Add LiteLLM provider for OpenAI API compatible models

docs/api/providers.md

@@ -39,3 +39,5 @@
 ::: pydantic_ai.providers.moonshotai.MoonshotAIProvider
 
 ::: pydantic_ai.providers.ollama.OllamaProvider
+
+::: pydantic_ai.providers.litellm.LiteLLMProvider

docs/models/openai.md

@@ -563,3 +563,29 @@ result = agent.run_sync('What is the capital of France?')
 print(result.output)
 #> The capital of France is Paris.
 ```
+
+### LiteLLM
+
+To use [LiteLLM](https://www.litellm.ai/), set the configs as outlined in the [doc](https://docs.litellm.ai/docs/set_keys). In `LiteLLMProvider`, you can pass `api_base` and `api_key`. The value of these configs will depend on your setup. For example, if you are using OpenAI models, then you need to pass `https://api.openai.com/v1` as the `api_base` and your OpenAI API key as the `api_key`. If you are using a LiteLLM proxy server running on your local machine, then you need to pass `http://localhost:<port>` as the `api_base` and your LiteLLM API key as the `api_key`.
+
+Once you have the configs, use the [`LiteLLMProvider`][pydantic_ai.providers.litellm.LiteLLMProvider] as follows:
+
+```python
+from pydantic_ai import Agent
+from pydantic_ai.models.openai import OpenAIChatModel
+from pydantic_ai.providers.litellm import LiteLLMProvider
+
+model = OpenAIChatModel(
+    'openai/gpt-3.5-turbo',
+    provider=LiteLLMProvider(
+        api_base='<api-base-url>',
+        api_key='<api-key>'
+    )
+)
+agent = Agent(model)
+
+result = agent.run_sync('What is the capital of France?')
+print(result.output)
+#> The capital of France is Paris.
+...
+```

pydantic_ai_slim/pydantic_ai/models/__init__.py

@@ -716,6 +716,7 @@ def infer_model(model: Model | KnownModelName | str) -> Model:  # noqa: C901
         'openrouter',
         'together',
         'vercel',
+        'litellm',
     ):
         from .openai import OpenAIChatModel
 

pydantic_ai_slim/pydantic_ai/models/openai.py

@@ -225,6 +225,7 @@ def __init__(
             'openrouter',
             'together',
             'vercel',
+            'litellm',
         ]
         | Provider[AsyncOpenAI] = 'openai',
         profile: ModelProfileSpec | None = None,
@@ -252,6 +253,7 @@ def __init__(
             'openrouter',
             'together',
             'vercel',
+            'litellm',
         ]
         | Provider[AsyncOpenAI] = 'openai',
         profile: ModelProfileSpec | None = None,
@@ -278,6 +280,7 @@ def __init__(
             'openrouter',
             'together',
             'vercel',
+            'litellm',
         ]
         | Provider[AsyncOpenAI] = 'openai',
         profile: ModelProfileSpec | None = None,

pydantic_ai_slim/pydantic_ai/providers/__init__.py

@@ -135,6 +135,10 @@ def infer_provider_class(provider: str) -> type[Provider[Any]]:  # noqa: C901
         from .github import GitHubProvider
 
         return GitHubProvider
+    elif provider == 'litellm':
+        from .litellm import LiteLLMProvider
+
+        return LiteLLMProvider
     else:  # pragma: no cover
         raise ValueError(f'Unknown provider: {provider}')
 

pydantic_ai_slim/pydantic_ai/providers/litellm.py

@@ -0,0 +1,138 @@
+from __future__ import annotations as _annotations
+
+from typing import overload
+
+from httpx import AsyncClient as AsyncHTTPClient
+from openai import AsyncOpenAI
+
+from pydantic_ai.models import cached_async_http_client
+from pydantic_ai.profiles import ModelProfile
+from pydantic_ai.profiles.amazon import amazon_model_profile
+from pydantic_ai.profiles.anthropic import anthropic_model_profile
+from pydantic_ai.profiles.cohere import cohere_model_profile
+from pydantic_ai.profiles.deepseek import deepseek_model_profile
+from pydantic_ai.profiles.google import google_model_profile
+from pydantic_ai.profiles.grok import grok_model_profile
+from pydantic_ai.profiles.groq import groq_model_profile
+from pydantic_ai.profiles.meta import meta_model_profile
+from pydantic_ai.profiles.mistral import mistral_model_profile
+from pydantic_ai.profiles.moonshotai import moonshotai_model_profile
+from pydantic_ai.profiles.openai import OpenAIJsonSchemaTransformer, OpenAIModelProfile, openai_model_profile
+from pydantic_ai.profiles.qwen import qwen_model_profile
+from pydantic_ai.providers import Provider
+
+try:
+    from openai import AsyncOpenAI
+except ImportError as _import_error:  # pragma: no cover
+    raise ImportError(
+        'Please install the `openai` package to use the LiteLLM provider, '
+        'you can use the `openai` optional group — `pip install "pydantic-ai-slim[openai]"`'
+    ) from _import_error
+
+
+class LiteLLMProvider(Provider[AsyncOpenAI]):
+    """Provider for LiteLLM API."""
+
+    @property
+    def name(self) -> str:
+        return 'litellm'
+
+    @property
+    def base_url(self) -> str:
+        return str(self.client.base_url)
+
+    @property
+    def client(self) -> AsyncOpenAI:
+        return self._client
+
+    def model_profile(self, model_name: str) -> ModelProfile | None:
+        # Map provider prefixes to their profile functions
+        provider_to_profile = {
+            'anthropic': anthropic_model_profile,
+            'openai': openai_model_profile,
+            'google': google_model_profile,
+            'mistralai': mistral_model_profile,
+            'mistral': mistral_model_profile,
+            'cohere': cohere_model_profile,
+            'amazon': amazon_model_profile,
+            'bedrock': amazon_model_profile,
+            'meta-llama': meta_model_profile,
+            'meta': meta_model_profile,
+            'groq': groq_model_profile,
+            'deepseek': deepseek_model_profile,
+            'moonshotai': moonshotai_model_profile,
+            'x-ai': grok_model_profile,
+            'qwen': qwen_model_profile,
+        }
+
+        profile = None
+
+        # Check if model name contains a provider prefix (e.g., "anthropic/claude-3")
+        if '/' in model_name:
+            provider_prefix, model_suffix = model_name.split('/', 1)
+            if provider_prefix in provider_to_profile:
+                profile = provider_to_profile[provider_prefix](model_suffix)
+
+        # If no profile found, default to OpenAI profile
+        if profile is None:
+            profile = openai_model_profile(model_name)
+
+        # As LiteLLMProvider is used with OpenAIModel, which uses OpenAIJsonSchemaTransformer,
+        # we maintain that behavior
+        return OpenAIModelProfile(json_schema_transformer=OpenAIJsonSchemaTransformer).update(profile)
+
+    @overload
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        api_base: str | None = None,
+        custom_llm_provider: str | None = None,
+    ) -> None: ...
+
+    @overload
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        api_base: str | None = None,
+        custom_llm_provider: str | None = None,
+        http_client: AsyncHTTPClient,
+    ) -> None: ...
+
+    @overload
+    def __init__(self, *, openai_client: AsyncOpenAI) -> None: ...
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        api_base: str | None = None,
+        custom_llm_provider: str | None = None,
+        openai_client: AsyncOpenAI | None = None,
+        http_client: AsyncHTTPClient | None = None,
+    ) -> None:
+        """Initialize a LiteLLM provider.
+
+        Args:
+            api_key: API key for the model provider. If None, LiteLLM will try to get it from environment variables.
+            api_base: Base URL for the model provider. Use this for custom endpoints or self-hosted models.
+            custom_llm_provider: Custom LLM provider name for LiteLLM. Use this if LiteLLM can't auto-detect the provider.
+            openai_client: Pre-configured OpenAI client. If provided, other parameters are ignored.
+            http_client: Custom HTTP client to use.
+        """
+        if openai_client is not None:
+            self._client = openai_client
+            return
+
+        # Create OpenAI client that will be used with LiteLLM's completion function
+        # The actual API calls will be intercepted and routed through LiteLLM
+        if http_client is not None:
+            self._client = AsyncOpenAI(
+                base_url=api_base, api_key=api_key or 'litellm-placeholder', http_client=http_client
+            )
+        else:
+            http_client = cached_async_http_client(provider='litellm')
+            self._client = AsyncOpenAI(
+                base_url=api_base, api_key=api_key or 'litellm-placeholder', http_client=http_client
+            )

tests/models/cassettes/test_model_names/test_known_model_names.yaml

@@ -99,53 +99,19 @@ interactions:
       alt-svc:
       - h3=":443"; ma=86400
       content-length:
-      - '762'
+      - '99'
       content-type:
       - application/json
       referrer-policy:
       - strict-origin-when-cross-origin
       strict-transport-security:
       - max-age=3600; includeSubDomains
     parsed_body:
-      data:
-      - created: 0
-        id: llama-4-maverick-17b-128e-instruct
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: qwen-3-32b
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: qwen-3-235b-a22b-instruct-2507
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: llama-4-scout-17b-16e-instruct
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: gpt-oss-120b
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: qwen-3-coder-480b
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: llama-3.3-70b
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: llama3.1-8b
-        object: model
-        owned_by: Cerebras
-      - created: 0
-        id: qwen-3-235b-a22b-thinking-2507
-        object: model
-        owned_by: Cerebras
-      object: list
+      code: wrong_api_key
+      message: Wrong API Key
+      param: api_key
+      type: invalid_request_error
     status:
-      code: 200
-      message: OK
+      code: 401
+      message: Unauthorized
 version: 1