BerriAI/litellm · error · ValueError

custom_llm_provider is required but passed as None

Error message

custom_llm_provider is required but passed as None

What it means

Dispatch guard in the Responses API: custom_llm_provider is None after get_llm_provider_info, so the model string could not be mapped to a provider and no provider config can be selected.

Source

Thrown at litellm/responses/main.py:1103

            user=user,
            optional_params=dict(responses_api_request_params),
            litellm_params={
                **responses_api_request_params,
                "aresponses": _is_async,
                "litellm_call_id": litellm_call_id,
                "model_info": kwargs.get("model_info"),
                "data_residency": infer_openai_data_residency(custom_llm_provider, litellm_params.api_base),
                "metadata": (kwargs["litellm_metadata"] if "litellm_metadata" in kwargs else kwargs.get("metadata")),
            },
            custom_llm_provider=custom_llm_provider,
        )

        # Decode any litellm-encoded encrypted-content item IDs back to their original IDs
        input = ResponsesAPIRequestUtils._restore_encrypted_content_item_ids_in_input(input)

        # Call the handler with _is_async flag instead of directly calling the async handler
        if custom_llm_provider is None:
            raise ValueError("custom_llm_provider is required but passed as None")

        response = base_llm_http_handler.response_api_handler(
            model=model,
            input=input,
            responses_api_provider_config=responses_api_provider_config,
            response_api_optional_request_params=responses_api_request_params,
            custom_llm_provider=custom_llm_provider,
            litellm_params=litellm_params,
            logging_obj=litellm_logging_obj,
            extra_headers=extra_headers,
            extra_body=extra_body,
            timeout=timeout or request_timeout,
            _is_async=_is_async,
            client=kwargs.get("client"),
            fake_stream=responses_api_provider_config.should_fake_stream(
                model=model, stream=stream, custom_llm_provider=custom_llm_provider
            ),
            litellm_metadata=kwargs.get("litellm_metadata", {}),

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Pass custom_llm_provider explicitly (e.g., 'openai') when calling the responses API.

When it happens

Trigger: Thrown at litellm/responses/main.py:1103 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/48a9f54ec2be796f. Report an issue: GitHub.