BerriAI/litellm · error · CohereError

{response_text}

Error message

{response_text}

What it means

Response-parsing failure in Cohere rerank: raw_response.json() raised (non-JSON body), so the raw response text is re-raised as the CohereError message — typically an HTML/XML error page or truncated body from the rerank endpoint.

Source

Thrown at litellm/llms/cohere/rerank/transformation.py:147

        self,
        model: str,
        raw_response: httpx.Response,
        model_response: RerankResponse,
        logging_obj: LiteLLMLoggingObj,
        api_key: str | None = None,
        request_data: dict = {},
        optional_params: dict = {},
        litellm_params: dict = {},
    ) -> RerankResponse:
        """
        Transform Cohere rerank response

        No transformation required, litellm follows cohere API response format
        """
        try:
            raw_response_json: Final = raw_response.json()
        except Exception:
            raise CohereError(message=raw_response.text, status_code=raw_response.status_code)

        return RerankResponse(**raw_response_json)

    def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BaseLLMException:
        return CohereError(message=error_message, status_code=status_code)

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Read the response text in the error; the Cohere rerank API rejected the request (commonly auth, model name, or payload shape).
  2. Verify COHERE_API_KEY is valid and the model (e.g. rerank-v3.5) is available on your plan.
Defensive patterns

Strategy: try-catch

When it happens

Trigger: Thrown at litellm/llms/cohere/rerank/transformation.py:147 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/4c4231ba0407b27c. Report an issue: GitHub.