BerriAI/litellm · error · HTTPException

Provider {custom_llm_provider} api base not found

Error message

Provider {custom_llm_provider} api base not found

What it means

HTTPException raised when the provider config for the pass-through route exists but get_api_base returns no base URL for custom_llm_provider — the provider has no default/known API base and none was configured. The pass-through cannot construct a target URL.

Source

Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:126

    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
):
    """
    Factory function for creating pass-through endpoints for LLM providers.
    """
    from litellm.types.utils import LlmProviders
    from litellm.utils import ProviderConfigManager

    provider_config: Final = ProviderConfigManager.get_provider_model_info(
        provider=LlmProviders(custom_llm_provider),
        model=None,
    )
    if provider_config is None:
        raise HTTPException(status_code=404, detail=f"Provider {custom_llm_provider} not found")

    base_target_url: Final = provider_config.get_api_base()

    if base_target_url is None:
        raise HTTPException(status_code=404, detail=f"Provider {custom_llm_provider} api base not found")

    encoded_endpoint = httpx.URL(endpoint).path

    # Ensure endpoint starts with '/' for proper URL construction
    if not encoded_endpoint.startswith("/"):
        encoded_endpoint = "/" + encoded_endpoint

    # Construct the full target URL using httpx, preserving any base path
    # prefix that the operator configured on base_target_url.
    base_url: Final = httpx.URL(base_target_url)
    updated_url: Final = base_url.copy_with(
        path=HttpPassThroughEndpointHelpers.join_base_and_endpoint_path(base_url, encoded_endpoint)
    )

    # Add or update query parameters
    provider_api_key: Final = passthrough_endpoint_router.get_credentials(
        custom_llm_provider=custom_llm_provider,
        region_name=None,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Configure the api base for the provider in the proxy config (api_base), then retry.

When it happens

Trigger: Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:126 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/133616eaaf6d23cf. Report an issue: GitHub.