fix: fix import errors

enterprise/litellm_enterprise/types/proxy/proxy_server.py

@@ -1,4 +1,6 @@
-from typing import Literal, TypedDict
+from typing import Literal
+
+from typing_extensions import TypedDict
 
 
 class CustomAuthSettings(TypedDict):

litellm/completion_extras/litellm_responses_transformation/handler.py

@@ -2,7 +2,9 @@
 Handler for transforming /chat/completions api requests to litellm.responses requests
 """
 
-from typing import TYPE_CHECKING, Any, Coroutine, TypedDict, Union
+from typing import TYPE_CHECKING, Any, Coroutine, Union
+
+from typing_extensions import TypedDict
 
 if TYPE_CHECKING:
     from litellm import CustomStreamWrapper, LiteLLMLoggingObj, ModelResponse

litellm/endpoints/speech/speech_to_completion_bridge/handler.py

@@ -2,7 +2,9 @@
 Handler for transforming /chat/completions api requests to litellm.responses requests
 """
 
-from typing import TYPE_CHECKING, Optional, TypedDict, Union
+from typing import TYPE_CHECKING, Optional, Union
+
+from typing_extensions import TypedDict
 
 if TYPE_CHECKING:
     from litellm import LiteLLMLoggingObj

litellm/integrations/humanloop.py

@@ -4,9 +4,10 @@ Humanloop integration
 https://humanloop.com/
 """
 
-from typing import Any, Dict, List, Optional, Tuple, TypedDict, Union, cast
+from typing import Any, Dict, List, Optional, Tuple, Union, cast
 
 import httpx
+from typing_extensions import TypedDict
 
 import litellm
 from litellm.caching import DualCache

litellm/integrations/prompt_management_base.py

@@ -1,5 +1,7 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional, Tuple, TypedDict
+from typing import Any, Dict, List, Optional, Tuple
+
+from typing_extensions import TypedDict
 
 from litellm.types.llms.openai import AllMessageValues
 from litellm.types.utils import StandardCallbackDynamicParams

litellm/litellm_core_utils/logging_worker.py

@@ -1,7 +1,9 @@
 import asyncio
 import contextlib
 import contextvars
-from typing import Coroutine, Optional, TypedDict
+from typing import Coroutine, Optional
+
+from typing_extensions import TypedDict
 
 from litellm._logging import verbose_logger
 

litellm/llms/huggingface/rerank/transformation.py

@@ -1,8 +1,9 @@
 import os
 import uuid
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, TypedDict, Union
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 
 import httpx
+from typing_extensions import TypedDict
 
 import litellm
 from litellm.llms.base_llm.chat.transformation import BaseLLMException

litellm/llms/vertex_ai/text_to_speech/text_to_speech_handler.py

@@ -1,6 +1,7 @@
-from typing import Optional, TypedDict, Union
+from typing import Optional, Union
 
 import httpx
+from typing_extensions import TypedDict
 
 import litellm
 from litellm.llms.custom_httpx.http_handler import (

litellm/llms/vertex_ai/vertex_embeddings/types.py

@@ -3,7 +3,9 @@ Types for Vertex Embeddings Requests
 """
 
 from enum import Enum
-from typing import List, Optional, TypedDict, Union
+from typing import List, Optional, Union
+
+from typing_extensions import TypedDict
 
 
 class TaskType(str, Enum):

litellm/model_prices_and_context_window_backup.json

@@ -20777,5 +20777,207 @@
         "metadata": {
             "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions"
         }
+    },
+    "ovhcloud/Qwen2.5-VL-72B-Instruct": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 9.1e-07,
+        "output_cost_per_token": 9.1e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct"
+    },
+    "ovhcloud/llava-v1.6-mistral-7b-hf": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 2.9e-07,
+        "output_cost_per_token": 2.9e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "supports_vision": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b"
+    },
+    "ovhcloud/gpt-oss-120b": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 8e-08,
+        "output_cost_per_token": 4e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "supports_reasoning": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b"
+    },
+    "ovhcloud/Meta-Llama-3_3-70B-Instruct": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 6.7e-07,
+        "output_cost_per_token": 6.7e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct"
+    },
+    "ovhcloud/Qwen2.5-Coder-32B-Instruct": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 8.7e-07,
+        "output_cost_per_token": 8.7e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct"
+    },
+    "ovhcloud/Mixtral-8x7B-Instruct-v0.1": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 6.3e-07,
+        "output_cost_per_token": 6.3e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1"
+    },
+    "ovhcloud/Meta-Llama-3_1-70B-Instruct": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 6.7e-07,
+        "output_cost_per_token": 6.7e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": false,
+        "supports_tool_choice": false,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct"
+    },
+    "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 9e-08,
+        "output_cost_per_token": 2.8e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506"
+    },
+    "ovhcloud/DeepSeek-R1-Distill-Llama-70B": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 6.7e-07,
+        "output_cost_per_token": 6.7e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b"
+    },
+    "ovhcloud/Llama-3.1-8B-Instruct": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct"
+    },
+    "ovhcloud/Mistral-7B-Instruct-v0.3": {
+        "max_tokens": 127000,
+        "max_input_tokens": 127000,
+        "max_output_tokens": 127000,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3"
+    },
+    "ovhcloud/gpt-oss-20b": {
+        "max_tokens": 131000,
+        "max_input_tokens": 131000,
+        "max_output_tokens": 131000,
+        "input_cost_per_token": 4e-08,
+        "output_cost_per_token": 1.5e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "supports_reasoning": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b"
+    },
+    "ovhcloud/Mistral-Nemo-Instruct-2407": {
+        "max_tokens": 118000,
+        "max_input_tokens": 118000,
+        "max_output_tokens": 118000,
+        "input_cost_per_token": 1.3e-07,
+        "output_cost_per_token": 1.3e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407"
+    },
+    "ovhcloud/Qwen3-32B": {
+        "max_tokens": 32000,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "input_cost_per_token": 8e-08,
+        "output_cost_per_token": 2.3e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b"
+    },
+    "ovhcloud/mamba-codestral-7B-v0.1": {
+        "max_tokens": 256000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "input_cost_per_token": 1.9e-07,
+        "output_cost_per_token": 1.9e-07,
+        "litellm_provider": "ovhcloud",
+        "mode": "chat",
+        "supports_function_calling": false,
+        "supports_response_schema": true,
+        "supports_tool_choice": false,
+        "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1"
     }
 }

litellm/proxy/hooks/parallel_request_limiter.py

@@ -1,10 +1,11 @@
 import asyncio
 import sys
 from datetime import datetime, timedelta
-from typing import TYPE_CHECKING, Any, List, Literal, Optional, Tuple, TypedDict, Union
+from typing import TYPE_CHECKING, Any, List, Literal, Optional, Tuple, Union
 
 from fastapi import HTTPException
 from pydantic import BaseModel
+from typing_extensions import TypedDict
 
 import litellm
 from litellm import DualCache, ModelResponse

litellm/proxy/management_endpoints/scim/scim_v2.py

@@ -5,7 +5,7 @@ This is an enterprise feature and requires a premium license.
 """
 
 import uuid
-from typing import Any, Dict, List, Optional, Set, Tuple, TypedDict
+from typing import Any, Dict, List, Optional, Set, Tuple
 
 from fastapi import (
     APIRouter,
@@ -17,6 +17,7 @@ from fastapi import (
     Request,
     Response,
 )
+from typing_extensions import TypedDict
 
 import litellm
 from litellm._logging import verbose_proxy_logger

litellm/proxy/pass_through_endpoints/llm_provider_handlers/assembly_passthrough_logging_handler.py

@@ -2,10 +2,11 @@ import asyncio
 import json
 import time
 from datetime import datetime
-from typing import Literal, Optional, TypedDict
+from typing import Literal, Optional
 from urllib.parse import urlparse
 
 import httpx
+from typing_extensions import TypedDict
 
 import litellm
 from litellm._logging import verbose_proxy_logger

litellm/router_utils/cooldown_cache.py

@@ -3,7 +3,9 @@ Wrapper around router cache. Meant to handle model cooldown logic
 """
 
 import time
-from typing import TYPE_CHECKING, Any, List, Optional, Tuple, TypedDict, Union
+from typing import TYPE_CHECKING, Any, List, Optional, Tuple, Union
+
+from typing_extensions import TypedDict
 
 from litellm import verbose_logger
 from litellm.caching.caching import DualCache

litellm/router_utils/prompt_caching_cache.py

@@ -4,7 +4,9 @@ Wrapper around router cache. Meant to store model id when prompt caching support
 
 import hashlib
 import json
-from typing import TYPE_CHECKING, Any, List, Optional, TypedDict, Union
+from typing import TYPE_CHECKING, Any, List, Optional, Union
+
+from typing_extensions import TypedDict
 
 from litellm.caching.caching import DualCache
 from litellm.caching.in_memory_cache import InMemoryCache

litellm/types/caching.py

@@ -1,7 +1,8 @@
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
 from pydantic import BaseModel
+from typing_extensions import TypedDict
 
 
 class LiteLLMCacheType(str, Enum):

litellm/types/guardrails.py

@@ -1,9 +1,9 @@
 from datetime import datetime
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, Field
-from typing_extensions import Required
+from typing_extensions import Required, TypedDict
 
 """
 Pydantic object defining how to set guardrails on litellm proxy

litellm/types/images/main.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 from litellm.types.utils import FileTypes
 

litellm/types/integrations/anthropic_cache_control_hook.py

@@ -1,4 +1,6 @@
-from typing import Literal, Optional, TypedDict, Union
+from typing import Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 from litellm.types.llms.openai import ChatCompletionCachedContent
 

litellm/types/integrations/argilla.py

@@ -1,7 +1,9 @@
 import os
 from datetime import datetime as dt
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, Set, TypedDict
+from typing import Any, Dict, List, Literal, Optional, Set
+
+from typing_extensions import TypedDict
 
 
 class ArgillaItem(TypedDict):

litellm/types/integrations/base_health_check.py

@@ -1,4 +1,6 @@
-from typing import Literal, Optional, TypedDict
+from typing import Literal, Optional
+
+from typing_extensions import TypedDict
 
 
 class IntegrationHealthCheckStatus(TypedDict):

litellm/types/integrations/datadog.py

@@ -1,5 +1,7 @@
 from enum import Enum
-from typing import Optional, TypedDict
+from typing import Optional
+
+from typing_extensions import TypedDict
 
 DD_MAX_BATCH_SIZE = 1000
 

litellm/types/integrations/datadog_llm_obs.py

@@ -3,7 +3,9 @@ Payloads for Datadog LLM Observability Service (LLMObs)
 
 API Reference: https://docs.datadoghq.com/llm_observability/setup/api/?tab=example#api-standards
 """
-from typing import Any, Dict, List, Literal, Optional, TypedDict
+from typing import Any, Dict, List, Literal, Optional
+
+from typing_extensions import TypedDict
 
 from litellm.types.integrations.custom_logger import StandardCustomLoggerInitParams
 

litellm/types/integrations/gcs_bucket.py

@@ -1,4 +1,6 @@
-from typing import TYPE_CHECKING, Any, Dict, Optional, TypedDict
+from typing import TYPE_CHECKING, Any, Dict, Optional
+
+from typing_extensions import TypedDict
 
 from litellm.types.utils import StandardLoggingPayload
 

litellm/types/integrations/langfuse.py

@@ -1,4 +1,6 @@
-from typing import Optional, TypedDict
+from typing import Optional
+
+from typing_extensions import TypedDict
 
 
 class LangfuseLoggingConfig(TypedDict):

litellm/types/integrations/langsmith.py

@@ -1,8 +1,9 @@
 from dataclasses import dataclass
 from datetime import datetime
-from typing import Any, Dict, List, NamedTuple, Optional, TypedDict
+from typing import Any, Dict, List, NamedTuple, Optional
 
 from pydantic import BaseModel
+from typing_extensions import TypedDict
 
 
 class LangsmithInputs(BaseModel):

litellm/types/integrations/pagerduty.py

@@ -1,5 +1,7 @@
 from datetime import datetime
-from typing import List, Literal, Optional, TypedDict, Union
+from typing import List, Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 from litellm.types.utils import StandardLoggingUserAPIKeyMetadata
 

litellm/types/integrations/rag/bedrock_knowledgebase.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 
 class BedrockKBLocation(TypedDict, total=False):

litellm/types/integrations/slack_alerting.py

@@ -1,9 +1,10 @@
 import os
 from datetime import datetime as dt
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, Set, TypedDict
+from typing import Any, Dict, List, Literal, Optional, Set
 
 from pydantic import BaseModel, Field
+from typing_extensions import TypedDict
 
 from litellm.types.utils import LiteLLMPydanticObjectBase
 

litellm/types/litellm_core_utils/streaming_chunk_builder_utils.py

@@ -1,4 +1,6 @@
-from typing import TYPE_CHECKING, Optional, TypedDict
+from typing import TYPE_CHECKING, Optional
+
+from typing_extensions import TypedDict
 
 from ..utils import CompletionTokensDetails, PromptTokensDetailsWrapper
 

litellm/types/llms/anthropic_messages/anthropic_response.py

@@ -1,6 +1,6 @@
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
-from typing_extensions import TypeAlias
+from typing_extensions import TypeAlias, TypedDict
 
 from litellm.types.llms.anthropic import (
     AnthropicResponseContentBlockText,

litellm/types/llms/bedrock.py

@@ -1,11 +1,12 @@
 import json
-from typing import Any, List, Literal, Optional, TypedDict, Union
+from typing import Any, List, Literal, Optional, Union
 
 from typing_extensions import (
     TYPE_CHECKING,
     Protocol,
     Required,
     Self,
+    TypedDict,
     TypeGuard,
     get_origin,
     override,

litellm/types/llms/bedrock_invoke_agents.py

@@ -4,7 +4,9 @@ Type definitions for AWS Bedrock Invoke Agent API responses.
 https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_InvokeAgent.html
 """
 
-from typing import Any, Dict, List, Optional, TypedDict, Union
+from typing import Any, Dict, List, Optional, Union
+
+from typing_extensions import TypedDict
 
 
 class InvokeAgentEventHeaders(TypedDict, total=False):

litellm/types/llms/databricks.py

@@ -1,11 +1,12 @@
 import json
-from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
 from pydantic import BaseModel
 from typing_extensions import (
     Protocol,
     Required,
     Self,
+    TypedDict,
     TypeGuard,
     get_origin,
     override,

litellm/types/llms/mistral.py

@@ -1,4 +1,6 @@
-from typing import List, Literal, Optional, TypedDict, Union
+from typing import List, Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 
 class FunctionCall(TypedDict):

litellm/types/llms/ollama.py

@@ -1,11 +1,12 @@
 import json
-from typing import Any, List, Optional, TypedDict, Union
+from typing import Any, List, Optional, Union
 
 from pydantic import BaseModel
 from typing_extensions import (
     Protocol,
     Required,
     Self,
+    TypedDict,
     TypeGuard,
     get_origin,
     override,

litellm/types/llms/openrouter.py

@@ -1,6 +1,8 @@
 import json
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, Tuple, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Tuple, Union
+
+from typing_extensions import TypedDict
 
 
 class OpenRouterErrorMessage(TypedDict):

litellm/types/llms/rerank.py

@@ -1,11 +1,12 @@
 import json
 from enum import Enum
-from typing import Any, Dict, List, Literal, Optional, Tuple, TypedDict, Union
+from typing import Any, Dict, List, Literal, Optional, Tuple, Union
 
 from typing_extensions import (
     Protocol,
     Required,
     Self,
+    TypedDict,
     TypeGuard,
     get_origin,
     override,

litellm/types/llms/watsonx.py

@@ -1,8 +1,9 @@
 import json
 from enum import Enum
-from typing import Any, List, Optional, TypedDict, Union
+from typing import Any, List, Optional, Union
 
 from pydantic import BaseModel
+from typing_extensions import TypedDict
 
 
 class WatsonXAPIParams(TypedDict):

litellm/types/passthrough_endpoints/pass_through_endpoints.py

@@ -1,5 +1,7 @@
 from enum import Enum
-from typing import Optional, TypedDict
+from typing import Optional
+
+from typing_extensions import TypedDict
 
 
 class EndpointType(str, Enum):

litellm/types/proxy/litellm_pre_call_utils.py

@@ -1,4 +1,4 @@
-from typing import TypedDict
+from typing_extensions import TypedDict
 
 
 class SecretFields(TypedDict):

litellm/types/proxy/management_endpoints/common_daily_activity.py

@@ -1,8 +1,9 @@
 from datetime import date
 from enum import Enum
-from typing import Any, Dict, List, Optional, TypedDict
+from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Field
+from typing_extensions import TypedDict
 
 
 class GroupByDimension(str, Enum):

litellm/types/proxy/management_endpoints/ui_sso.py

@@ -1,6 +1,7 @@
-from typing import List, Literal, Optional, TypedDict, Union
+from typing import List, Literal, Optional, Union
 
 from pydantic import Field
+from typing_extensions import TypedDict
 
 from litellm.types.utils import LiteLLMPydanticObjectBase
 

litellm/types/proxy/ui_sso.py

@@ -1,4 +1,6 @@
-from typing import Literal, Optional, TypedDict
+from typing import Literal, Optional
+
+from typing_extensions import TypedDict
 
 
 class ReturnedUITokenObject(TypedDict):

litellm/types/realtime.py

@@ -1,4 +1,6 @@
-from typing import List, Literal, Optional, TypedDict, Union
+from typing import List, Literal, Optional, Union
+
+from typing_extensions import TypedDict
 
 from .llms.openai import (
     OpenAIRealtimeEvents,

litellm/utils.py

@@ -4616,7 +4616,7 @@ def _check_provider_match(model_info: dict, custom_llm_provider: Optional[str])
     return True
 
 
-from typing import TypedDict
+from typing_extensions import TypedDict
 
 
 class PotentialModelNamesAndCustomLLMProvider(TypedDict):