BerriAI/litellm · error · ValueError

GET responses is not supported for {custom_llm_provider}

Error message

GET responses is not supported for {custom_llm_provider}

What it means

Dispatch guard in the Responses API get path: no BaseResponsesAPIConfig implementing get_response was found for the resolved custom_llm_provider, so retrieving a stored response is unsupported for that provider.

Source

Thrown at litellm/responses/main.py:1426

        decoded_response_id: Final[DecodedResponseId] = ResponsesAPIRequestUtils._decode_responses_api_response_id(
            response_id=response_id,
        )
        response_id = decoded_response_id.get("response_id") or response_id
        custom_llm_provider = decoded_response_id.get("custom_llm_provider") or custom_llm_provider

        if custom_llm_provider is None:
            raise ValueError("custom_llm_provider is required but passed as None")

        # get provider config
        responses_api_provider_config: Final[BaseResponsesAPIConfig | None] = (
            ProviderConfigManager.get_provider_responses_api_config(
                model=None,
                provider=custom_llm_provider,
            )
        )

        if responses_api_provider_config is None:
            raise ValueError(f"GET responses is not supported for {custom_llm_provider}")

        local_vars.update(kwargs)

        # Pre Call logging
        litellm_logging_obj.update_from_kwargs(
            kwargs=local_vars,
            model=None,
            optional_params={
                "response_id": response_id,
            },
            litellm_params={
                "litellm_call_id": litellm_call_id,
            },
            custom_llm_provider=custom_llm_provider,
        )

        # Call the handler with _is_async flag instead of directly calling the async handler
        response = base_llm_http_handler.get_responses(

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use a provider that supports GET responses, or retrieve the response from a supported provider.

When it happens

Trigger: Thrown at litellm/responses/main.py:1426 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/bab24539054a1e65. Report an issue: GitHub.