Read response content.

Convenience wrapper around update_environment_variables that automatically extracts metadata/litellm_metadata from kwargs, so

Count records matching the criteria.

List all API keys with optional filtering and pagination. Args: page (Optional[int]): Page number for pagination

Safely read the request body and parse it as JSON. Parameters: - request: The request object to read the body from Returns: - d

Allows users to raise custom exceptions/log when a call fails, without having to deal with parsing Request body. Callbacks can return

Returns an Exception as ProxyException, this ensures all exceptions are OpenAI API compatible

Create a new record.

Get encoding, loading it lazily if needed.

Start the logging worker. Idempotent - safe to call multiple times.

Generate an API key based on the provided data. Docs: https://docs.litellm.ai/docs/proxy/virtual_keys Parameters: - duration: Optio

Calculates the cost per token for a given model, prompt tokens, and completion tokens. Handles context caching as well. Input:

Maps an LLM Provider Exception to OpenAI Exception Format

Includes router model_group_alias'es as well if team_id specified, returns matching team-specific models

Choose one deployment from `candidates` (all sharing the requested `model_name`). Returns `None` when there are no candidates.

Common checks across jwt + key-based auth. 1. If team is blocked 1.1. If project is blocked 2. If team can call model 2.2 If pro

Converts given messages from OpenAI format to Gemini format - Parts must be iterable - Roles must alternate b/w 'user' and 'model' (same

Builds `StandardLoggingGuardrailInformation` and adds it to the request metadata so it can be used for logging to DataDog, Langfuse, etc.

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

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

- Check if team id in proxy Team Table - if valid, return LiteLLM_TeamTable object with defined limits - if not, then raise an error

Converts given messages from OpenAI format to Bedrock format - Roles must alternate b/w 'user' and 'model' (same as anthropic -> merge conse

Raw-seed a scratch-tagged team row; returns its team_id. The target team for the team write matrices (update / member_*). Raw prisma (not POS

Override to add debug logging.

Returns auth token and project id

Check if the request body is safe. A malicious user can set the api_base to their own domain and invoke POST /chat/completions to intercept