Common helper to route the request

Converts a string to a boolean if it's a recognized boolean string. Returns None if the string is not a recognized boolean value. :param

Build a request-like object whose same-origin is ``base_url``. ``get_request_base_url`` defers to ``request.base_url`` unless the caller is a

[Non-Blocking] Safely get the request headers. Caches the result on request.state to avoid re-creating dict(request.headers) per call. W

Generate config class dynamically from JSON configuration

Create streaming response, checking if the first chunk is an error. If the first chunk is an error, return a standard JSON error response.

Get the cache key for the given arguments. Args: **kwargs: kwargs to litellm.completion() or embedding() Return

Get the base URL for Vertex AI API calls. - ``global`` uses the global control plane host. - Multi-region geographies (e.g. ``us``, ``eu

Calls async_post_call_response_headers_hook on all CustomLogger callbacks. Merges all returned header dicts (later callbacks override

Common utility function to process audio files for audio transcription APIs. Handles various input types: - File paths (str, os.PathLike

Release the lock if the current pod holds it. Uses an atomic Lua compare-and-delete to prevent TOCTOU races where a stale own

Call PANW Prisma AIRS API to scan content or a tool_event.

Update the litellm params for health check. - gets a short `messages` param for health check - adds a bounded `max_tokens` when the depl

Auto-apply ``pytest.mark.vcr`` to collected items. Skip semantics (in priority order): 1. ``vcr_disabled()`` — global env-var off-switch (``

Main authentication and authorization builder

- handles scenario where content is list and not string - content list is just text, and no images Motivation: mistral api + azure ai do

Encode a file/batch ID with model routing information. Format: <prefix><base64(litellm:<original_id>;model,<model_name>)> The result pre

Encode provider and model_id into video_id using base64.

Returns the deployment based on routing strategy

Get the `custom_llm_provider` from the request header `custom-llm-provider`

Get the MCP Server from the server id

Retrieves a value from a nested dictionary using dot notation. Args: data: The dictionary to search in key_path: The path to

Raises Exception if Virtual Key is not allowed to call the route

Sets a span attribute safely with OTEL-compliant primitive typing for Arize/Phoenix.

Factory mirroring user_api_key_auth: SERVER span + url.path + http.route.

for cloudflare ai gateway - https://github.com/BerriAI/litellm/issues/4317 Handles custom api_base for: 1. Gemini (Google AI

Get the AWS region name from the environment variables. Parameters: optional_params (dict): Optional parameters for the

Ensure mock_prisma.db.litellm_config exists with async methods (the conftest only stubs ``litellm_configtable`` — this is a different table).

Construct the handler with auth + proxy seams patched at the instance level. ``_ensure_access_token`` and ``_check_custom_proxy`` are inherited f

Check if the given model supports function calling and return a boolean value. Parameters: model (str): The model name to be checked.

Add a success callback to `litellm.success_callback`. Auto-routes async callbacks to litellm._async_success_callback. Special

Get the `custom_llm_provider` from the request query parameters Safely reads the request query parameters

Get the base URL for the request, considering X-Forwarded-* headers. Resolution order: ``PROXY_BASE_URL`` env var, then X-Forwarded-* when