BerriAI/litellm · error · HTTPException

Router not initialized. Cannot use model-based routing.

Error message

Router not initialized. Cannot use model-based routing.

What it means

HTTPException(500) from the model-credential resolver in the files/batch proxy utils: llm_router is None — the proxy has no LiteLLM Router initialized (no models loaded) — so model-based routing to fetch provider credentials is impossible. The operator must add models to the proxy config.

Source

Thrown at litellm/proxy/openai_files_endpoints/common_utils.py:310

):
    """
    Retrieve API credentials for a model from the LLM Router.

    Args:
        llm_router: LiteLLM Router instance
        model_id: Model name or deployment ID
        operation_context: Description for error messages (e.g., "file upload", "batch creation")

    Returns:
        Dictionary with credentials (api_key, api_base, custom_llm_provider, etc.)

    Raises:
        HTTPException: If router not initialized or model not found
    """
    from fastapi import HTTPException

    if llm_router is None:
        raise HTTPException(
            status_code=500,
            detail={"error": "Router not initialized. Cannot use model-based routing."},
        )

    credentials: Final = llm_router.get_deployment_credentials_with_provider(model_id=model_id)

    if credentials is None:
        raise HTTPException(
            status_code=400,
            detail={"error": f"Model '{model_id}' not found in model_list. Please check your config.yaml."},
        )

    return credentials


def get_team_provider_credentials(
    llm_router: Optional["Router"],
    user_api_key_dict: "UserAPIKeyAuth",

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Add models to the proxy config so the router is initialized, or avoid model-based routing for this request.

When it happens

Trigger: Thrown at litellm/proxy/openai_files_endpoints/common_utils.py:310 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/238cc841eaf4e0d8. Report an issue: GitHub.