BerriAI/litellm · error · OVHCloudException

raw_response.text

Error message

raw_response.text

What it means

LiteLLM's OVHCloud embedding handler calls raw_response.json(); on failure it raises OVHCloudException with the raw response body as the message plus the real status code and headers. The body text typically explains the underlying problem.

Source

Thrown at litellm/llms/ovhcloud/embedding/transformation.py:100

        headers: dict,
    ) -> dict:
        return {"input": input, "model": model, **optional_params}

    def transform_embedding_response(
        self,
        model: str,
        raw_response: httpx.Response,
        model_response: EmbeddingResponse,
        logging_obj: LiteLLMLoggingObj,
        api_key: str | None,
        request_data: dict,
        optional_params: dict,
        litellm_params: dict,
    ) -> EmbeddingResponse:
        try:
            raw_response_json: Final = raw_response.json()
        except Exception:
            raise OVHCloudException(
                message=raw_response.text,
                status_code=raw_response.status_code,
                headers=raw_response.headers,
            )

        model_response.model = raw_response_json.get("model")
        model_response.data = raw_response_json.get("data")
        model_response.object = raw_response_json.get("object")

        usage: Final = Usage(
            prompt_tokens=raw_response_json.get("usage", {}).get("prompt_tokens", 0),
            total_tokens=raw_response_json.get("usage", {}).get("total_tokens", 0),
        )

        model_response.usage = usage
        return model_response

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

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Read the exception message - it is the raw body and states the cause
2. Verify the OVH token is valid for AI Endpoints
3. Confirm the embedding model is actually deployed on your OVH project and spelled exactly as documented
4. Retry after OVH incidents if the body indicates a transient gateway error

Catch OVHCloudException around litellm.embedding(); log the message (raw body) and branch: auth/model errors need configuration fixes, gateway errors justify one retry with backoff.

When it happens

Trigger: Calling litellm.embedding() with an ovhcloud/* model when the endpoint returns non-JSON: invalid token error page, model not deployed on the OVH project, or an HTML gateway error.

Common situations: Wrong OVH token; embedding model name not matching what is deployed on the project; OVH incidents returning HTML maintenance pages.

Related errors

• raw_response.text
• raw_response.text
• Error parsing OpenRouter response: {e}
• Error parsing OpenRouter response: {e}
• judge response is not a JSON object

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/18f18fad96766cda. Report an issue: GitHub.