300_000 else 0.01
+    expected_output_rate: Final = 0.06 if prompt_tokens > 300_000 else 0.02
+    expected_cache_rate: Final = (
+        (tier_override if tier_override is not None else 0.007) if prompt_tokens > 300_000 else 0.001
+    )
+    total: Final = completion_cost(
+        completion_response=response,
+        model=f"bedrock/converse/{model}",
+        custom_llm_provider="bedrock",
+        optional_params={"model_id": profile},
+        litellm_logging_obj=logging_obj,
+    )
+    assert total == pytest.approx(
+        (prompt_tokens - 5) * expected_input_rate + 3 * expected_output_rate + 5 * expected_cache_rate
+    )
+    breakdown_key: Final = "cache_read_cost" if cache_field == "cache_read_input_token_cost" else "cache_creation_cost"
+    assert logging_obj.cost_breakdown is not None
+    assert logging_obj.cost_breakdown.get(breakdown_key, 0.0) == pytest.approx(5 * expected_cache_rate)
+    assert logging_obj.billed_token_rates is not None
+    assert logging_obj.billed_token_rates.input_cost_per_token == expected_input_rate
+    assert logging_obj.billed_token_rates.output_cost_per_token == expected_output_rate
+    entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj)
+    assert entry is not None
+    assert entry[1]["input_cost_per_token_above_300k_tokens"] == 0.03
+    assert entry[1][tier_field] == (tier_override if tier_override is not None else 0.007)
diff --git a/tests/unit/test_main.py b/tests/unit/test_main.py
index c7e9301c02b..0302c3d648b 100644
--- a/tests/unit/test_main.py
+++ b/tests/unit/test_main.py
@@ -986,6 +986,50 @@ def test_responses_api_bridge_check_gpt_5_4_tools_with_reasoning_none_stays_chat
     assert model_info.get("mode") != "responses"
 
 
+@pytest.mark.parametrize(
+    "model, custom_llm_provider, reasoning_effort",
+    [
+        ("gpt-6.1-sol", "openai", "none"),
+        ("gpt-6.1-sol", "openai", {"effort": "none"}),
+        ("gpt-6-astra", "azure", "none"),
+    ],
+)
+def test_responses_api_bridge_check_tools_with_a_none_the_row_refuses_routes_to_responses(
+    local_model_cost_map: None, model: str, custom_llm_provider: str, reasoning_effort: object
+) -> None:
+    """The ``none`` escape hatch only holds when the chat gate forwards it. These rows refuse
+    ``none``, so the gate drops it (or refuses the call) and the provider runs its default effort,
+    under which Chat Completions rejects function tools; the bridge has to fire the way it does
+    for an unset effort. Row-derived: the test follows the flag, never the vendor's answer."""
+    from litellm.main import responses_api_bridge_check
+
+    row_key: Final = model if custom_llm_provider == "openai" else f"{custom_llm_provider}/{model}"
+    assert litellm.model_cost[row_key]["supports_none_reasoning_effort"] is False
+
+    model_info, _ = responses_api_bridge_check(
+        model=model,
+        custom_llm_provider=custom_llm_provider,
+        tools=[{"type": "function", "function": {"name": "get_capital"}}],
+        reasoning_effort=reasoning_effort,
+    )
+
+    assert model_info.get("mode") == "responses"
+
+
+def test_responses_api_bridge_check_a_none_the_row_refuses_stays_chat_without_tools(
+    local_model_cost_map: None,
+) -> None:
+    """Without function tools nothing forces the Responses route: the dropped ``none`` leaves a
+    plain chat call at the default effort, as for any other dropped level."""
+    from litellm.main import responses_api_bridge_check
+
+    model_info, _ = responses_api_bridge_check(
+        model="gpt-6.1-sol", custom_llm_provider="openai", reasoning_effort="none"
+    )
+
+    assert model_info.get("mode") != "responses"
+
+
 def test_responses_api_bridge_check_reasoning_none_with_summary_still_routes_to_responses():
     """A reasoning summary is Responses-only regardless of effort value."""
     from litellm.main import responses_api_bridge_check
@@ -1362,11 +1406,15 @@ _FOUNDRY_FUNCTION_TOOL: Final = ({"type": "function", "function": {"name": "get_
         pytest.param("gpt-6-astra", "https://myresource.openai.azure.com", None, id="gpt-6-azure-openai-host"),
         pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, "low", id="gpt-5.6-explicit-effort"),
         pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, {"effort": "high"}, id="gpt-5.6-explicit-effort-dict"),
+        pytest.param("gpt-6-astra", _FOUNDRY_API_BASE, "none", id="gpt-6-row-refused-none"),
     ],
 )
 def test_responses_api_bridge_check_azure_ai_foundry_rejected_tools_route_to_responses(
     model_name, api_base, reasoning_effort
 ):
+    """The explicit ``none`` only keeps a Foundry gpt-6 request on chat while the deployment takes
+    it; the ``azure_ai/gpt-6-astra`` row says it does not, so the gate drops it and the call runs at
+    the default effort, under which Foundry rejects function tools from gpt-6 on."""
     from litellm.main import responses_api_bridge_check
 
     model_info, model = responses_api_bridge_check(
@@ -1384,7 +1432,6 @@ def test_responses_api_bridge_check_azure_ai_foundry_rejected_tools_route_to_res
 @pytest.mark.parametrize(
     "model_name, api_base, reasoning_effort",
     [
-        pytest.param("gpt-6-astra", _FOUNDRY_API_BASE, "none", id="explicit-none-stays-chat"),
         pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, None, id="gpt-5.6-unset-effort-stays-chat"),
         pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, "none", id="gpt-5.6-explicit-none-stays-chat"),
         pytest.param("gpt-5.5", _FOUNDRY_API_BASE, "high", id="gpt-5.5-explicit-effort-stays-chat"),
@@ -4222,3 +4269,98 @@ def test_completion_rejects_untranslatable_tool_choice_with_a_400(tool_choice):
         )
     assert exc_info.value.status_code == 400
     assert f"tool_choice={tool_choice}" in str(exc_info.value)
+
+
+@pytest.mark.parametrize("stream", (False, True))
+@pytest.mark.parametrize("asynchronous", (False, True))
+@pytest.mark.parametrize("profile,custom_price", ((None, False), ("us.openai.gpt-6-sol", False), (None, True)))
+@pytest.mark.asyncio
+async def test_converse_fallback_prices_the_current_attempt(
+    monkeypatch: pytest.MonkeyPatch, stream: bool, asynchronous: bool, profile: str | None, custom_price: bool
+) -> None:
+    from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
+    from litellm.rust_bridge import configuration
+
+    CONVERSE_ANSWER: Final = json.dumps(
+        {
+            "output": {"message": {"role": "assistant", "content": [{"text": "hi"}]}},
+            "stopReason": "end_turn",
+            "usage": {"inputTokens": 1, "outputTokens": 1, "totalTokens": 2},
+            "metrics": {"latencyMs": 1},
+        }
+    ).encode()
+
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    monkeypatch.setenv("LITELLM_RUST", "0")
+    configuration.rust(False)
+    monkeypatch.setattr(litellm, "model_cost", dict(litellm.model_cost))
+    failed_profile: Final = "us.amazon.nova-micro-v1:0"
+    model: Final = "openai.gpt-6-sol"
+    logging_obj: Final = LiteLLMLogging(
+        model="amazon.nova-micro-v1:0",
+        messages=[{"role": "user", "content": "hi"}],
+        stream=stream,
+        call_type="acompletion" if asynchronous else "completion",
+        start_time=datetime(2026, 1, 1),
+        litellm_call_id="bedrock-fallback-pricing",
+        function_id="bedrock-fallback-pricing",
+    )
+
+    def respond(request: httpx.Request) -> httpx.Response:
+        if failed_profile in request.url.path:
+            return httpx.Response(400, json={"message": "Input is too long for requested model."})
+        assert request.url.path == f"/model/{profile or model}/converse"
+        return httpx.Response(200, content=CONVERSE_ANSWER)
+
+    client: Final = (
+        AsyncHTTPHandler(transport=httpx.MockTransport(respond))
+        if asynchronous
+        else HTTPHandler(client=httpx.Client(transport=httpx.MockTransport(respond)))
+    )
+    kwargs: Final = {
+        "messages": [{"role": "user", "content": "hi"}],
+        "api_key": "test-bearer",
+        "aws_region_name": "us-east-1",
+        "client": client,
+        "litellm_logging_obj": logging_obj,
+        "num_retries": 0,
+        "stream": stream,
+        "fake_stream": stream,
+    }
+    if asynchronous:
+        with pytest.raises(litellm.BadRequestError):
+            await litellm.acompletion(model="bedrock/converse/amazon.nova-micro-v1:0", model_id=failed_profile, **kwargs)
+    else:
+        with pytest.raises(litellm.BadRequestError):
+            litellm.completion(model="bedrock/converse/amazon.nova-micro-v1:0", model_id=failed_profile, **kwargs)
+
+    overrides: Final = {
+        **({"model_id": profile} if profile is not None else {}),
+        **({"input_cost_per_token": 0.001, "output_cost_per_token": 0.002} if custom_price else {}),
+    }
+    response: Final = (
+        await litellm.acompletion(model=f"bedrock/converse/{model}", **kwargs, **overrides)
+        if asynchronous
+        else litellm.completion(model=f"bedrock/converse/{model}", **kwargs, **overrides)
+    )
+    result: Final = (
+        litellm.stream_chunk_builder(
+            [chunk async for chunk in response] if asynchronous else list(response), logging_obj=response.logging_obj
+        )
+        if stream
+        else response
+    )
+    assert result is not None
+    prices: Final = litellm.get_model_info(profile or model, custom_llm_provider="bedrock")
+    expected: Final = (
+        0.001 + 0.002
+        if custom_price
+        else prices["input_cost_per_token"] + prices["output_cost_per_token"]
+    )
+    active_logging: Final = response.logging_obj if stream else logging_obj
+    assert active_logging._response_cost_calculator(result) == pytest.approx(expected)
+    if asynchronous:
+        await client.close()
+    else:
+        client.close()
+    configuration.reset_rust_configuration()
diff --git a/tests/unit/test_model_prices_schema.py b/tests/unit/test_model_prices_schema.py
index faa6b6d2ef7..3e37e47aefa 100644
--- a/tests/unit/test_model_prices_schema.py
+++ b/tests/unit/test_model_prices_schema.py
@@ -511,7 +511,19 @@ def test_deepseek_rows_bill_half_rate_outside_weekday_peak_hours(path: Path):
     assert all(name in rows for name in DEEPSEEK_PRICED_ROWS)
 
 
-PROVIDER_LABELS_WITHOUT_A_MODEL_SET: Final = frozenset({"sagemaker", "bedrock_converse"})
+PROVIDER_LABELS_WITHOUT_A_MODEL_SET: Final = frozenset(
+    {
+        "sagemaker",
+        "bedrock_converse",
+        "coralbricks",
+        "inferenceapis",
+        "microsoft_365_copilot",
+        "openinfer",
+        "prism",
+        "sail",
+        "scaledown",
+    }
+)
 MODES_SERVED_OUTSIDE_THE_LLM_PROVIDER_REGISTRY: Final = frozenset({"search", "evaluation"})
 VERTEX_FAMILIES_A_VERTEX_WILDCARD_GRANT_DOES_NOT_LIST: Final = frozenset(
     {
diff --git a/tests/unit/test_router_model_cost_isolation.py b/tests/unit/test_router_model_cost_isolation.py
index 6a6e4c5b4d4..2a7d9813925 100644
--- a/tests/unit/test_router_model_cost_isolation.py
+++ b/tests/unit/test_router_model_cost_isolation.py
@@ -761,6 +761,178 @@ def test_should_not_downgrade_chatgpt_shared_key_mode_with_alias_override():
         _restore_model_cost_entries(model_keys)
 
 
+@pytest.mark.parametrize("service_tier", ("default", "priority", "flex"))
+@pytest.mark.parametrize(
+    "field",
+    ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost", "input_cost_per_token_priority"),
+)
+@pytest.mark.parametrize("rate", (0.0, 0.004))
+@pytest.mark.parametrize("explicit_base", (False, True))
+@pytest.mark.parametrize("provider", (None, "bedrock"))
+@pytest.mark.parametrize("registration_path", ("direct", "startup", "reload"))
+def test_bedrock_deployment_inherits_invoked_profile_around_custom_prices(
+    monkeypatch: pytest.MonkeyPatch,
+    field: str,
+    rate: float,
+    explicit_base: bool,
+    provider: str | None,
+    registration_path: str,
+    service_tier: str,
+) -> None:
+    from litellm.cost_calculator import completion_cost
+    from litellm.types.utils import ModelResponse, Usage, PromptTokensDetailsWrapper
+
+    model: Final = "openai.gpt-5.6-sol"
+    profile: Final = f"us.{model}"
+    base_model: Final = f"global.{model}"
+    profile_prices: Final = {
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "input_cost_per_token": 0.01,
+        "output_cost_per_token": 0.02,
+        "cache_read_input_token_cost": 0.001,
+        "input_cost_per_token_priority": 0.05,
+        "output_cost_per_token_priority": 0.06,
+        "input_cost_per_token_flex": 0.007,
+        "output_cost_per_token_flex": 0.008,
+    }
+    base_prices: Final = {**profile_prices, "input_cost_per_token": 0.03, "output_cost_per_token": 0.04}
+    monkeypatch.setattr(
+        litellm, "model_cost", {**litellm.model_cost, profile: dict(profile_prices), base_model: dict(base_prices)}
+    )
+    deployment: Final = Deployment(
+        model_name="profile-priced",
+        litellm_params=LiteLLM_Params(
+            model=f"converse/{model}" if provider else f"bedrock/converse/{model}",
+            model_id=profile,
+            custom_llm_provider=provider,
+        ),
+        model_info=ModelInfo(
+            **{
+                "id": "profile-priced-deployment",
+                field: rate,
+                **({"base_model": f"bedrock/{base_model}"} if explicit_base else {}),
+            }
+        ),
+    )
+    if registration_path == "direct":
+        Router._register_deployment_pricing(deployment)
+    else:
+        router: Final = Router(model_list=[deployment.to_json(exclude_none=True)])
+        if registration_path == "reload":
+            router._replay_model_cost_registrations()
+    response: Final = ModelResponse(
+        model=model,
+        usage=Usage(
+            prompt_tokens=100,
+            completion_tokens=3,
+            total_tokens=103,
+            prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5),
+        ),
+    )
+    catalog: Final = base_prices if explicit_base else profile_prices
+    input_field: Final = "input_cost_per_token" + (f"_{service_tier}" if service_tier != "default" else "")
+    output_field: Final = "output_cost_per_token" + (f"_{service_tier}" if service_tier != "default" else "")
+    input_rate: Final = rate if field == input_field else catalog[input_field]
+    output_rate: Final = rate if field == output_field else catalog[output_field]
+    cache_rate: Final = rate if field == "cache_read_input_token_cost" else 0.001
+    assert completion_cost(
+        model=model,
+        completion_response=response,
+        custom_llm_provider="bedrock",
+        custom_pricing=True,
+        router_model_id="profile-priced-deployment",
+        service_tier=service_tier,
+    ) == pytest.approx(95 * input_rate + 3 * output_rate + 5 * cache_rate)
+    assert litellm.model_cost[profile] == profile_prices
+
+
+@pytest.mark.parametrize("catalog_entry", (None, {"litellm_provider": 1, "mode": "chat"}))
+@pytest.mark.parametrize("known_model", (False, True))
+@pytest.mark.parametrize("explicit_base", (False, True))
+@pytest.mark.parametrize("service_tier", ("default", "priority", "flex"))
+@pytest.mark.parametrize("override", (None, "cache_read_input_token_cost", "input_cost_per_token_priority"))
+@pytest.mark.parametrize("reload", (False, True))
+def test_bedrock_deployment_keeps_custom_prices_when_profile_lookup_fails(
+    monkeypatch: pytest.MonkeyPatch,
+    catalog_entry: dict[str, object] | None,
+    known_model: bool,
+    explicit_base: bool,
+    service_tier: str,
+    override: str | None,
+    reload: bool,
+) -> None:
+    from litellm.cost_calculator import completion_cost
+    from litellm.types.utils import ModelResponse, Usage, PromptTokensDetailsWrapper
+
+    model: Final = "anthropic.unmapped-profile-pricing-test"
+    profile: Final = (
+        "us.anthropic.invalid-profile-pricing-test"
+        if catalog_entry is not None
+        else "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/opaque-test"
+    )
+    configured_prices: Final = {
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "input_cost_per_token": 0.03,
+        "output_cost_per_token": 0.04,
+        "cache_read_input_token_cost": 0.001,
+        "input_cost_per_token_priority": 0.05,
+        "output_cost_per_token_priority": 0.06,
+        "input_cost_per_token_flex": 0.007,
+        "output_cost_per_token_flex": 0.008,
+    }
+    monkeypatch.setattr(
+        litellm,
+        "model_cost",
+        {
+            **litellm.model_cost,
+            **({model: dict(configured_prices)} if known_model else {}),
+            **({profile: catalog_entry} if catalog_entry is not None else {}),
+        },
+    )
+    deployment: Final = Deployment(
+        model_name="custom-priced",
+        litellm_params=LiteLLM_Params(model=f"bedrock/converse/{model}", model_id=profile),
+        model_info=ModelInfo(
+            id="unmapped-profile-deployment",
+            input_cost_per_token=0.01,
+            output_cost_per_token=0.02,
+            **({override: 0.0} if override else {}),
+            **({"base_model": f"bedrock/{profile}"} if explicit_base else {}),
+        ),
+    )
+    router: Final = Router(model_list=[deployment.to_json(exclude_none=True)])
+    if reload:
+        router._replay_model_cost_registrations()
+    inherit_configured: Final = known_model and not explicit_base
+    tier_rates: Final = inherit_configured and service_tier != "default"
+    input_rate: Final = configured_prices[f"input_cost_per_token_{service_tier}"] if tier_rates else 0.01
+    output_rate: Final = configured_prices[f"output_cost_per_token_{service_tier}"] if tier_rates else 0.02
+    effective_input: Final = 0.0 if override == "input_cost_per_token_priority" and service_tier == "priority" else input_rate
+    cache_rate: Final = 0.0 if override == "cache_read_input_token_cost" else (0.001 if inherit_configured else effective_input)
+    assert completion_cost(
+        model=model,
+        completion_response=ModelResponse(
+            model=model,
+            usage=Usage(
+                prompt_tokens=100,
+                completion_tokens=3,
+                total_tokens=103,
+                prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=80),
+            ),
+        ),
+        custom_llm_provider="bedrock",
+        custom_pricing=True,
+        router_model_id="unmapped-profile-deployment",
+        service_tier=service_tier,
+    ) == pytest.approx(20 * effective_input + 80 * cache_rate + 3 * output_rate)
+    if known_model:
+        assert {
+            key: value for key, value in litellm.model_cost[model].items() if key in configured_prices
+        } == configured_prices
+
+
 def test_partial_custom_pricing_inherits_builtin_cache_pricing():
     """A deployment that overrides only input/output cost on a cache-supporting
     model must still bill cache_read and cache_creation tokens. Before the
@@ -1771,14 +1943,7 @@ def test_a_reload_rebuilds_exactly_what_a_fresh_boot_registered() -> None:
         )
 
         rebuilt = litellm.model_cost["priced-id"]
-        assert at_boot.items() <= rebuilt.items(), (
-            f"the rebuild changed or dropped a field the boot registration wrote: "
-            f"{ {k: (v, rebuilt.get(k)) for k, v in at_boot.items() if rebuilt.get(k) != v} }"
-        )
-        assert {field: rebuilt[field] for field in set(rebuilt) - set(at_boot)} == {
-            "db_model": False,
-            "member_auto_router": False,
-        }
+        assert at_boot == rebuilt
         assert "member_auto_router" not in litellm.model_cost["gpt-4o"]
         assert router.model_list
     finally:
diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py
index 67f50decf21..cb6a16e0c4c 100644
--- a/tests/unit/test_utils.py
+++ b/tests/unit/test_utils.py
@@ -756,10 +756,41 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
             "type": "object",
             "properties": {
                 "supports_computer_use": {"type": "boolean"},
+                "cache_creation_input_token_cost_above_272k_tokens_decisions": {"type": "number"},
+                "cache_creation_input_token_cost_above_272k_tokens_ultrafast": {"type": "number"},
+                "cache_creation_input_token_cost_decisions": {"type": "number"},
+                "cache_creation_input_token_cost_ultrafast": {"type": "number"},
+                "cache_read_input_token_cost_above_272k_tokens_decisions": {"type": "number"},
+                "cache_read_input_token_cost_above_272k_tokens_ultrafast": {"type": "number"},
+                "cache_read_input_token_cost_balanced": {"type": "number"},
+                "cache_read_input_token_cost_decisions": {"type": "number"},
+                "cache_read_input_token_cost_ultrafast": {"type": "number"},
+                "cost_per_second": {"type": "number"},
+                "explicit_cache_read_input_token_cost": {"type": "number"},
+                "input_cost_per_token_above_272k_tokens_decisions": {"type": "number"},
+                "input_cost_per_token_above_272k_tokens_ultrafast": {"type": "number"},
+                "input_cost_per_token_balanced": {"type": "number"},
+                "input_cost_per_token_decisions": {"type": "number"},
+                "input_cost_per_token_ultrafast": {"type": "number"},
+                "output_cost_per_image_token_batches": {"type": "number"},
+                "output_cost_per_token_above_272k_tokens_decisions": {"type": "number"},
+                "output_cost_per_token_above_272k_tokens_ultrafast": {"type": "number"},
+                "output_cost_per_token_balanced": {"type": "number"},
+                "output_cost_per_token_decisions": {"type": "number"},
+                "output_cost_per_token_ultrafast": {"type": "number"},
+                "supports_bedrock_converse_tool_result_images": {"type": "boolean"},
+                "supports_bedrock_native_structured_output": {"type": "boolean"},
+                "supports_bedrock_runtime_chat_completions_inline_reasoning": {"type": "boolean"},
+                "supports_box_questions": {"type": "boolean"},
+                "supports_bedrock_runtime_chat_completions_tools_with_reasoning": {"type": "boolean"},
+                "supports_bedrock_runtime_chat_completions_response_format": {"type": "boolean"},
+                "supports_regex_lookaround": {"type": "boolean"},
                 "cache_creation_input_audio_token_cost": {"type": "number"},
                 "cache_creation_input_token_cost": {"type": "number"},
                 "cache_creation_input_token_cost_above_1hr": {"type": "number"},
                 "cache_creation_input_token_cost_above_32k_tokens": {"type": "number"},
+                "cache_creation_input_token_cost_above_100k_tokens": {"type": "number"},
+                "cache_creation_input_token_cost_above_100k_tokens_batches": {"type": "number"},
                 "cache_creation_input_token_cost_above_128k_tokens": {"type": "number"},
                 "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"},
                 "cache_creation_input_token_cost_above_256k_tokens": {"type": "number"},
@@ -773,6 +804,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_creation_input_token_cost_priority": {"type": "number"},
                 "cache_read_input_token_cost": {"type": "number"},
                 "cache_read_input_token_cost_above_32k_tokens": {"type": "number"},
+                "cache_read_input_token_cost_above_100k_tokens": {"type": "number"},
+                "cache_read_input_token_cost_above_100k_tokens_batches": {"type": "number"},
                 "cache_read_input_token_cost_above_128k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_above_200k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_above_256k_tokens": {"type": "number"},
@@ -781,6 +814,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_read_input_token_cost_above_512k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_batches": {"type": "number"},
                 "cache_read_input_token_cost_above_272k_tokens_batches": {"type": "number"},
+                "cache_creation_input_token_cost_above_1hr_above_100k_tokens": {"type": "number"},
                 "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {"type": "number"},
                 "cache_read_input_audio_token_cost": {"type": "number"},
                 "cache_read_input_image_token_cost": {"type": "number"},
@@ -797,6 +831,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "input_cost_per_image_above_128k_tokens": {"type": "number"},
                 "input_cost_per_video_token": {"type": "number"},
                 "input_cost_per_token_above_32k_tokens": {"type": "number"},
+                "input_cost_per_token_above_100k_tokens": {"type": "number"},
+                "input_cost_per_token_above_100k_tokens_batches": {"type": "number"},
                 "input_cost_per_token_above_200k_tokens": {"type": "number"},
                 "input_cost_per_token_above_256k_tokens": {"type": "number"},
                 "input_cost_per_token_above_272k_tokens": {"type": "number"},
@@ -826,6 +862,10 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "input_cost_per_request": {"type": "number"},
                 "input_cost_per_second": {"type": "number"},
                 "input_cost_per_token": {"type": "number"},
+                "cache_read_input_token_cost_above_200k_tokens_batches": {"type": "number"},
+                "input_cost_per_token_above_200k_tokens_batches": {"type": "number"},
+                "output_cost_per_token_above_200k_tokens_batches": {"type": "number"},
+                "input_cost_per_text_message": {"type": "number"},
                 "input_cost_per_token_above_128k_tokens": {"type": "number"},
                 "input_cost_per_audio_token_batches": {"type": "number"},
                 "input_cost_per_image_token_batches": {"type": "number"},
@@ -861,6 +901,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                         "image_edit",
                         "embedding",
                         "evaluation",
+                        "extraction",
                         "guardrail",
                         "image_generation",
                         "video_generation",
@@ -896,6 +937,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "output_cost_per_second_4k": {"type": "number"},
                 "output_cost_per_token": {"type": "number"},
                 "output_cost_per_token_above_32k_tokens": {"type": "number"},
+                "output_cost_per_token_above_100k_tokens": {"type": "number"},
+                "output_cost_per_token_above_100k_tokens_batches": {"type": "number"},
                 "output_cost_per_token_above_128k_tokens": {"type": "number"},
                 "output_cost_per_token_above_200k_tokens": {"type": "number"},
                 "output_cost_per_token_above_256k_tokens": {"type": "number"},
@@ -4204,7 +4247,11 @@ async def test_builtin_string_callback_registers_when_subclass_already_active(
     assert any(type(cb) is S3Logger for cb in litellm._async_success_callback)
 
 
-def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypatch):
+@pytest.mark.parametrize("rate", (0.0, 0.000123))
+@pytest.mark.parametrize("updated_rate", (None, 0.0, 0.000456))
+def test_reapply_runtime_registrations_replays_register_model_overrides(
+    monkeypatch: pytest.MonkeyPatch, rate: float, updated_rate: float | None
+) -> None:
     """
     register_model is the documented way to override pricing for a model. A
     price-data reload swaps litellm.model_cost for a freshly fetched catalog,
@@ -4235,11 +4282,17 @@ def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypa
                 "openai/gpt-4o": {
                     "litellm_provider": "openai",
                     "mode": "chat",
-                    "input_cost_per_token": 0.000123,
+                    "input_cost_per_token": rate,
                 }
             }
         )
 
+        litellm.register_model({"openai/gpt-4o": {"supports_function_calling": True, "input_cost_per_token": None}})
+        litellm.register_model(
+            {"openai/gpt-4o": {"input_cost_per_token": str(updated_rate) if updated_rate is not None else None}}
+        )
+        litellm.register_model({"openai/gpt-4o": {"supports_function_calling": False}})
+
         litellm.model_cost = {
             "openai/gpt-4o": {
                 "litellm_provider": "openai",
@@ -4251,7 +4304,9 @@ def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypa
         _invalidate_model_cost_lowercase_map()
         reapply_runtime_model_cost_registrations()
 
-        assert litellm.model_cost["openai/gpt-4o"]["input_cost_per_token"] == 0.000123
+        expected_rate: Final = rate if updated_rate is None else updated_rate
+        assert litellm.model_cost["openai/gpt-4o"]["input_cost_per_token"] == expected_rate
+        assert litellm.model_cost["openai/gpt-4o"]["supports_function_calling"] is False
         assert litellm.model_cost["openai/gpt-4o"]["max_input_tokens"] == 4242
     finally:
         litellm.model_cost = saved_model_cost
@@ -6371,6 +6426,36 @@ def test_function_setup_never_logs_the_ocr_data_uri_payload() -> None:
     assert payload not in str(logged)
 
 
+@pytest.mark.parametrize(
+    "key", ("openai.test-converse", "bedrock/openai.test-converse", "bedrock/converse/openai.test-converse")
+)
+def test_runtime_model_cost_registrations_resolve_bedrock_routing(monkeypatch: pytest.MonkeyPatch, key: str) -> None:
+    from litellm import utils as model_utils
+
+    rates: Final = {"input_cost_per_token": 0.001, "output_cost_per_token": 0.002}
+    monkeypatch.setattr(
+        litellm, "model_cost", {**litellm.model_cost, key: {"litellm_provider": "bedrock_converse", "mode": "chat"}}
+    )
+    monkeypatch.setattr(model_utils, "_runtime_registered_fields", {})
+    litellm.register_model({key: rates}, persist_across_reloads=False)
+
+    registrations: Final = dict(
+        model_utils.runtime_model_cost_registrations("bedrock/converse/openai.test-converse", "bedrock")
+    )
+    assert registrations[key] == rates
+    assert model_utils.runtime_model_cost_registrations("bedrock/converse/openai.other-converse", "bedrock") == ()
+
+
+def test_registered_fields_reset_when_model_cost_is_replaced(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(litellm, "model_cost", {})
+    litellm.register_model({"registered-fields-probe": {"input_cost_per_token": 1e-06, "litellm_provider": "openai"}})
+    assert "registered-fields-probe" in litellm.utils._registered_fields_for_current_map()
+
+    monkeypatch.setattr(litellm, "model_cost", {})
+
+    assert litellm.utils._registered_fields_for_current_map() == {}
+
+
 def test_get_optional_params_keeps_a_tool_config_cache_point_out_of_the_openai_extra_body():
     """LIT-9880: the hook hands a tool_config point on for the provider step, and OpenAI has no
     step that consumes it, so it must not ride along in extra_body and 400 at OpenAI."""
diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index a91ec268faa..bcd00757227 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -32623,8 +32623,14 @@ export interface components {
             cache_creation_input_audio_token_cost?: number | null;
             /** Cache Creation Input Token Cost */
             cache_creation_input_token_cost?: number | null;
+            /** Cache Creation Input Token Cost Above 100K Tokens */
+            cache_creation_input_token_cost_above_100k_tokens?: number | null;
+            /** Cache Creation Input Token Cost Above 100K Tokens Batches */
+            cache_creation_input_token_cost_above_100k_tokens_batches?: number | null;
             /** Cache Creation Input Token Cost Above 1Hr */
             cache_creation_input_token_cost_above_1hr?: number | null;
+            /** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */
+            cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 200K Tokens */
             cache_creation_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 200K Tokens Batches */
@@ -32651,6 +32657,10 @@ export interface components {
             cache_read_input_image_token_cost?: number | null;
             /** Cache Read Input Token Cost */
             cache_read_input_token_cost?: number | null;
+            /** Cache Read Input Token Cost Above 100K Tokens */
+            cache_read_input_token_cost_above_100k_tokens?: number | null;
+            /** Cache Read Input Token Cost Above 100K Tokens Batches */
+            cache_read_input_token_cost_above_100k_tokens_batches?: number | null;
             /** Cache Read Input Token Cost Above 200K Tokens */
             cache_read_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Read Input Token Cost Above 200K Tokens Priority */
@@ -32727,6 +32737,10 @@ export interface components {
             input_cost_per_second?: number | null;
             /** Input Cost Per Token */
             input_cost_per_token?: number | null;
+            /** Input Cost Per Token Above 100K Tokens */
+            input_cost_per_token_above_100k_tokens?: number | null;
+            /** Input Cost Per Token Above 100K Tokens Batches */
+            input_cost_per_token_above_100k_tokens_batches?: number | null;
             /** Input Cost Per Token Above 128K Tokens */
             input_cost_per_token_above_128k_tokens?: number | null;
             /** Input Cost Per Token Above 200K Tokens */
@@ -32850,6 +32864,10 @@ export interface components {
             output_cost_per_second_768p?: number | null;
             /** Output Cost Per Token */
             output_cost_per_token?: number | null;
+            /** Output Cost Per Token Above 100K Tokens */
+            output_cost_per_token_above_100k_tokens?: number | null;
+            /** Output Cost Per Token Above 100K Tokens Batches */
+            output_cost_per_token_above_100k_tokens_batches?: number | null;
             /** Output Cost Per Token Above 128K Tokens */
             output_cost_per_token_above_128k_tokens?: number | null;
             /** Output Cost Per Token Above 200K Tokens */
@@ -46229,8 +46247,14 @@ export interface components {
             cache_creation_input_audio_token_cost?: number | null;
             /** Cache Creation Input Token Cost */
             cache_creation_input_token_cost?: number | null;
+            /** Cache Creation Input Token Cost Above 100K Tokens */
+            cache_creation_input_token_cost_above_100k_tokens?: number | null;
+            /** Cache Creation Input Token Cost Above 100K Tokens Batches */
+            cache_creation_input_token_cost_above_100k_tokens_batches?: number | null;
             /** Cache Creation Input Token Cost Above 1Hr */
             cache_creation_input_token_cost_above_1hr?: number | null;
+            /** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */
+            cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 200K Tokens */
             cache_creation_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 200K Tokens Batches */
@@ -46257,6 +46281,10 @@ export interface components {
             cache_read_input_image_token_cost?: number | null;
             /** Cache Read Input Token Cost */
             cache_read_input_token_cost?: number | null;
+            /** Cache Read Input Token Cost Above 100K Tokens */
+            cache_read_input_token_cost_above_100k_tokens?: number | null;
+            /** Cache Read Input Token Cost Above 100K Tokens Batches */
+            cache_read_input_token_cost_above_100k_tokens_batches?: number | null;
             /** Cache Read Input Token Cost Above 200K Tokens */
             cache_read_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Read Input Token Cost Above 200K Tokens Priority */
@@ -46333,6 +46361,10 @@ export interface components {
             input_cost_per_second?: number | null;
             /** Input Cost Per Token */
             input_cost_per_token?: number | null;
+            /** Input Cost Per Token Above 100K Tokens */
+            input_cost_per_token_above_100k_tokens?: number | null;
+            /** Input Cost Per Token Above 100K Tokens Batches */
+            input_cost_per_token_above_100k_tokens_batches?: number | null;
             /** Input Cost Per Token Above 128K Tokens */
             input_cost_per_token_above_128k_tokens?: number | null;
             /** Input Cost Per Token Above 200K Tokens */
@@ -46456,6 +46488,10 @@ export interface components {
             output_cost_per_second_768p?: number | null;
             /** Output Cost Per Token */
             output_cost_per_token?: number | null;
+            /** Output Cost Per Token Above 100K Tokens */
+            output_cost_per_token_above_100k_tokens?: number | null;
+            /** Output Cost Per Token Above 100K Tokens Batches */
+            output_cost_per_token_above_100k_tokens_batches?: number | null;
             /** Output Cost Per Token Above 128K Tokens */
             output_cost_per_token_above_128k_tokens?: number | null;
             /** Output Cost Per Token Above 200K Tokens */
diff --git a/uv.lock b/uv.lock
index 36eaf65c521..0714560846e 100644
--- a/uv.lock
+++ b/uv.lock
@@ -10,7 +10,7 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-10-17T18:08:05.560666223Z"
+exclude-newer = "2026-10-18T00:08:44.741377Z"
 exclude-newer-span = "P3D"
 
 [manifest]
@@ -85,7 +85,7 @@ wheels = [
 
 [[package]]
 name = "aiohttp"
-version = "3.14.4"
+version = "3.14.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohappyeyeballs" },
@@ -98,127 +98,127 @@ dependencies = [
     { name = "typing-extensions", marker = "python_full_version < '3.13'" },
     { name = "yarl" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/93/2f/6a91adaa2dc26877d6ed2f54c0370c8910f019db7d77c5c6a194611e93ea/aiohttp-3.14.4.tar.gz", hash = "sha256:831fc5bd39ec2517851e348f613ddb5447a47cf4b71cb09845af7ad7ed45d8f9", size = 8077839, upload-time = "2026-10-05T17:43:48.309Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/4c/bdccd81e9ee225b69c60e7766c9a5b05364f118f4d383713b89a682d772d/aiohttp-3.14.5.tar.gz", hash = "sha256:5558a7f5a05af9ecf744af91e5baefc436f93c9333e656c27ec253f9a6bbe178", size = 8078052, upload-time = "2026-10-11T01:05:12.408Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b3/08/290e4be6e3ed239751c446505c324406a4ae8a82a15009a12a3c550f18d9/aiohttp-3.14.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dea3b3653c1d0d6babd8ce09cb9e5a7776864315d9cfb1c569f926389874a261", size = 834853, upload-time = "2026-10-05T17:37:45.079Z" },
-    { url = "https://files.pythonhosted.org/packages/81/81/ed5e04508ba1fcf9a34e0449c78009956e8256f62ebef708e2948594cf94/aiohttp-3.14.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3099a389e5b5900fc79c6f613015ff3f8fa06a519744e6001cc68a31ba418cac", size = 560957, upload-time = "2026-10-05T17:37:47.497Z" },
-    { url = "https://files.pythonhosted.org/packages/90/28/1a91411c53704db0481cc64b0f0c9465aa9d738856abdcaa3a5bbbe18180/aiohttp-3.14.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70247156fc76e92919f9aacb820556cb30289a54784299a31714d030bb604d84", size = 553475, upload-time = "2026-10-05T17:37:49.099Z" },
-    { url = "https://files.pythonhosted.org/packages/cf/2e/1038f3fa8832f9f4bed0f9f751f70dbc52bc4a09c66788f97bbfb0ce3d88/aiohttp-3.14.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fdf2d2a6ad402797422949f4a200a60d43e3a021695c8a7804aa1d5bbef22652", size = 1845211, upload-time = "2026-10-05T17:37:50.728Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/54/e2253f17604c5c1c69a05e3c12400b51cd6a5fb32d7175592114d8c7a470/aiohttp-3.14.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:ba835fad8d4b5eaea0d34f9461cf499737a720a5f8bc6768d2f6d98a1d3ba8b5", size = 1814629, upload-time = "2026-10-05T17:37:52.481Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/ef/7bd1e45db925376720555d7268c2d642b113105263d37a522e41e1ba3a6c/aiohttp-3.14.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d4415ca5c9c8b24bc2f5733f870d4eab4929e680203559ba60131dd1a27852a", size = 1898528, upload-time = "2026-10-05T17:37:54.078Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/40/26d09668e7e0cadc16027566765aa4ce26e8a41276bad6764848c8b04d11/aiohttp-3.14.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6757e02c2c2b0d7985f57be87cf4a7c5b35708f849e1feaea3f77656ddb9dff", size = 2024385, upload-time = "2026-10-05T17:37:55.626Z" },
-    { url = "https://files.pythonhosted.org/packages/73/38/0f1c4aab1cc9518e1bf874e2481e59e541b3e32330b9542e52bb2712f86f/aiohttp-3.14.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a950bd8418ef54eccf5f9f517f08e37c1adab4bc50a470a0422ee1cc1032e29", size = 1859130, upload-time = "2026-10-05T17:37:57.342Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/98/09d5998ba4b5fe9f0cb97d794fab9d1b3d8245c5ec6a5fb84e41a8cec142/aiohttp-3.14.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34cf6f2fe4fc1d7183e8cc0d8c48bbdda828a740bc372d8278126149714d343c", size = 1714768, upload-time = "2026-10-05T17:37:58.831Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/63/39d01a74d525d6443084d47ad4aa8c719f44a030149d03566f3761527465/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bc0fbe4f79c3b156d754dd062718ffe404c3b31ca878d9d2b88ecdbc72ef8369", size = 1813228, upload-time = "2026-10-05T17:38:00.611Z" },
-    { url = "https://files.pythonhosted.org/packages/39/6b/183d7b969bdb7892e86af74147b4afedbb4e03b8cad5006e41aa2034c288/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d3d50a5a07a2b31a4369b86dd4a3acf3c2577c45091dbd5e884b198dec56480b", size = 1831844, upload-time = "2026-10-05T17:38:02.272Z" },
-    { url = "https://files.pythonhosted.org/packages/2c/be/4c6df02b62083efd3f008974cf9016a4afd2023f5a9d2c3fd55499fcbac6/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:de15c46a63f46da881d219e44a04778c40114c756e5575b5ea38143b20eb3713", size = 1868738, upload-time = "2026-10-05T17:38:03.831Z" },
-    { url = "https://files.pythonhosted.org/packages/86/21/406be8b0cf1105a35a6a6da16a95796be39b354e29bfca0d1626d822835f/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:caa4c0fc9b25e8c679baac68337e9c00deb6baf6601fe6f07e8511469cc1ceba", size = 1700006, upload-time = "2026-10-05T17:38:05.631Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/e6/beac98020ea0885ea1ee3b2ef59ec952405590fe2ccef2fa4ef7614c3c2b/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3647f8c090632c70abb1e80826e4ee24faea3f895f0283b60e91a0b17aea5e34", size = 1889997, upload-time = "2026-10-05T17:38:07.578Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/89/d608dd9571988a529c7fead5bc79ad36b56fd52bad7941f40774acbc87e9/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3f3e8030169843fb652a60a3d32c206e03f260198aa398985a48b41cd7e42f0a", size = 1844619, upload-time = "2026-10-05T17:38:10.003Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/7d/7f51e6338d2c74b75173ee66fcb50d778d5407c32f34e76ef1c4b25d0d75/aiohttp-3.14.4-cp310-cp310-win32.whl", hash = "sha256:a1205cbdddfca1428129bb6d23e0b292b09e681df951fa828145d83a63ffc0ca", size = 489598, upload-time = "2026-10-05T17:38:11.795Z" },
-    { url = "https://files.pythonhosted.org/packages/33/2a/3434e450a4395fc07f3070d6ac24553f0b170b173e949216b1723395028c/aiohttp-3.14.4-cp310-cp310-win_amd64.whl", hash = "sha256:e90980e0454a043f81b435309a089ac5deab883779557eb58d004f33990f61e4", size = 512204, upload-time = "2026-10-05T17:38:13.309Z" },
-    { url = "https://files.pythonhosted.org/packages/53/c0/1d89303cf1bea5418268c1cb82b872661bad027e5fd785c2d30d0a31ee6f/aiohttp-3.14.4-cp310-cp310-win_arm64.whl", hash = "sha256:e63eecf9a4b670a24055d5c0486128af16f83b02d9817abd685d3238940f8752", size = 492725, upload-time = "2026-10-05T17:38:14.825Z" },
-    { url = "https://files.pythonhosted.org/packages/81/e3/998dc75634ecd2a24f33bab480b57313059d55bcadff8825a46b7c80a8af/aiohttp-3.14.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb0093ca0817019d539f0d27bdf98e823944e05bb7efd9d2337a45b92e4d1b06", size = 832892, upload-time = "2026-10-05T17:38:16.373Z" },
-    { url = "https://files.pythonhosted.org/packages/58/c9/9bacc26397854440d169f70ae00ea51721f504611d3a64cf043643792c32/aiohttp-3.14.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f482dc9c8309801b4259dd218609d3dae0a7bcdedeac56d90500eabaa0c23465", size = 559893, upload-time = "2026-10-05T17:38:18.74Z" },
-    { url = "https://files.pythonhosted.org/packages/fa/f3/90c5856014328a8b1e9a753de794edea282182b776ff65f0602ad4ffa520/aiohttp-3.14.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aa800bb7c1d00e166493931f2ddacb982db913292503dc2f4884db1f2bc5f105", size = 552850, upload-time = "2026-10-05T17:38:20.385Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/88/e71c29ce6daa78fcee0feb1992f0fdc408f09f42c3311b1f1c68c36f16ea/aiohttp-3.14.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d90e4dae71b26597f6d1fd12af7d092ae67551edf0e524b73e0687214b79ee33", size = 1928941, upload-time = "2026-10-05T17:38:22.218Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/4f/f0f3bebfa521a2ce5fd4302c937701cbc50cd6d908beaa597388639b0b98/aiohttp-3.14.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5b681054b8c3b86aa6a0384b6ad7f5cb78dccbabab1f4a3a6793f98ad1378959", size = 1882092, upload-time = "2026-10-05T17:38:24.016Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/0d/5df041fd25dceb4f4cafbbee49bb2c1e2d54a91aedecaf03b77cbb404c44/aiohttp-3.14.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dfe80b41bcf8d80d2125fb99a171adeb86db2fcb35c1a68e0226acba0ba7f03", size = 1986051, upload-time = "2026-10-05T17:38:26.022Z" },
-    { url = "https://files.pythonhosted.org/packages/1a/07/e95eddafffef7c3a74446f67ac4e477a49cec2c78f2ab6c86d1acfd90d2d/aiohttp-3.14.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:71e4a59c6a8c5a6ae8b0b696c32635913e8f526cc01448762eaf5a3c59df8a4f", size = 2107840, upload-time = "2026-10-05T17:38:28.112Z" },
-    { url = "https://files.pythonhosted.org/packages/da/6c/1f83990fea249dcb10f48086726953546efc9199c96b6be7114532ac361f/aiohttp-3.14.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f887c3b7fb3058fc1ccd917f52078540c18d938d12018cb9edd64b6811d20c57", size = 1930721, upload-time = "2026-10-05T17:38:30.046Z" },
-    { url = "https://files.pythonhosted.org/packages/6f/d1/48184a186ea26df4f81dd466144dcab7f9cdd1e131bfee0f0e41278c6f0d/aiohttp-3.14.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0da4525e9ba145a11617d2cd7e44fe1acaf471f9c72a0cad28e72879c1020fbb", size = 1774508, upload-time = "2026-10-05T17:38:31.8Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/ef/a9ec758c6d3850453838c31b56d1e4499eb47c80883753a12dcb203f9afa/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f7e8d3c5caa44fdbee3eba1aa1417aa58c74c95d4089fe3c451911117fcbb2f3", size = 1902311, upload-time = "2026-10-05T17:38:33.791Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/49/9a2be54900f2dea6e63bbf9628fced604686a2e301130ccde0b1aa2e7e53/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:09092cf906c18c824b6b16881da5a89cc9cfa9b15344e496bcf880e9045bee33", size = 1912107, upload-time = "2026-10-05T17:38:35.614Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/2b/151254abfc0fe5cbb8e6c41ad04d52122db0af176fb31dbf3bc44e081bda/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:dfd144837e92264878bba6d3a7ffa8206668b21e87748740afd45d193e48c87e", size = 1960207, upload-time = "2026-10-05T17:38:37.322Z" },
-    { url = "https://files.pythonhosted.org/packages/23/99/92c8dce336ac5784755a3144623528516f2e3b6b4871d02cad5a0642ae66/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:9413cffe4e0d654b9b524f9c99dde8cbdb37e0ed9a2c4edd2e63adbac6b374e8", size = 1760168, upload-time = "2026-10-05T17:38:39.214Z" },
-    { url = "https://files.pythonhosted.org/packages/66/3e/f05fd8d1a9595730db8d522882eea76429b9be2ed5337609f7c6e3d9d49c/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f50d719f97ba488dfb8e306cf8c8cc172ff0683ec0af53917b288229aa555ba5", size = 1979946, upload-time = "2026-10-05T17:38:40.927Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/14/8941aa73ffceabc2a0eb26878b4f1b2958fb7b5358f97cc49b1c00ed9258/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:68ed4824d96b7afec1f3a8d7fba190fe282718041c5772e20298003e1e3e5d66", size = 1923375, upload-time = "2026-10-05T17:38:43.184Z" },
-    { url = "https://files.pythonhosted.org/packages/18/b5/ef275b63c8bfe0a21e7e8d3ef0e67c4745ed403f1894fe5205057cedd3b9/aiohttp-3.14.4-cp311-cp311-win32.whl", hash = "sha256:d7a41d1427136828e6b11d3f3fd194d4357d5205a5b610be7ae07b1ba52ab974", size = 488414, upload-time = "2026-10-05T17:38:44.978Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/0b/21bdd70a1e072222d9dbd96bed4fbed26f7c46c5a20af11b78d32fd049d6/aiohttp-3.14.4-cp311-cp311-win_amd64.whl", hash = "sha256:2efbdb87e79d596325c4eefaef0f4495d701145e882351310ebc538e854dc7a3", size = 512755, upload-time = "2026-10-05T17:38:47.036Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/4c/bb324a7d20a9598187bb028ca8d6bcf66c63589c8632420919dd576964ed/aiohttp-3.14.4-cp311-cp311-win_arm64.whl", hash = "sha256:ac6e6f90d9360e460c873f945f11dc8698db0a71fec6612823f1aaaab2c11faa", size = 492960, upload-time = "2026-10-05T17:38:49.006Z" },
-    { url = "https://files.pythonhosted.org/packages/22/02/db5935d45347fa8ede56b777930740fb0e72bbb4473ddb6ff8541f6f2afa/aiohttp-3.14.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:55b0b335982b0db7117dff7f6a8e3aad43c4105f9e392ca04f9fc8d958a95cce", size = 817689, upload-time = "2026-10-05T17:38:50.69Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/56/f00aa46127e6342f019d567853eeeb932e04fb9b9424b5fb981ad68f4178/aiohttp-3.14.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2d0d8e435582b0d53009dac99e26a3d2be932ed7c9dbfcfc70f3fce1cf943bd5", size = 549599, upload-time = "2026-10-05T17:38:52.525Z" },
-    { url = "https://files.pythonhosted.org/packages/3f/bc/825c09b09962253a2103e4a88c04374ee939c0c8ea31c270daa0308efb07/aiohttp-3.14.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bf734016932d68e1324cfb638cac7a0866a83933a33badf15e836a7e24efb8c0", size = 548132, upload-time = "2026-10-05T17:38:54.629Z" },
-    { url = "https://files.pythonhosted.org/packages/40/80/8a1bc8036540fe7cb38219cc5c0aa67d32e9068165725e8199ea8200b08b/aiohttp-3.14.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:322e3d741b3133bcbb981a41d4f9b8ac3545c18de49c662c2b1f4e1c770b98ad", size = 1898485, upload-time = "2026-10-05T17:38:56.439Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/fe/65b464d8520ace0d65b4ca69bc9abe175f842c8ce8d1522d363d9669903f/aiohttp-3.14.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:15a3bb5f90a4e515071f3617a45dfe26560beb834a6b6e108cdf4bc9e9719ec3", size = 1875334, upload-time = "2026-10-05T17:38:58.536Z" },
-    { url = "https://files.pythonhosted.org/packages/be/51/9c583be502720e927560a8414f4dfb7c7de41945e1a30ccf7003b93c6f85/aiohttp-3.14.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6c044e52df1a466af82cad3518c92ea80cc4ddcfea86966ff083bb34bab29bf4", size = 1937772, upload-time = "2026-10-05T17:39:00.376Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/3d/b56512df7ea9cbb5f59099a6b375088dd578356a5a3fb27198ab82e19832/aiohttp-3.14.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d613d7d51bf06fe9a5e3aab86ce06d835bb0ceb1a31ea9e8766df4a403ae62a6", size = 2066220, upload-time = "2026-10-05T17:39:02.54Z" },
-    { url = "https://files.pythonhosted.org/packages/11/6c/a7a42701d9ea319140a3d44a24ec72a00b0b46d1b899b26d8a705e65bdd8/aiohttp-3.14.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5e93ab6e6330dce40f5b43996f1fc5f2543296d263a5e4b59ff09e73870b7d8", size = 1922895, upload-time = "2026-10-05T17:39:04.638Z" },
-    { url = "https://files.pythonhosted.org/packages/77/04/f8337bd824ca3fe3968d34dc5037ace1c4872551c4621f8266239311d301/aiohttp-3.14.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:20134dc8e68c67e7478124d516449428684c0545b2d3faa575691c8bcbd56678", size = 1712589, upload-time = "2026-10-05T17:39:06.671Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/a6/d20e2c940b592d7c4a21690889dbff64fe0ca3facd9190696368694e1488/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f0daef5ef012369dddc391c61f604111424aa9a96313a69fb899018b09d1b01e", size = 1862251, upload-time = "2026-10-05T17:39:08.523Z" },
-    { url = "https://files.pythonhosted.org/packages/f5/e4/d50edd5ae5d024b380a8e892e333840bb22967a9eb9c8492108a403f678a/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:19290a108de0718b73bc69b86e788975c6a59855c671ebe2a98a07a6f968328f", size = 1895155, upload-time = "2026-10-05T17:39:10.305Z" },
-    { url = "https://files.pythonhosted.org/packages/c3/d3/f36f2931f807ccf8437ec15e8f8bfaa4748d4792639401cc767a866abaa0/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1494877625baeffab669f4a25a09ec4eea721b49e35363081a2a8e4231fe141f", size = 1906623, upload-time = "2026-10-05T17:39:12.411Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/0a/94821b711493142bf5e11c27b0d7502776778f7792c77ecc6647357d20c1/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a779ce4bf099ce4ad2cdfed62f1ca536d435f53237c54ff40172fddada24d1b5", size = 1698932, upload-time = "2026-10-05T17:39:14.446Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/76/3d5a0d28362f0053c1c457024749911932481e8fd105fddf8305b1f93c81/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0b4cec9fca876e2d4f4c6cb32b177390132d04618867689f43fefabf3f5c3980", size = 1934528, upload-time = "2026-10-05T17:39:16.354Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/51/9784a21dc05d2e0f6acaf864f16db53dab0fbd7b0753cef168601eacb012/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:217707313e23aedde9bea67cf8365c7b138b549ae179121ef3f476cf67e3173a", size = 1901984, upload-time = "2026-10-05T17:39:18.299Z" },
-    { url = "https://files.pythonhosted.org/packages/44/4f/f98c88703e6d620243aa08473a946ca4e3756b6288690e38f0d9f9c1d007/aiohttp-3.14.4-cp312-cp312-win32.whl", hash = "sha256:18a9fb9a3f6e6e63f4d27f9adeef313a2d3c69a84d31170a844623824e722534", size = 480278, upload-time = "2026-10-05T17:39:20.206Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/bc/8555013f84b53e4fdde423131b641af50e822c6d7d9118b24c52b31f6900/aiohttp-3.14.4-cp312-cp312-win_amd64.whl", hash = "sha256:69dcb02d33dfe415d5ee342cc63b7d320efcaf4b761701c7bd7bfb91c715481a", size = 506317, upload-time = "2026-10-05T17:39:22.706Z" },
-    { url = "https://files.pythonhosted.org/packages/21/3f/ca5bad7bfdaa7ddca053a044a1c7c0d4f3ad9d1f12f96dcab10bfb9c50e7/aiohttp-3.14.4-cp312-cp312-win_arm64.whl", hash = "sha256:d36b0263e7c2fbf1750b9f35d4e7e48b0442d8c45e4a89e3e74168821fb014bb", size = 487683, upload-time = "2026-10-05T17:39:24.482Z" },
-    { url = "https://files.pythonhosted.org/packages/23/ec/7fee140da700ec3f5aa5e0fd2319f67be5e86de197e2384d27e5e6209e0e/aiohttp-3.14.4-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:264b5a7568306590c44ae4a0237ad1715e35d447ea44ebf324e4c8fd9f78f67a", size = 539114, upload-time = "2026-10-05T17:39:26.322Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/04/930c01ce9e186e787046433d7dc5b45b188885f8406c14b58435b4431974/aiohttp-3.14.4-cp313-cp313-android_24_x86_64.whl", hash = "sha256:17e5d7c7775d8dd8e894c7ef6ebfa26509de36868a9a6c7c4fcfaf6a1bf43d60", size = 553514, upload-time = "2026-10-05T17:39:28.104Z" },
-    { url = "https://files.pythonhosted.org/packages/2c/d7/983e3cea81c07e95f35d34da4d1e182b5c05489c49b7560b198a83f0da79/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:e91dc8fe9cbd052d16f7f1267e285cf8bbac4d2194bd5741f05ef201c77ed09e", size = 521381, upload-time = "2026-10-05T17:39:30.419Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/2d/80baed11659093883f51245755105557d3253e45bd0b693d70df0059d68b/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:8df6157d31703972aec9e3b93963f039ff06318301e30b007c3e941ff8a7ac42", size = 528347, upload-time = "2026-10-05T17:39:32.344Z" },
-    { url = "https://files.pythonhosted.org/packages/c8/18/bfda255c311096c08dab26dc65f3d219f090df37dc5f5f6345f8c3aefc1f/aiohttp-3.14.4-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:220912b351549dc736c59d104dc443fa615753102bb778a4e98f86e4d94bff6a", size = 539914, upload-time = "2026-10-05T17:39:34.265Z" },
-    { url = "https://files.pythonhosted.org/packages/51/fc/3b6ca6117c0c42481d719411fff7b5d3970ebd906543d3dc1ba40fe2462f/aiohttp-3.14.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2efa42b39bb3f524d5eca3760639b584afdd1143a6b047fda29910ffb75e4993", size = 813997, upload-time = "2026-10-05T17:39:36.061Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/f6/86e3e02a9712aadc1ae0a1076bb2d1adf3d9addfe5542a28190c8f9b6d9b/aiohttp-3.14.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7e7356059c8262d2c1fd95242e2b7b70fbc6eee3135bf470049cbec3e968b5b0", size = 548058, upload-time = "2026-10-05T17:39:38.109Z" },
-    { url = "https://files.pythonhosted.org/packages/85/7e/6b9c2e271419d40ca76589613b3c7ab185fd3050a407bd2565b6aa46f695/aiohttp-3.14.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fac247d0cc956d732df1211ac2d8a9999ec8dc1a92a90401de9d52e4ead546f7", size = 545933, upload-time = "2026-10-05T17:39:40.193Z" },
-    { url = "https://files.pythonhosted.org/packages/14/fc/33d6e24a5f8ac32423230088c415e2a1c6efee23d902b62f20506631e40b/aiohttp-3.14.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2eb0f8b03b4f2bd154ed8cf7c1a119a1ad04808c258bf58f90138c83b8c6d5", size = 1888265, upload-time = "2026-10-05T17:39:42.182Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/e8/2eca1d468d83a514621d1280f9992d08649191db2028c9236b4edfa7c723/aiohttp-3.14.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7fbe827d27e0e369fd7bb88ceeaa5b46ea006e73e015b9dd77e3723a53162293", size = 1872300, upload-time = "2026-10-05T17:39:44.195Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/f6/5872983de71b0214acdfb86822f5cca295b39be4832ec589fa224aee0f6c/aiohttp-3.14.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a70387146d03af9f047c629b71aa27d9594b3b31ec4c9c91e1a73d0d8bf38e0e", size = 1926213, upload-time = "2026-10-05T17:39:46.199Z" },
-    { url = "https://files.pythonhosted.org/packages/ee/65/ebfefa11a546c33c717af63c67868408ecf0b33b23a9d75669af95485407/aiohttp-3.14.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d0934926fc65744e2fdd44ce68b2d79d5ee608a1e23f0596b35dd696519bb7c", size = 2056609, upload-time = "2026-10-05T17:39:48.221Z" },
-    { url = "https://files.pythonhosted.org/packages/69/c0/70667e82ec041f4122a17afce711bbcf94a71bec5888b69a49aed8817be2/aiohttp-3.14.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ff4b366510c733974adb7a4102c094e4a6308e6f369315a4cf14d2d0a619cf82", size = 1914740, upload-time = "2026-10-05T17:39:50.304Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/86/559e9dfea676206b20737d7ccb5b3716bff5e58d2a8d53682e5301724cd1/aiohttp-3.14.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:85fac7c99e0ac3dcbd6ae1c33774e0603bfc732ddb967a6fce4a731103c1888e", size = 1703390, upload-time = "2026-10-05T17:39:52.385Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/91/c98897d4cf23e120b2f3980042835cb34c86bbe3c653f3eaacf4bf986349/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef1e9c3b4a2300023a5dc865889ce532cfaf6798ba4ef78fbbefe738a9d23efa", size = 1852642, upload-time = "2026-10-05T17:39:54.391Z" },
-    { url = "https://files.pythonhosted.org/packages/14/13/0258f352cb2c236f358a5b57d138e15fa2566e17accc0758d968dbf2ceb6/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:97e65916588be0f952b3307aaa8460c0771fa98dbea2dd27dabc9f5d84d53c3b", size = 1890616, upload-time = "2026-10-05T17:39:56.466Z" },
-    { url = "https://files.pythonhosted.org/packages/64/3c/f43e294ce1a06d1234a97bd862c1aa31acfa1a0eea3786c22fd0dc1ea731/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:840775cb39a9424f9edf142133a1192263ac5bd79117ad2a16602cef6a0c1e9d", size = 1896638, upload-time = "2026-10-05T17:39:58.585Z" },
-    { url = "https://files.pythonhosted.org/packages/9f/f7/ce1e3a85b73d05037d729d3d32da7d6959b9e433435e9abd46c2fb38410f/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:54f9256430ca040d58affbd551513de13a5cff7d065204fc52b9a1b0af09a049", size = 1693003, upload-time = "2026-10-05T17:40:00.698Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/72/45eb900d6a9ee046728f5589f3d07f5d78f049b5fb84f48881fa4174d5df/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:6112d5931bf12c776188cab81b82bbb17d86e2e1381f2ade6edc43e6b240f0cb", size = 1927730, upload-time = "2026-10-05T17:40:02.943Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/43/a83ff79dc8375953a1f00b808a21c82590f4e68304fecccdcc42a25fb7d8/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:facc6df39047c4732cbd885bb62e40df20885fcd709fc399e11f81b45ce0fff9", size = 1891177, upload-time = "2026-10-05T17:40:04.989Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/ba/fbdc41608d4e2fb6084d960a41b392fa82beb5b126c2466de549b5c67fc8/aiohttp-3.14.4-cp313-cp313-win32.whl", hash = "sha256:7968634fa3a967a2bc0b9aeba1d5a1955501dcd7d0de44b96f7ebfb662797735", size = 479943, upload-time = "2026-10-05T17:40:07.402Z" },
-    { url = "https://files.pythonhosted.org/packages/35/51/d75629750e705832fd5cd52516a82943ed58b6e09c30e14830f5d87452fa/aiohttp-3.14.4-cp313-cp313-win_amd64.whl", hash = "sha256:c0a894b0265d139cd4c2c8bd4643822cc289a4a5331e21e810881bd000ffb2dc", size = 506209, upload-time = "2026-10-05T17:40:09.49Z" },
-    { url = "https://files.pythonhosted.org/packages/02/64/66452d2ffcc13e5e5ee4ba4a968656fa4a98c29ed5ff0205d4fde02b2943/aiohttp-3.14.4-cp313-cp313-win_arm64.whl", hash = "sha256:da16c3037178e72589d91de59536d271dffc92c2be2b47c38a45538cba54fd29", size = 487163, upload-time = "2026-10-05T17:40:11.526Z" },
-    { url = "https://files.pythonhosted.org/packages/d2/fd/b653b1f969e2e949fe4726af7a8043e8ef117f202bed7757ac8564e077a1/aiohttp-3.14.4-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:749bfc43bb1df71bbe6ed215044d5412d786698fc5771d2037436ca49622f3c9", size = 540738, upload-time = "2026-10-05T17:40:14.109Z" },
-    { url = "https://files.pythonhosted.org/packages/90/b5/eea49a0bb697deffac5165d707ec53a24748d6720b3af77a544107b49573/aiohttp-3.14.4-cp314-cp314-android_24_x86_64.whl", hash = "sha256:c113e4b489d711f606ca278cd8dc89179746244ea841aa0638b1b134600afad0", size = 554494, upload-time = "2026-10-05T17:40:16.231Z" },
-    { url = "https://files.pythonhosted.org/packages/11/ea/cf8f4efbbfa8572d9965cd43b3c6c84c581aa006772e5ce3ab4020027e9b/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:50969522bc7022026a2c7968e67da5c789f6b716b988edac55dc630390efd5df", size = 522653, upload-time = "2026-10-05T17:40:18.879Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/24/9f6721f0b52323789cb1041ffc3afa729462d9925607e733a065b6fc5e17/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:cbf92cd7a1c800cee244558dd5630abb45c1c1093ef7b0d546a99f526ff7a9eb", size = 529697, upload-time = "2026-10-05T17:40:21.296Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/a4/399debc3c2ca0ab88a08e3082b4c4f62d0f66978af60243c63f2345ef337/aiohttp-3.14.4-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fc76be08ff407fba717a769aff04ca1b4bf9ecfdcb5caadef84a563fdbbd146d", size = 540526, upload-time = "2026-10-05T17:40:23.548Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/97/90379813b18b795bccdeb3a5a85e9b93ac2c69f9c2a5d0faba59da3ad6d1/aiohttp-3.14.4-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9b416f995b68a921069e6ec61fa07f2ac3ff033d92e97a69f673af89f5bb954d", size = 818866, upload-time = "2026-10-05T17:40:25.842Z" },
-    { url = "https://files.pythonhosted.org/packages/78/70/824fd0dac819652f1df895b3f621a75bf0a3050c30e38d8d2316e34ab821/aiohttp-3.14.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2c9585101cfca10e74a07cc0ef2bdc6d90616e6750926b20456f429d0608f740", size = 549666, upload-time = "2026-10-05T17:40:28.523Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/45/eafb2dd200dd2b770ed25a2dc5731c4ba5d58ab3fa8e2e82494bb946808e/aiohttp-3.14.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3c4dcf611b095e7983421f49d01ffbed7ed574891533d606ea115fc23e7c4e90", size = 548961, upload-time = "2026-10-05T17:40:30.613Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/bc/6c733a1c71300293471ac7ef1dffd12b5b4dc9a43c53461224b2b8a7f667/aiohttp-3.14.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f8f61a9b5fa56c58e3441f9dc64137f786232d40fb89127190d0e0f84e1e5865", size = 1883165, upload-time = "2026-10-05T17:40:33.062Z" },
-    { url = "https://files.pythonhosted.org/packages/37/34/885ddbd351679a31141b25e0d1a5e4f67738806e564c858b399709b61239/aiohttp-3.14.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d43e538dfc85b705fd832620d050970ef5613b3869a7169b44a554b9dab9eee9", size = 1844119, upload-time = "2026-10-05T17:40:35.266Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/ef/0a64dac53c11d569851efb3e7eddb43551df72b2c172ebb34cccc93bcd3f/aiohttp-3.14.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4135c4bb4b7682a7633fadc7170ea969d843f83aa7224e70111a20675105c985", size = 1930222, upload-time = "2026-10-05T17:40:37.527Z" },
-    { url = "https://files.pythonhosted.org/packages/69/5f/774792ed8f973e0d234fcb06b0f0bc9f29e9a0a0dd847f6418c2904be7d9/aiohttp-3.14.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:9055324f156a94fdf6dc9a825ae60f9a2947b88f591ea81ee80826633de62ae7", size = 2038842, upload-time = "2026-10-05T17:40:39.815Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/05/e00f35581c97656d9e864edaa03292382c620dd1d9c836a4f73a2279acc4/aiohttp-3.14.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb22c8e4b60385a9b414c70c6e8b2d0f4b23ff7fc4bb572ceb58297b228169f1", size = 1887845, upload-time = "2026-10-05T17:40:42.359Z" },
-    { url = "https://files.pythonhosted.org/packages/ca/2e/07e3eff5b4c1b082a2eaf0ffb508b409b21ea1ddc9fdc57f3eabb51469a1/aiohttp-3.14.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3b6945559a260112742ed58cde2165488d2fc51aeea34afbaa99d9371b43e1b5", size = 1702533, upload-time = "2026-10-05T17:40:44.569Z" },
-    { url = "https://files.pythonhosted.org/packages/75/44/816844b7f876e6f8fee4ecb088269fcd92241da712e4814a4d624eda13a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f4078a90b174f15efb2c8725e8720c40dbd3b2cf6350dbc085c964a938d9de7", size = 1849058, upload-time = "2026-10-05T17:40:47.818Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/bd/163242e12464a1f3e58a77e28beca949652ddce84abdd5500a91c70a1e0d/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f433c5654e32f72de3ef074d715eb5c7604eb6d28a5c2f3c9e5056f20fe6b306", size = 1854600, upload-time = "2026-10-05T17:40:50.401Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/59/5c1ae708a89524eddfd9c727b87cae26b5c50c3c76683b910ac06151ead0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:871035fe79c636b6bc126ed78df37d72b830dfc751612cb4b1040360edf2719f", size = 1896565, upload-time = "2026-10-05T17:40:52.625Z" },
-    { url = "https://files.pythonhosted.org/packages/37/45/95300a7de69241fe47d3f838f3fb582c712782e172d447ff650a013ea673/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2617132524f66338f6c1d218cd16081576aefc40df4f2bcba338a99fbf67fec1", size = 1693092, upload-time = "2026-10-05T17:40:54.862Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/33/01a8e61d48d0094121092c74125df14c0f8f10ee3149bfe68b6f869409a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:d8bc326133272deee8ef337581550450e4bb735c0520be893b950a1f5baaf41a", size = 1917073, upload-time = "2026-10-05T17:40:57.656Z" },
-    { url = "https://files.pythonhosted.org/packages/9e/d6/1a4f24624cda6686d5b927e26d5d1ae3ebb692faf88e93017fab4b391fd0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3ec57223e261b7fa9979c12dbce009ca53439be76cac3af27f860d3e4b1d6f7a", size = 1872656, upload-time = "2026-10-05T17:41:00.123Z" },
-    { url = "https://files.pythonhosted.org/packages/be/be/ed286fcfa2d22061ae021b568c790123505cd482df35e23023339ecaed96/aiohttp-3.14.4-cp314-cp314-win32.whl", hash = "sha256:7242043e71fc449a19a47d92f4e9fd1e0ae8d3f88488982381f422bf6d651218", size = 485461, upload-time = "2026-10-05T17:41:02.686Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/74/e040e6f65f4da305777f1adb3023d47401693489e4a337c983b52d2a0a6b/aiohttp-3.14.4-cp314-cp314-win_amd64.whl", hash = "sha256:019587c7b3a44917dd61bcb312fd5c034f341dc9851b83e7b41b65e08b68ca0f", size = 512147, upload-time = "2026-10-05T17:41:04.98Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/5e/bddb33ae15fdd5a68a10a986587aa9916c418a712fdd110d3b3ae9b51407/aiohttp-3.14.4-cp314-cp314-win_arm64.whl", hash = "sha256:60dc71d38db0988f37e78f6ad4a010a2f6355cfac3fff5f130cf5ef2231f3f0d", size = 494685, upload-time = "2026-10-05T17:41:07.366Z" },
-    { url = "https://files.pythonhosted.org/packages/22/2e/7b884014b40573f919fc3a528e5028bc37b249e31a93928ba61bdd25c960/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:674f53ab9d2794e2dd767619a3384bf1006f8d075e43c19d449a645f8ff641c2", size = 855696, upload-time = "2026-10-05T17:41:09.514Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/e6/b6e2b4f580ab6ae39241bb9182aca60e6e1915cdad0148faaa04db3f366b/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:6d243221f73e5ac546c2ed9255100423e4bc092b08b944f23498e8cf3096c26c", size = 567931, upload-time = "2026-10-05T17:41:11.685Z" },
-    { url = "https://files.pythonhosted.org/packages/63/99/ae8e3a1a18adcbf636839d18b3cccc51007836ccdae5209381c5cf82d1ae/aiohttp-3.14.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0daa016eb74e7888ed5f9ceec6eea3158999c1c4a115ef5cbe88baa8d924f94c", size = 567421, upload-time = "2026-10-05T17:41:13.836Z" },
-    { url = "https://files.pythonhosted.org/packages/63/38/c5d4bb58be72b967a4090d2deeb38571f8c992852936c51dbbbeae49db1c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70c031a622aa20add05ebd234b90adaf6bf51c1c88cc305ec760721af83308c3", size = 2054173, upload-time = "2026-10-05T17:41:16.098Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/87/3c8a9c7670f56d478a75c5bb84b336fb61a67b908e36c30a4a96ed8c8e86/aiohttp-3.14.4-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7df363fa7c38945a896e12c69af4a1a56cbd4152791d9e41fd0bac396b72de38", size = 1918296, upload-time = "2026-10-05T17:41:18.478Z" },
-    { url = "https://files.pythonhosted.org/packages/49/97/bd00e499c0a1505b44f5e23b9739034ea9be792ad42537f2894211ba1c07/aiohttp-3.14.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:02a508ba5ad91c4d730523584c0adc65882274bba5e37c33bc2f475e37577256", size = 2027513, upload-time = "2026-10-05T17:41:20.874Z" },
-    { url = "https://files.pythonhosted.org/packages/23/1d/a3666a7c224f86a881f18d673a8ffdc92fa4c35274fb4361822f8f0dc566/aiohttp-3.14.4-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0cb3edece6fe6a944eaf97d803b88f606da6bc1600b1894c2969e78ffdc1fc29", size = 2152686, upload-time = "2026-10-05T17:41:23.181Z" },
-    { url = "https://files.pythonhosted.org/packages/46/7e/f4204b8c4959c46f6367c182afbbacef08a1b53874281912c52fbd80151c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21ce1223b461bcc5fb389a7204001578f1c0b85c2da60a84d915ebb021294245", size = 2006431, upload-time = "2026-10-05T17:41:25.776Z" },
-    { url = "https://files.pythonhosted.org/packages/33/43/091e69d42967cbea833ceb355c5457f8f70748fe08b88c9d91491b3fafb8/aiohttp-3.14.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35d5432f0dc1c8b71307e9112461b52f336da225e344283eec4779222c0a1dff", size = 1789101, upload-time = "2026-10-05T17:41:28.095Z" },
-    { url = "https://files.pythonhosted.org/packages/47/7b/b57cbe533c01098c5d30471f057e7c3c19f281122f756acc9c716b636e2c/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6ec364493057c118d08292f7cd60865965c209167d8657b45643a26aef77495", size = 1974472, upload-time = "2026-10-05T17:41:30.499Z" },
-    { url = "https://files.pythonhosted.org/packages/9f/44/79acce03611450e4ed8594f96f1cea40d70bc84fb4e918f94d7d9454a4af/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:70492983b7aed9e61bda82fe1ce80bcba9199610886443133783a288638923c0", size = 1956340, upload-time = "2026-10-05T17:41:33.009Z" },
-    { url = "https://files.pythonhosted.org/packages/da/bb/36e6cbd6720e3377a02f8709aec6fe80de729ef41e78ba01f13d50363c73/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a77776673331577147e9d25cd7833a72e8891b47556336cff06ba1569e488b99", size = 1965771, upload-time = "2026-10-05T17:41:35.506Z" },
-    { url = "https://files.pythonhosted.org/packages/69/0f/879735ac70ce5e6852916eed51c706a517b205150a8d384f9fa60933a3fc/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:73799000dd6fd5247094fd8e6d3e1eb871e41aab5cc35dff9d9f654cd230bc24", size = 1780297, upload-time = "2026-10-05T17:41:38.284Z" },
-    { url = "https://files.pythonhosted.org/packages/01/5d/7c030ca5b6baf3b02eccd11afc3d58f0b35e407031d5cc78cae9c24921c0/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:27b370fb532e707e8c96d04fa0c96301fb7dba2d50aaca57f6c456cdfffec5bd", size = 2001374, upload-time = "2026-10-05T17:41:40.888Z" },
-    { url = "https://files.pythonhosted.org/packages/80/1e/ddacbb8141d727034c51dd192d17749521d5b30b03f84aa034325396089e/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:884e0d1c707b6217fee3080b9b4029eee7551af788ee761010df19be158414b7", size = 1968531, upload-time = "2026-10-05T17:41:43.62Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/08/2214f823701eebc3e57db141faeae76df7bfd415f254cc7c1692258f228d/aiohttp-3.14.4-cp314-cp314t-win32.whl", hash = "sha256:f2e3d34edb151d3e27f93a8338e2da33e2c7261cd4c879ce5f5fe280cc190ea5", size = 504126, upload-time = "2026-10-05T17:41:46.321Z" },
-    { url = "https://files.pythonhosted.org/packages/91/a1/90e9b6fd23310b4e82d0c0a37b5ecc2944053350473c57533c1da9647235/aiohttp-3.14.4-cp314-cp314t-win_amd64.whl", hash = "sha256:88cf889e51092537fe44adfbff96c2a22d6479d6f92b97b3d413fbfd0a4decf4", size = 531494, upload-time = "2026-10-05T17:41:48.849Z" },
-    { url = "https://files.pythonhosted.org/packages/97/ab/5b501472c92b9b1dc53742591d6210dccb262962f4721299300d3a9f664b/aiohttp-3.14.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ca450c6d42fda7c0bfaf0e200f32f77c5f2c960a33be1e14d197c84588b7f5f6", size = 510544, upload-time = "2026-10-05T17:41:51.358Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/27/5e1f8446545be98e9416af59c396b1ed1f9f3294afb0a40ee3a709889273/aiohttp-3.14.4-py3-none-any.whl", hash = "sha256:5c6758ba62aea282c537179cfc8474a90f2b5f7b089cc5ff66d8920d86a9bfdd", size = 279487, upload-time = "2026-10-05T17:43:44.905Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/82/f7f0652e3a845e095d8505a2807a0fe5782abb71f99b2f516c93ff0be492/aiohttp-3.14.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ef692a24087a699c0a4a26af45e746e0c1eae2116f6d8a5ff91d8aae2b867b45", size = 834351, upload-time = "2026-10-11T00:59:07.668Z" },
+    { url = "https://files.pythonhosted.org/packages/95/c5/10cb0a5195bc3ec05a74ee494f8431a15e559800f2e869f3526ad4a16f04/aiohttp-3.14.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1220353657ad49493551f089ce02f1a348fd57ffd585bfec77f2f3c4fe3a7346", size = 560663, upload-time = "2026-10-11T00:59:09.853Z" },
+    { url = "https://files.pythonhosted.org/packages/32/dc/b7fefdd7dd64d080da2d69d609344191cc94b0e2eba70200c371014c9b36/aiohttp-3.14.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:330900acd0dc4cb8b27f9c127fbaad770964845338493e7906ae3822e82dbf8d", size = 553263, upload-time = "2026-10-11T00:59:11.5Z" },
+    { url = "https://files.pythonhosted.org/packages/61/5f/3271cad1b34347e8bf27abee20d501ebdc56cec97e8ae59cd3fabb23d917/aiohttp-3.14.5-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0684952aeae1f5dbfe02d46039338513b94009baecd15d8e4098a357c4c4a2a6", size = 1843813, upload-time = "2026-10-11T00:59:13.143Z" },
+    { url = "https://files.pythonhosted.org/packages/67/af/2011b30fe61889af112ad380e6fd44a93cca4b51296f612cac666c177882/aiohttp-3.14.5-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d94e44be379e569758fee8a9a58431cfc3c2598c708b92b1cfe96c66b4c94aef", size = 1811243, upload-time = "2026-10-11T00:59:15.091Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/ba/72f3ac523ed48d38cdfb169f1b2a2e93ce06d9fcf4f46d0f5692e9539bcc/aiohttp-3.14.5-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:5af42135fdfebdadbc2bcd9c0842a48ccf0d62794c36a260b21dc4b94d1e0119", size = 1898815, upload-time = "2026-10-11T00:59:17.224Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/69/bbf24f3b555ea1befa7db1e2510c728c8b0e80e61ce360beb7d94bc562b7/aiohttp-3.14.5-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4f07fe3ac408d8b3f768be471dc3f56d43843c47d97c66120534467a15ead197", size = 2022390, upload-time = "2026-10-11T00:59:19.244Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/38/01f5fc732d5373d6c099db0343279cd4e6607287d336bab6ff6ae9085a0d/aiohttp-3.14.5-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f375db73a39f5cf83696d500e21a67f418dc9a988955756f254be8f03b7b3651", size = 1856329, upload-time = "2026-10-11T00:59:21.19Z" },
+    { url = "https://files.pythonhosted.org/packages/15/85/1f86fbd8fe34ad447c63e679404a1d5be435fe256a9d281b791fc1ed0d35/aiohttp-3.14.5-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:8df7d481654ac96fe1ba9a02a9f67770fdd367823e0d5ef01b922725c4bd2cfa", size = 1712763, upload-time = "2026-10-11T00:59:22.982Z" },
+    { url = "https://files.pythonhosted.org/packages/39/1e/ced51cf47e427e7aa6142c3bf6f33022472703bc9061289329532d3c40c0/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:e95c8def4b81c5d68d5cf1f54c07acd7c0d2577af244e5b6da802120825737c6", size = 1812125, upload-time = "2026-10-11T00:59:25.032Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/f1/9610b4e263b554ca4191501ba72b952efe06556b647da74887abc5d41049/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f2ebb54b3f932210503072f09974b4fb574d823e497a944adfdcd140a6a00255", size = 1829550, upload-time = "2026-10-11T00:59:27.078Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/8a/1d1fb27cf9fa99b13133de33044c4d10d7705be0d4173d6d56abad1b67f9/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:038c2c7e8caa26b6c8423779b5eaf1893904048a512c19b32fe841ffa5592b50", size = 1868179, upload-time = "2026-10-11T00:59:29.315Z" },
+    { url = "https://files.pythonhosted.org/packages/24/9f/3cfafa86ff025623dcca0d30335db7b8a6f3fa348148441208147e827e04/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:b7806e804889231b0e06469fd4a5c06313d1c0a3377322b6d9237fa5e0fe4167", size = 1697721, upload-time = "2026-10-11T00:59:31.161Z" },
+    { url = "https://files.pythonhosted.org/packages/62/1d/86439a23bf32296e715d8c75535f0cd701821d36719324baef65bcd6af9e/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:9bab2045550c4fe0f7baf89574db1b455c195750702ba96fef1f16972b146617", size = 1887000, upload-time = "2026-10-11T00:59:33.329Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/0f/6044f2d02b3874966d84cd119f9b8eda46aa2991230078aea4dd17750cc9/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:96a2e584f0b9ed8f1fa33211397dcf67bb7069866402cb405d191c2f0defb9a3", size = 1842020, upload-time = "2026-10-11T00:59:35.384Z" },
+    { url = "https://files.pythonhosted.org/packages/18/64/b49d2a34428ff937631b07dde74d5879a7a2c8559aab39331d40769e8cb6/aiohttp-3.14.5-cp310-cp310-win32.whl", hash = "sha256:602c1e9b718a3275c580149f947e7fac65044c0a20e599553fb12e9700da9eca", size = 489282, upload-time = "2026-10-11T00:59:37.061Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/7c/1114e723f1c4a65597820b605a0ddcd7f3b28fdfde3ac8d520d517ca582c/aiohttp-3.14.5-cp310-cp310-win_amd64.whl", hash = "sha256:bea559ad70218d230663e4210875735076a9bfea5994cef34a55a25faeaf2544", size = 512021, upload-time = "2026-10-11T00:59:38.7Z" },
+    { url = "https://files.pythonhosted.org/packages/48/97/e08c646f4bad63d77876b24591d013d7f33f02fda7c931eafe3224f38467/aiohttp-3.14.5-cp310-cp310-win_arm64.whl", hash = "sha256:dca3fa8d8a0a26679862eccb0b1a9151b2b9f1cd2c212e7a6335778faaff5833", size = 493016, upload-time = "2026-10-11T00:59:40.525Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/f3/8997f18890a92c79f77fcfbb4f78ca17c2d4ab109e9eb6d31b4e9de194a0/aiohttp-3.14.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:d51db97c96384fbfcaf8f4c65922183a68b94f891c3c10c862ef5f6df2adbb1f", size = 832358, upload-time = "2026-10-11T00:59:42.195Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/42/084651e9efb5cadb99265f786df60f2a7b353cead7bfd2c87003cb4867ad/aiohttp-3.14.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ae53924aa853a7a2ca20ed4142c7c6b56338e4d4cd999e2980075b9efc2e257a", size = 559636, upload-time = "2026-10-11T00:59:43.677Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/fe/92838944e601f0fe195fd3f3ada37e29fbee3d19bfd323fe15937ec79d36/aiohttp-3.14.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a2c473a355f9239efcb72c92d5abfd8fcdb0cc78c8e9af607e72ca12dbb36593", size = 552588, upload-time = "2026-10-11T00:59:45.592Z" },
+    { url = "https://files.pythonhosted.org/packages/8f/b8/dd9b95c5c20ceae1b47738e656bd79e9883e3117a9cc8b143901eb604e9a/aiohttp-3.14.5-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:32e8fa6644e541fcd7e02430588c7fc93b602c1778ea0bc345505db76b61cfb4", size = 1928224, upload-time = "2026-10-11T00:59:47.294Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/47/70010cd2ba8746968d53d433ff328c33f06a66c99da5f3de759c64a6b2eb/aiohttp-3.14.5-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:579f97d5120f2971876d2ddca2968135f6944d00c44c3a6590ad7d86ca9b403f", size = 1877674, upload-time = "2026-10-11T00:59:49.472Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/a1/b026f071dbd87f0bdba86b92d47e46f3899e3ad7143b6e0fe7e7887090b4/aiohttp-3.14.5-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:24409db442e2fb6e766bc7f3943851a8381dec3098140e43bb2e843b79e31b12", size = 1985850, upload-time = "2026-10-11T00:59:51.296Z" },
+    { url = "https://files.pythonhosted.org/packages/36/d1/f7b6f6f8c3cb5a71b53baeddc2e70c224c28b12a23a55c42994c504019b7/aiohttp-3.14.5-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5e8f97c0488ffda3082766ac0f2c8150a9a58c4d05788330e479cfd449b37939", size = 2105471, upload-time = "2026-10-11T00:59:53.191Z" },
+    { url = "https://files.pythonhosted.org/packages/42/74/2a2b22953de15c6c8a80debf26db3047e4e8a5a5db6dd7c2c6c01eec0605/aiohttp-3.14.5-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:50a195903119008fe9cc68710535eb37f556ffffd6a7759afe70a2c145587045", size = 1929915, upload-time = "2026-10-11T00:59:55.609Z" },
+    { url = "https://files.pythonhosted.org/packages/33/ad/f80e8d33933d0eacd0217efa3b7fb32c9f48ed480ed0db53cf9948bf474f/aiohttp-3.14.5-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0133c3c3b54a0bf1e71fa5c1ad95c93f07fd54e24ef1fe182f5122e1573d2bf1", size = 1773832, upload-time = "2026-10-11T00:59:57.611Z" },
+    { url = "https://files.pythonhosted.org/packages/04/a4/0273d239f3e3bb69438f209c64c82e1f98dc60d5db264795e41f7dd05dcb/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c172db893e516e1358e65a95ee20b7ce7173963eefe318b6ab2a2220688b999e", size = 1901001, upload-time = "2026-10-11T01:00:00.605Z" },
+    { url = "https://files.pythonhosted.org/packages/16/ed/7dd439d26c654645bc34ca3c9a822fc11c1c51801fed1cefdfe1cc41c1f6/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:f2a7966bda23dd85051f1661ce0ace38d6890e05ec6c357ecae9d2479cba377e", size = 1907218, upload-time = "2026-10-11T01:00:02.699Z" },
+    { url = "https://files.pythonhosted.org/packages/32/dd/86249c3b8248562a17fd3e22ee0c164378d65766f01aceef62cf52783710/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:4887d130a7bbfed3a85493bb5a25e5b5b558d40c1d986dd16970d2bb26d63793", size = 1958650, upload-time = "2026-10-11T01:00:04.851Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/0b/ca4d53d68f683ce195807fd0aeb063bf6d1c6b39343fff234c9524e8d5a9/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:225c579c23b68b343cccea27a7e06e3bd8ec23a09c30b427eb3f1e4ca6239b20", size = 1760057, upload-time = "2026-10-11T01:00:06.978Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/42/005437ffd7fa56c2ce3347add40404b654a32754ce91f2e2a14b9e5ab2bc/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ab52d8f1fc1b64821c1fbad64a647ed6203627004059a6d1ed4f0858a1499703", size = 1978081, upload-time = "2026-10-11T01:00:08.868Z" },
+    { url = "https://files.pythonhosted.org/packages/03/71/3a5b66fe1b7b23d3c6524350817ed55de5feb7fbb4cccba7cbe044d118dd/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:cb131d775a1573c1aee66656bd78b023577bbdb6cb8349a07773bd4f73e68a6e", size = 1922954, upload-time = "2026-10-11T01:00:11.035Z" },
+    { url = "https://files.pythonhosted.org/packages/69/84/d08a554f281d42fd7c6b2b6dd7738f3e3a7a9f657ddd87e11ca2091cdfe3/aiohttp-3.14.5-cp311-cp311-win32.whl", hash = "sha256:e87046c8ff77a8decdb6a41d8ab25824b47531b2da933aeab0c1e21c7acff329", size = 488101, upload-time = "2026-10-11T01:00:12.933Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/15/52b5e65f02b33686ae49f1518548ae4f5a7adaf31d9d3c54fa12a143137b/aiohttp-3.14.5-cp311-cp311-win_amd64.whl", hash = "sha256:6f275c11d1aa6d4c458e05a68be084efe3c55a113d99e3f46a318098e52948fc", size = 512575, upload-time = "2026-10-11T01:00:14.743Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/b9/bb75012635f3defb0f7cbb7c4ae391e36bb9cb3fbdca3b9944e2ebebf743/aiohttp-3.14.5-cp311-cp311-win_arm64.whl", hash = "sha256:b032a0023eb41d768ce77d83210ab2a3c389bc0b09313273c7e1eca48c10a755", size = 493179, upload-time = "2026-10-11T01:00:16.961Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/94/6ba86efddcb616c811b40e6a0dfdd862738f647e4e3860a961075d5e9ed8/aiohttp-3.14.5-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:df37b620684e19b5e25724412518ccafc3b1a49cdac706fdbd2f983fad943450", size = 817499, upload-time = "2026-10-11T01:00:18.901Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/e1/7bca6d84dabd228aa8eb4b7f9feac2586aaa9be5505d7d65bf287a615c43/aiohttp-3.14.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ef60869969180ec2464f1349aff07138ae35ca2200f0946cb3552e49e8f301a8", size = 549467, upload-time = "2026-10-11T01:00:20.854Z" },
+    { url = "https://files.pythonhosted.org/packages/64/91/11b89f45ca486252dd67dd5f3231fec04bf5518da39a95cb3997619f17fb/aiohttp-3.14.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d079c0a0135c36e7beb6f1c88087c8f108dc5891cdd0b5eafa778421bda70ed2", size = 548067, upload-time = "2026-10-11T01:00:22.659Z" },
+    { url = "https://files.pythonhosted.org/packages/22/ff/c6615806c14aab34f82b9424ccde8ce6e417315fd57ce1c5b4d4747888e1/aiohttp-3.14.5-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:abfda5cb094a829f7bc25216a32f7db2e85cc65bd59910f8e7b40b3d9b224764", size = 1896245, upload-time = "2026-10-11T01:00:24.638Z" },
+    { url = "https://files.pythonhosted.org/packages/39/b2/25a8c971ae6a92c8394d77e42422d7f38989e05cf41a5ceb92d73d67ab7e/aiohttp-3.14.5-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:9cc882cf8619109583c906b4d4a85d6a111a98afa34b7a450d1e08118d016820", size = 1872180, upload-time = "2026-10-11T01:00:26.838Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/d5/99f93ea36cc5205e47c1e5a803e087f2ad21b5430b5db2e942cb6e988a37/aiohttp-3.14.5-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7457580535e019e1247ea35d6a02bf081ad30c26d0cbc210c93f6c3ab67a0835", size = 1937261, upload-time = "2026-10-11T01:00:28.74Z" },
+    { url = "https://files.pythonhosted.org/packages/40/a6/9ac9c9e6695040bd73d2584a1b59a9388f6433c76d5294a7bf591e21ffe5/aiohttp-3.14.5-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:c5ed596aedb9c42afd3fe0aae3117725378ac73d2cc5ddc735056fbdb96c5d02", size = 2064994, upload-time = "2026-10-11T01:00:30.623Z" },
+    { url = "https://files.pythonhosted.org/packages/da/e4/aa172eb534b7f02f1f8ff1c3213347eaf3cf218db91a727c6863c22f1035/aiohttp-3.14.5-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:20f085697d7e911f1f73c43ed03fafbed1e7121797e2eb5428efa80398060584", size = 1919630, upload-time = "2026-10-11T01:00:32.548Z" },
+    { url = "https://files.pythonhosted.org/packages/06/7d/4eedafc5bababa8932636c141e346806966eade12c0b7e5946d43bf8218b/aiohttp-3.14.5-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:74b0a9c8270f9b0a11410e124ff8d4f18bfc1f1837440ec84da5ae7b50927b5d", size = 1710016, upload-time = "2026-10-11T01:00:34.471Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/94/eee018537ba19da0ceb2ac79cab83faed4ac49568e08376e2799043f2538/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:19e2ba471507c34f8252402ab50f5ab512398b9ea8c8f1cb26beb3f75793ba30", size = 1858112, upload-time = "2026-10-11T01:00:36.581Z" },
+    { url = "https://files.pythonhosted.org/packages/68/76/354653a306547238f3427283905972d796ba7c292ba9977abec9f2b6f260/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:d418ce2af40c6bb685b3f663e9e8de27cb0a22431d8e88a167348d7f01878073", size = 1896371, upload-time = "2026-10-11T01:00:38.478Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/ec/63e8c7136b570e356345ad3174e3820fdc973ea10712cb6c649bf875755a/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:70cb4008ac2ed1e0ca9e824deb4b53d3aa0d939109698ebf1e723a84337bd794", size = 1905836, upload-time = "2026-10-11T01:00:40.527Z" },
+    { url = "https://files.pythonhosted.org/packages/57/d8/11365bda144b127928cd42533d0eff78a55613c9e28f81941bd6630ea887/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a23fe35d776bc03cb495938b9594450d047e3bc08c5255315a82323e9cb7d2dd", size = 1696534, upload-time = "2026-10-11T01:00:42.686Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/3d/82df0461b18e00b2998f205c03e0d3010222478c43640aceb8e03dcd7e8f/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3e0eb43bed3c6801a6cee315195377789e90b2a72c2277a475b578535312488d", size = 1933970, upload-time = "2026-10-11T01:00:44.71Z" },
+    { url = "https://files.pythonhosted.org/packages/03/ad/6ddfe0aacd931c17b53533336d97e9d11a98b96d6ae815a9da0b19f82ccf/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be7dd397d64ca3e1869626fa9318aaebb54b7bf93bc72d7a205448d83e4f748", size = 1899501, upload-time = "2026-10-11T01:00:46.629Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/8e/189bdd9ae4793059bb09f6dc880f211a6c6c7859cebcbf33912dbfab7dd7/aiohttp-3.14.5-cp312-cp312-win32.whl", hash = "sha256:eb324e2009fb54db30a071dad7caf6998ee2879c4704007efb244514dad1fec1", size = 480370, upload-time = "2026-10-11T01:00:48.468Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/ce/1f08114679d49655b30a6e0a29858375c94b82c1de1a0bd0a20c2fee8b02/aiohttp-3.14.5-cp312-cp312-win_amd64.whl", hash = "sha256:2cc38a4f2b516bef1714e690df87a0e043faf1a7693c82d860091684453d5111", size = 506141, upload-time = "2026-10-11T01:00:50.272Z" },
+    { url = "https://files.pythonhosted.org/packages/79/d4/c7b4f60b16a1b7e43249fa9031ae05e7e8c341ba4b7d1866f914dafeaa0e/aiohttp-3.14.5-cp312-cp312-win_arm64.whl", hash = "sha256:a63afd1f757de949028387e65a7127b61ad0f775432dbb0e62816ae619fe69ac", size = 488108, upload-time = "2026-10-11T01:00:52.321Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/e1/2841e020ebb7aefae5513586193e011e06313d9a6bdbd296622afbbce204/aiohttp-3.14.5-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:9ad7e6aa38c20da1be697874349c4c273c8a03b7887169665081706398d0439a", size = 538932, upload-time = "2026-10-11T01:00:54.3Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/a6/7fb8ea8fe96bcc7b7c7a36d10f021d99d01a8dc8a4b3f0ddacecfad9a80e/aiohttp-3.14.5-cp313-cp313-android_24_x86_64.whl", hash = "sha256:f59c7673465908cbe506117176156c127f29f917677afceada34957179221d91", size = 553329, upload-time = "2026-10-11T01:00:56.442Z" },
+    { url = "https://files.pythonhosted.org/packages/de/64/d056e3c27647dc25af1a592cf356245382ea7c808171b9dac7677afedfc8/aiohttp-3.14.5-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:1b5416552740edf07234cc9437d0706f2acb67b93c198670b1a68e1b2b587dec", size = 521367, upload-time = "2026-10-11T01:00:58.345Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/e4/95226147e11d4db916fd1d495dcf85af8e3816e38333e42718241196e848/aiohttp-3.14.5-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:43351bdb5e4c3cb7d1772368e988534e869a74db7778079a83782c11c69535c7", size = 528322, upload-time = "2026-10-11T01:01:00.211Z" },
+    { url = "https://files.pythonhosted.org/packages/17/cd/1d3c9192cafdb51cad62b2d3ded96cff9cc8af51893210aadd448a325389/aiohttp-3.14.5-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:c8c4478bef6d57fcfda15dae461ea3c9f06aa7b257c58df3f2300174ccbb185a", size = 539874, upload-time = "2026-10-11T01:01:02.06Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/0c/dfa33aecc7d4d1dc75e05248f5eac5a0edf4d09e7b44d93ab62529b0c1db/aiohttp-3.14.5-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c2c30484dd1417ef98b51021ffa2cc0d7f3c78918adaaaab7e70817335ab3e02", size = 813836, upload-time = "2026-10-11T01:01:04.01Z" },
+    { url = "https://files.pythonhosted.org/packages/33/17/4a63738052d20567d55529d6daa1b9480d906fd52930fbcf6d3fbed618f0/aiohttp-3.14.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dab9ac5a67c8d1f070c00fa8fccb7cbd1b8dcc1a8d6b42f37540df9b3d4cc603", size = 548070, upload-time = "2026-10-11T01:01:06.035Z" },
+    { url = "https://files.pythonhosted.org/packages/15/e5/b57e58695a757fd4c02497c033fced96a69c631b13866c43d336530c9670/aiohttp-3.14.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e1cc2bfaee8c214f06080a7c7d5772419b8a1108e8e5349236189811823fb02a", size = 545786, upload-time = "2026-10-11T01:01:07.817Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/68/8c2c67a3aedf46e00f3c42f04fbc6983de80d4ed5786151e33681ba45883/aiohttp-3.14.5-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74efb69332b85675b1eabd760a8cfc2e2cf42c60607c66f88014c1bdfb40942d", size = 1886492, upload-time = "2026-10-11T01:01:09.834Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/4b/74aab5e8d28c62e8f795b4fe8f38cf5586fd264a9a27bd2141ef6490333d/aiohttp-3.14.5-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:42b5e616946dbaf505e2bff18c9af2cd4ef9e7ef300ee58a6e951a5b7cf147ae", size = 1870057, upload-time = "2026-10-11T01:01:12.045Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/f7/eafc3b1988302b1815d9fd4a21071be5c360d616c0a430d02fd92dc97688/aiohttp-3.14.5-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f9033b43f511f27547c557dcaba0177649e10a3725336ccd2cce0fdc1dc4850d", size = 1925119, upload-time = "2026-10-11T01:01:14.09Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/04/78d8f294f74dd570f3898ff20402349fce524176045df98ba727d6846a68/aiohttp-3.14.5-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:15a310d3c71398e3d7bfc93a1a73fbe664315cd9e9016b8efc1cff85eeab7155", size = 2053137, upload-time = "2026-10-11T01:01:16.344Z" },
+    { url = "https://files.pythonhosted.org/packages/32/51/395d225ef36f5a50d8e548dcd3141bfdbcd31fb6eed859022c573d2c4d66/aiohttp-3.14.5-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1ffa3a523a36d8628f98c06492ae16a31a23d14c0b4ec721757b477319f656d6", size = 1911038, upload-time = "2026-10-11T01:01:18.653Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/a4/2aec1aa06d82e8a244843b5dae31d78061e5e76744270a86dd0ee051c889/aiohttp-3.14.5-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5fb6a6e919bfb703227bc1ce6579281b84b1a2ba57deb9794dfdbec7dcd1e40c", size = 1702205, upload-time = "2026-10-11T01:01:20.904Z" },
+    { url = "https://files.pythonhosted.org/packages/16/27/6051bfde7b6f418f70edd60d655fa426abb3355fa0981764739d87ecf160/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:43e1b7994a8b038125f722bff07492ef501110722c2727c408995d9fb864c421", size = 1848588, upload-time = "2026-10-11T01:01:22.918Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/44/55efc06fc26c4e6e1c095f231b4c222bf2d86d64a8eebbc24b2bb5958ea8/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:5f3e96071686755d9cd3600c3880183eb94b012178e92746d68101800f0ed8a3", size = 1887540, upload-time = "2026-10-11T01:01:25.278Z" },
+    { url = "https://files.pythonhosted.org/packages/48/dc/1502bfdc2a65760d386ac6a00090b0addaa8a3c9c60b3f8127fad3a9afb2/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:cd88b01f3d37b7a2a34f91d98f14720206f1ea3d540843fab2d649dd5fb91fec", size = 1895030, upload-time = "2026-10-11T01:01:27.316Z" },
+    { url = "https://files.pythonhosted.org/packages/93/7e/44174bb6288264418c9eec07a5e35180969c0d5a796c7af544db3cb8a33a/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:f2ed8b64dc0c651c0f5a9c926777719770021251b8f336d97c4b80b660836ce1", size = 1693244, upload-time = "2026-10-11T01:01:29.39Z" },
+    { url = "https://files.pythonhosted.org/packages/47/dd/b507d64e50db23888582fff08eda13998b12f9dea70c072edaac19218380/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:a9918e58faf62ba2c7147927d06057aec78f42475aff5048047ec47e7265a600", size = 1926308, upload-time = "2026-10-11T01:01:31.634Z" },
+    { url = "https://files.pythonhosted.org/packages/98/4b/5b51b4f63e3f2793151f4aea49c48fe1e00baeb7cec9c7a206de499f8de0/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:42f320d4a5b00b9af0bddcfec5407dc6f2d9816f006b2f79ebbaa31f16895df3", size = 1888406, upload-time = "2026-10-11T01:01:33.715Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/13/d5e818a5eaba9f822016727299f41c0e1075799f82a6433ec508a93ab867/aiohttp-3.14.5-cp313-cp313-win32.whl", hash = "sha256:3ae800a20947e2c2e53088047d021e6bf7d51560cc49f6a0737a1f79d2e3a13c", size = 479970, upload-time = "2026-10-11T01:01:35.677Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/d0/8eca2c65aa467320990d78fb2005f38ed3588944280c39ff9deb6423fef1/aiohttp-3.14.5-cp313-cp313-win_amd64.whl", hash = "sha256:d05e94cdfe0d15d0206f970722d2554780ce562787b21b218b275447f8751319", size = 505985, upload-time = "2026-10-11T01:01:37.574Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/f8/4cdd65305d2fca14b886bea9ed2abb1fe726287872524e56e3d26692b47d/aiohttp-3.14.5-cp313-cp313-win_arm64.whl", hash = "sha256:f001b571ead90ca1770f1e616db255351a1703317f20374c361ef22f12c06d09", size = 487629, upload-time = "2026-10-11T01:01:39.477Z" },
+    { url = "https://files.pythonhosted.org/packages/43/be/3184a1d34a8be665569eadb7e9e764b4629e4f3413e241cb2e4d6fecf3b3/aiohttp-3.14.5-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:939042d5cda21d41a6f512e7cc8b8e33a2aebff863352251da495fbd91b673b5", size = 540673, upload-time = "2026-10-11T01:01:41.354Z" },
+    { url = "https://files.pythonhosted.org/packages/60/2a/d35f3ba4cf157b072e3b674bf9983047ca5ea5173c995d32d877e1191d36/aiohttp-3.14.5-cp314-cp314-android_24_x86_64.whl", hash = "sha256:6da32b5ff3fd78d244e37300463434c7145162bfd2b6e9e915ab164da37f7343", size = 554087, upload-time = "2026-10-11T01:01:43.719Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/d2/61a33880ca4eaca95a9c60ca3f6beed15555af1028652dfaac601627787b/aiohttp-3.14.5-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:1b438b73c38111818d0c9d6a5c2bfed8584c8e503a49ef085d70e874ec846738", size = 522613, upload-time = "2026-10-11T01:01:46.154Z" },
+    { url = "https://files.pythonhosted.org/packages/31/1d/de579b299d2225dc2c6fd99d579d91f16c02a913fb5af9a3cf2fe9bd88ba/aiohttp-3.14.5-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:755933b107ea7a6a9ac916f635a70595a5b1a32fac10a8ff0b9f2ab88555550c", size = 529682, upload-time = "2026-10-11T01:01:48.477Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/4a/ddb923564e15e053b6e060b0036e1694dcadcb13aa476c5a87dcad20e336/aiohttp-3.14.5-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:b3cc509327c7b27f6f4727a8830f4004f6df7766e179f2f4b8e54e65c0bec5d3", size = 540120, upload-time = "2026-10-11T01:01:50.474Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/36/a640fbecaa53727a5900b892bdbe17b5f3e8cc88903e22864fe41b654def/aiohttp-3.14.5-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:7bd8ac754ebd6733a3e2a0dd1674c4d8ab086196803fd8dcd776f07b4e2607d9", size = 818795, upload-time = "2026-10-11T01:01:52.665Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/b6/d52ca608859e271b5fa7944074802dc45f60e52c318a4ddc34edbf73586e/aiohttp-3.14.5-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:e724a7b6091f0b1ac064f9d1b15ff9ec52e6033a86cdae649e5f086e32a3c0db", size = 549667, upload-time = "2026-10-11T01:01:54.65Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/b5/05b8ac39a76ff4bca89f42a4c2471560c71f894ff6e4bc16158c951874e3/aiohttp-3.14.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c32e26310cc10e547f53cd13d39a369034f69dcb7d749d5cb0e5f67bc196b6ba", size = 548922, upload-time = "2026-10-11T01:01:56.547Z" },
+    { url = "https://files.pythonhosted.org/packages/19/b0/5aa186d56ce2334dabe29b70bd99dc8ae926ee44184c0de64a53d415a4f3/aiohttp-3.14.5-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1eb8167961ec4dfcc8cb9dd50bd0ee72519f7ef496be95203e49e27b01618382", size = 1882422, upload-time = "2026-10-11T01:01:59.258Z" },
+    { url = "https://files.pythonhosted.org/packages/db/f7/7d5c91bb9620db300c8ddb05337a9014301acb626223faff3abcb8ea47d7/aiohttp-3.14.5-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c1d60eafd9c7e8e74abd03a5b00df44e7febfe6d9b89b559c0a6551eef0699d4", size = 1843621, upload-time = "2026-10-11T01:02:01.417Z" },
+    { url = "https://files.pythonhosted.org/packages/30/0a/b208953b96d8f24b75f6da704f508e6c5cf3022f52b60c61933df082e89c/aiohttp-3.14.5-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:137351bf20bbed9a65e839f4a4452ac377389bdb2f2857d2acffef38f5e9f2d1", size = 1927915, upload-time = "2026-10-11T01:02:03.697Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/79/90ebcccb55e2d1e11a1fed581d83bb966e38fb35fb4b2577fdc980f8707a/aiohttp-3.14.5-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fba47bc2c3d7303c3d027c6cf4d07626c37b1314ac81f5820c31032e0ca1f677", size = 2036339, upload-time = "2026-10-11T01:02:06.046Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/66/55a8904b3a129fafdf94f9cc0a2e4ca09a3c914650be52355db7ad0bbdb6/aiohttp-3.14.5-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:94684b879ac1d71e4238850c99b62dc1b28d9086b156a2555f082010b85a865c", size = 1888041, upload-time = "2026-10-11T01:02:08.384Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/b8/96b25da7329a52e42c812b1e8b076386039ec4fc312afa043d173d8147fc/aiohttp-3.14.5-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:56572c42e3ecd636de8d2c3dd54cf5fc939cb5c32eb56297f176a0d366fac622", size = 1703849, upload-time = "2026-10-11T01:02:10.903Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/43/fbf976e3ae4c038d6f5c84945ab2150298c2d71201674d4e53d158063e75/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:a95529a92a446db351675f4aab518feaf5e99842f63f5dd17160c2b74f382db3", size = 1849703, upload-time = "2026-10-11T01:02:13.15Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/7d/218e912f4c1d89bde7ac551409be57ad2f6121638e56942d395a7cb1fa58/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:3edbece0379b8b4aaa67619b8aa2399bb66fce372cd5911098a434ea77220aa0", size = 1852695, upload-time = "2026-10-11T01:02:15.295Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/42/252a1b9287e3b6e393a1c3bd1776f36af30f5f25f071bbf2b0cb7eba9116/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:56d9828f204331a5ca8850fcfe2bcce95a149f1f223f60cc7216e5524978e480", size = 1893493, upload-time = "2026-10-11T01:02:17.93Z" },
+    { url = "https://files.pythonhosted.org/packages/78/97/71cae83d5100556fad1521684f7cd1e3e578432644f850245ed3bd969310/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:20064a177a070d789ee64a50b01a9161d3468e989baacfc6c714aa685c4b332f", size = 1693468, upload-time = "2026-10-11T01:02:20.666Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/69/73d88e97a8b5f0ca7a946d0011c0de99fb188b1687c7948ecd0553dc5bf0/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:81c2b3dfd56c62bee6108e4852d5970b4cf9086390b6983f52b666e878c1f115", size = 1915398, upload-time = "2026-10-11T01:02:23.011Z" },
+    { url = "https://files.pythonhosted.org/packages/05/f0/881644bcb15d4b258daea9b720a0af9dc4330496cc8d6ade9090cdd0cffc/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:09ec102b4b8c9a920275733bbc11fdbb615efe6f9231a06007c0218d336fb77a", size = 1871470, upload-time = "2026-10-11T01:02:25.278Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/de/19d9ebbcce5aedaa3242d8a99ff8816a60bdb7629fb0084bf4a45bfd1f62/aiohttp-3.14.5-cp314-cp314-win32.whl", hash = "sha256:9c428eb2bd8817588d16a0ab898aa4eb5d141f896aa2b394cc79a4cf61d9a8e2", size = 485517, upload-time = "2026-10-11T01:02:27.579Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/74/8cdaf0e58c2588371670d5a9a8215bbb971d36940b6e5d051967dd05c07d/aiohttp-3.14.5-cp314-cp314-win_amd64.whl", hash = "sha256:6f967dde489ca6a8c02d093ab245d2cbf50ccb5c36adf0188b17b0ca39d24b67", size = 511755, upload-time = "2026-10-11T01:02:29.685Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/6b/e0100e25502430a531c7cf1482a378d0b65bf728ab60c01ee270e56bc469/aiohttp-3.14.5-cp314-cp314-win_arm64.whl", hash = "sha256:1d2d981b53dd09a319e3570ef8cc3bbc3ef86f5a7abef0f6b2bff3867db3a9e7", size = 495151, upload-time = "2026-10-11T01:02:32.163Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/c2/ca2ead7b655688c53c03aeeb6e96e6851c9ff08d6be7b13802f53a6ae8fd/aiohttp-3.14.5-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:9ce66feae6ac65327379460380549bf1b8df8e17c4e25df2a2bcf168272e3bed", size = 855396, upload-time = "2026-10-11T01:02:34.443Z" },
+    { url = "https://files.pythonhosted.org/packages/a7/70/22206fea409255a240c926ce11de48de354ae2bb90ca44f709c05497585d/aiohttp-3.14.5-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:27c2322e03f66101acb09869ce1cf1efc04994ee95e1735b69827bf8c8b9d781", size = 567734, upload-time = "2026-10-11T01:02:36.644Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/e5/79a36c118308b56f8667d67e05d2fb6dc638ab45985704cdb199631bedaa/aiohttp-3.14.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ff75a7537413a86e7cafe98e0e1d6e3dc4b15c6349896e7d5c6b881bfdb6d550", size = 567379, upload-time = "2026-10-11T01:02:38.757Z" },
+    { url = "https://files.pythonhosted.org/packages/63/a3/2ebec7dece3b1f02c30d2e484647f6f7b13952b1bb40a4cb285b849e8432/aiohttp-3.14.5-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c061aa954daaf57d2a4b8374f9fca621ef0e1b603584431c220c22458c59b6d", size = 2050686, upload-time = "2026-10-11T01:02:41.169Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/d2/7e4d093db2f4450482652e7ef19a9e19919028f5135aa52bc4078c3beb80/aiohttp-3.14.5-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1612fa5857b37bf32e5c1eaeefb96e3b01e9c70679eec81f0934e8a600080863", size = 1915077, upload-time = "2026-10-11T01:02:43.563Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/88/bd40d09958442a0a1df67da81de496361d6e2afc04f9db2950d835da750b/aiohttp-3.14.5-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:adbeee7d6fd4cf5fe0aece2fb3edc4243615d3180430ba8149d01a90670cac99", size = 2027204, upload-time = "2026-10-11T01:02:46.185Z" },
+    { url = "https://files.pythonhosted.org/packages/63/eb/3a601c1f8d3103c1a60ea981f20924855da9f575d2007fc38f8898b792fb/aiohttp-3.14.5-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b2966998927d7bed9db12c0a4647b0c7b179755878fc9c357fe1ffd3e3b0c1a5", size = 2149520, upload-time = "2026-10-11T01:02:48.812Z" },
+    { url = "https://files.pythonhosted.org/packages/22/d0/4e41bfe1b1ce1cb6f6d2e59fa7a88ef5cf92c402b2d07e9018778ba9edbc/aiohttp-3.14.5-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8e317e0fb6b16212c881d2205a7d87414c29acd69320b3aa6dce9d9c7b86fe4f", size = 2002039, upload-time = "2026-10-11T01:02:51.293Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/5e/72067019545c502b881b031153c437752ecef48d7d213bc0218ccebb4bfb/aiohttp-3.14.5-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:50343c1757b4b6f6708eeaf24534b32f19dfb99fb1b762c00420867a62fc81e0", size = 1786164, upload-time = "2026-10-11T01:02:53.533Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/fe/7741efd6119bfb7a00827fe6f7b84b4409de58d888ae21adc5a9a6824992/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:083673c7a94c3ea035caaa5ca04288bdb44887abfe1f5ba23294e6a4b03efd2d", size = 1970689, upload-time = "2026-10-11T01:02:55.888Z" },
+    { url = "https://files.pythonhosted.org/packages/43/e7/342a13bf67f34d269bf2f7e870ecd72b99c832cc6f0a271a9210c0ebfb84/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:2528cb4c6b92008c76ac9ac6298624069bb2db91ff4929905512d1d84485f658", size = 1951967, upload-time = "2026-10-11T01:02:58.467Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/d4/fdb3b27340617e5e64df18a70fa89097778652ea5c7c7e2f79def76999c3/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:b1b8ece1e71132d2afba4dbc0c3d62c766e25165990b25db1196c04969eb3d84", size = 1968511, upload-time = "2026-10-11T01:03:00.883Z" },
+    { url = "https://files.pythonhosted.org/packages/83/b2/e8f88298de78d1a951f36f9f966d38ec6ed1d4721303ba02064a545e8aa6/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:fce9523df31cea6284f3e2c479876750d7687cf671d7b25d32b19effc0e86441", size = 1778497, upload-time = "2026-10-11T01:03:03.206Z" },
+    { url = "https://files.pythonhosted.org/packages/22/68/9ccdb93d664345c546be7f34480b921774d8c0d98f47e70d7e03b115d475/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:09e0eb18c7e0c8777e2f9149de63799195b9b3ca1b5c81ba6f32f2c6b8628210", size = 1999676, upload-time = "2026-10-11T01:03:05.829Z" },
+    { url = "https://files.pythonhosted.org/packages/57/4a/a33cfa6dcb00e94194ae4fe710432ca4ed111e016356b4ba4d2f4c3a124c/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6774814fd5c338e72ee0da5cbb9432816df450e69c019f72b5d29bdec2a1792d", size = 1963437, upload-time = "2026-10-11T01:03:08.196Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/20/eacbecfea3b5c3dcbfc9b023e3a5460f43e5dda16d06a2877ebe7184c3f3/aiohttp-3.14.5-cp314-cp314t-win32.whl", hash = "sha256:33f706574e32c6e694f352a856e05caf18f7f2c871b3e87b41c55ea452b409ab", size = 503973, upload-time = "2026-10-11T01:03:10.481Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/78/18eec294f6c8c5dc845dcf6d730a0147d8d0f17e86138a7bdb85e43a30fa/aiohttp-3.14.5-cp314-cp314t-win_amd64.whl", hash = "sha256:5ba14a839fbe87cf7c12a6b5661c05f324a296eb8363141edb3944ba63d4c9d3", size = 531190, upload-time = "2026-10-11T01:03:12.716Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/39/e53f8169acc85271ebd12b5b32ad7f1541b35639ccbe0f49034c64785d10/aiohttp-3.14.5-cp314-cp314t-win_arm64.whl", hash = "sha256:1061b364556e8172e8d46b0b183adeeb73e8c42d30ebc745591e1bd89acad52e", size = 510360, upload-time = "2026-10-11T01:03:15.08Z" },
+    { url = "https://files.pythonhosted.org/packages/68/30/173960c42b05a6c59f7558e4b12a4b0d9ba376cf6aa9bde7f9e08a30ca8d/aiohttp-3.14.5-py3-none-any.whl", hash = "sha256:efc21a454892828368b11c2c780de0ff8bc991f73f6b99c6b66e56205470929b", size = 279517, upload-time = "2026-10-11T01:05:08.523Z" },
 ]
 
 [[package]]
@@ -1146,19 +1146,22 @@ wheels = [
 
 [[package]]
 name = "claude-agent-sdk"
-version = "0.1.44"
+version = "0.2.165"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
+    { name = "jsonschema" },
     { name = "mcp" },
+    { name = "sniffio" },
     { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/30/40/5661e10daf69ee5c864f82a1888cc33c9378b2d7f7d11db3c2360aef3a30/claude_agent_sdk-0.1.44.tar.gz", hash = "sha256:8629436e7af367a1cbc81aa2a58a93aa68b8b2e4e14b0c5be5ac3627bd462c1b", size = 62439, upload-time = "2026-02-26T01:17:28.118Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/7f/45/10f00a408b480926b5e340e3507562ede1e30d4ce5b73eea9ccc3468a9e6/claude_agent_sdk-0.2.165.tar.gz", hash = "sha256:1bfa8e7a6bb36e82de9a12324c9bcfa6eebd4f96ee5890f0c656d50445240ff8", size = 365169, upload-time = "2026-10-08T18:18:49.528Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e9/1a/dcde83a6477bfdf8c5510fd84006cca763296e6bc5576e90cd89b97ec034/claude_agent_sdk-0.1.44-py3-none-macosx_11_0_arm64.whl", hash = "sha256:1dd976ad3efb673aefd5037dc75ee7926fb5033c4b9ab7382897ab647fed74e6", size = 55828889, upload-time = "2026-02-26T01:17:15.474Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/33/3b161256956968e18c81e2b2650fed7d2a1144d51042ed6317848643e5d7/claude_agent_sdk-0.1.44-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:d35b38ca40fa28f50fa88705599a298ab30c121c56b53655025eeceb463ac399", size = 70795212, upload-time = "2026-02-26T01:17:18.873Z" },
-    { url = "https://files.pythonhosted.org/packages/17/cb/67af9796dad77a94dfe851138f5ffc9e2e0a14407ba55fea07462c1cc8e5/claude_agent_sdk-0.1.44-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:853c15501f71a913a6cc6b40dc0b24b9505166cad164206b8eab229889e670b8", size = 71424685, upload-time = "2026-02-26T01:17:22.345Z" },
-    { url = "https://files.pythonhosted.org/packages/46/cd/2d3806c791250a76de2c1be863fc01d420729ad61496253e3d3033464c72/claude_agent_sdk-0.1.44-py3-none-win_amd64.whl", hash = "sha256:597e2fcad372086f93e4f6a380d3088ec4dd9b9efce309c5281b52a256fd5d25", size = 73493771, upload-time = "2026-02-26T01:17:25.837Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/a7/a7226ae5e7fa3f225d99a0acf12ee354c4af9c953661f66bbcd424e48853/claude_agent_sdk-0.2.165-py3-none-macosx_11_0_arm64.whl", hash = "sha256:7f7017bb59eaf77b9a7c7ce3b9ed2c8a397b8201c8630f011bb1b955290f06e4", size = 97973182, upload-time = "2026-10-08T18:18:56.039Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/9d/1eaa82f8dbafa63a3fb26aabc088be307c4977438269cc6cb10056a32e99/claude_agent_sdk-0.2.165-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:f4b5c6f536062e3af72357b1235f05ad4513230a32a3c639341a91a607d2df1e", size = 102479136, upload-time = "2026-10-08T18:19:01.908Z" },
+    { url = "https://files.pythonhosted.org/packages/40/4a/93fe172811bcd7704c4c4776d5eed1bb1881ba440d86e0f8e5cbbec0dca9/claude_agent_sdk-0.2.165-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:46a47e1e1075a8f2b7976f6bd5aa06c5610cb322c47cdc5b728fb25d02691164", size = 107447420, upload-time = "2026-10-08T18:19:09.571Z" },
+    { url = "https://files.pythonhosted.org/packages/57/81/a0d3ff04ae7045218566b36d1c78729c3fc7550877e154697f263ac5122e/claude_agent_sdk-0.2.165-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:9dbee4bfc69f0bb27ee455afdc19d78f958540a99217d2e28831fb9b7d496f08", size = 107800988, upload-time = "2026-10-08T18:19:16.24Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/d8/1685e8fc14bae5b9cbcfd6f4f6ca8b7ae8fd497a8bbf9c108978dd98620b/claude_agent_sdk-0.2.165-py3-none-win_amd64.whl", hash = "sha256:cf41dc1b1019bc7321b695d621fc94e6d8982c095cfb7d433d5c293e356a2404", size = 110401968, upload-time = "2026-10-08T18:19:24.136Z" },
 ]
 
 [[package]]
@@ -4871,7 +4874,7 @@ ci = [
     { name = "assemblyai", specifier = "==0.52.4" },
     { name = "beautifulsoup4", specifier = "==4.14.3" },
     { name = "blockbuster", specifier = "==1.5.26" },
-    { name = "claude-agent-sdk", specifier = "==0.1.44" },
+    { name = "claude-agent-sdk", specifier = "==0.2.165" },
     { name = "detect-secrets", specifier = "==1.5.0" },
     { name = "google-cloud-speech", specifier = "==2.40.0" },
     { name = "google-generativeai", specifier = "==0.8.6" },