BerriAI/litellm · error · HTTPException

Internal Server Error ({e})

Error message

Internal Server Error ({e})

What it means

Catch-all around litellm.model_cost access on the public model cost map endpoint: reading the model cost map raised unexpectedly (import or initialization problem inside litellm). The original exception is embedded and surfaced as a 500.

Source

Thrown at litellm/proxy/public_endpoints/public_endpoints.py:416

    return provider_create_fields


@router.get(
    "/public/litellm_model_cost_map",
    tags=["public", "model management"],
)
async def get_litellm_model_cost_map():
    """
    Public endpoint to get the LiteLLM model cost map.
    Returns pricing information for all supported models.
    """
    import litellm

    try:
        _model_cost_map: Final = litellm.model_cost
        return _model_cost_map
    except Exception as e:
        raise HTTPException(
            status_code=500,
            detail=f"Internal Server Error ({e})",
        )


@router.get(
    "/public/litellm_blog_posts",
    tags=["public"],
    response_model=BlogPostsResponse,
)
async def get_litellm_blog_posts():
    """
    Public endpoint to get the latest LiteLLM blog posts.

    Fetches from GitHub with a 1-hour in-process cache.
    Falls back to the bundled local backup on any failure.
    """
    try:

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check proxy logs for the exception detail; fix the failing configuration or request and retry.

When it happens

Trigger: Thrown at litellm/proxy/public_endpoints/public_endpoints.py:416 when the library encounters an invalid state.

Common situations: See trigger scenarios.

Understand the failure class

• HTTP status errors: handling 4xx and 5xx responses — how to handle 4xx and 5xx responses properly.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/2e983b9323782696. Report an issue: GitHub.