BerriAI/litellm · error · ValueError

Error in response: {raw_response.error}

Error message

Error in response: {raw_response.error}

What it means

transform_response raises this when the parsed ResponsesAPIResponse carries a non-null error field — the provider accepted the HTTP request but embedded an error object in the response body (common with the Responses API: 200 OK plus response.error). The message includes the provider's error payload verbatim.

Source

Thrown at litellm/completion_extras/litellm_responses_transformation/transformation.py:745

        model_response: "ModelResponse",
        logging_obj: "LiteLLMLoggingObj",
        request_data: dict,
        messages: list["AllMessageValues"],
        optional_params: dict,
        litellm_params: dict,
        encoding: object,
        api_key: str | None = None,
        json_mode: bool | None = None,
    ) -> "ModelResponse":
        """Transform Responses API response to chat completion response"""
        from litellm.responses.utils import ResponseAPILoggingUtils
        from litellm.types.llms.openai import ResponsesAPIResponse

        if not isinstance(raw_response, ResponsesAPIResponse):
            raise ValueError(f"Unexpected response type: {type(raw_response)}")

        if raw_response.error is not None:
            raise ValueError(f"Error in response: {raw_response.error}")

        output_items = raw_response.output
        if len(output_items) == 0:
            recovered_output_items: Final = self._recover_output_items_from_logging(logging_obj)
            if recovered_output_items:
                output_items = cast(Any, recovered_output_items)
                raw_response.output = cast(Any, recovered_output_items)
                verbose_logger.warning(
                    "Recovered empty Responses API output from raw SSE for model=%s",
                    model,
                )

        # Convert response output to choices using the static helper
        choices: Final = self._convert_response_output_to_choices(
            output_items=output_items,
            handle_raw_dict_callback=self._handle_raw_dict_response_item,
        )

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Read the embedded error message — it is the provider's own text and names the root cause
2. For auth/quota errors, verify API key and billing, then retry
3. For transient upstream errors, retry with backoff or fail over to another deployment via litellm Router
4. If using a proxy/gateway, check its logs for the upstream exchange

def response_has_error(parsed) -> bool:
    return getattr(parsed, "error", None) is not None

try:
    resp = litellm.completion(model=m, messages=msgs)
except ValueError as e:
    if str(e).startswith("Error in response:"):
        # in-band provider error: inspect text, retry transient causes, fail over for auth/quota
        handle_provider_error(str(e))
    raise

When it happens

Trigger: Provider returns 200 with an error object: invalid API key surfaced late, content policy violations, model access denied, or upstream failures reported in-band instead of via HTTP status.

Common situations: Misconfigured credentials on some gateways; region-locked or deactivated models; transient upstream errors; quota issues delivered as in-band errors.

Related errors

• {error_message}
• Unexpected responses stream payload
• Stream ended without a completed response
• Stream completed response is invalid
• tool call not supported: {tool_call}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/fffc4c98e6773253. Report an issue: GitHub.