For a given model id, return the model info Returns - dict: the model in list with 'model_name', 'litellm_params', Optional[

Retrieves the HTTP client from the cache If not present, creates a new client Caches the new client and returns it.

Context manager that overrides ``user_api_key_auth`` for a role. Usage:: def test_admin_only(client, auth_as): from litellm.

Example usage: response = router.completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hey, how's it going?"}]

Load providers from JSON configuration file

Returns the provider for a given model name - e.g. 'azure/chatgpt-v-2' -> 'azure' For router -> Can also give the whole litellm param dict -

Recursively serialize data while detecting circular references. If a circular reference is detected then a marker string is returned. NUL

Replace volatile field values with "<VOLATILE>" so dict equality works. Recursive over dicts and lists. Pass an explicit ``volatile`` set to

Adds LiteLLM-specific data to the request. Args: data (dict): The data dictionary to be modified. request (Request): The inc

Get a compiled regex pattern by name. Args: pattern_name: Name of the prebuilt pattern Returns: Compiled regex pattern

Clear all policies from the registry.

Generate a mock UserAPIKeyAuth object

Helper to construct a guardrail with test defaults.

This hook is called before the routing decision is made. Used for the litellm auto-router to modify the request before the routing d

Get the allowed MCP Servers for the user. Priority: 1. If object_permission.mcp_servers is explicitly set, use it (even for

Process and validate MCP request headers from the ASGI scope. This includes: 1. Extracting and validating authentication head

Calculate the cost of a given completion call fot GPT-3.5-turbo, llama2, any litellm supported llm. Parameters: completion_response

Start a span for ``role`` without dedup or attribute mapping. For callers that own and manage their own span lifecycle. ``tracer`` ov

Get the complete URL for the CometAPI call. Returns: str: The complete URL for the API call.

Add a callback to litellm.callbacks Ensures no duplicates are added.