BerriAI/litellm · error · BlackForestLabsError

No image URL in BFL result

Error message

No image URL in BFL result

What it means

The final edit response is expected to look like {"status":"Ready","result":{"sample":"https://..."}}. If JSON parsing succeeded but response_data['result']['sample'] is missing, empty, or null, this 500 BlackForestLabsError is raised. BFL signalled completion but delivered no image URL — usually a schema change or an upstream inconsistency.

Source

Thrown at litellm/llms/black_forest_labs/image_edit/transformation.py:305

    ) -> ImageResponse:
        """
        Transform Black Forest Labs response to OpenAI-compatible ImageResponse.

        This is called with the FINAL polled response (after handler does polling).
        The response contains: {"status": "Ready", "result": {"sample": "https://..."}}
        """
        try:
            response_data: Final = raw_response.json()
        except Exception as e:
            raise BlackForestLabsError(
                status_code=raw_response.status_code,
                message=f"Error parsing BFL response: {e}",
            )

        # Get image URL from result
        image_url: Final = response_data.get("result", {}).get("sample")
        if not image_url:
            raise BlackForestLabsError(
                status_code=500,
                message="No image URL in BFL result",
            )

        # Build ImageResponse
        return ImageResponse(
            created=int(time.time()),
            data=[ImageObject(url=image_url)],
        )

    def get_error_class(
        self, error_message: str, status_code: int, headers: dict | httpx.Headers
    ) -> BlackForestLabsError:
        """Return the appropriate error class for Black Forest Labs."""
        return BlackForestLabsError(
            status_code=status_code,
            message=error_message,
        )

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Log the full response JSON on failure to see the actual schema; if the URL moved to another key, report/patch the transformation in LiteLLM and update.
2. Ensure you are hitting the official api.bfl.ai base unless you control the alternative's schema.
3. Retry the edit once — occasional null samples on BFL's side are transient.
4. Upgrade LiteLLM in case a newer release already tracks the new BFL schema.

null

null

try:
    resp = await litellm.aimage_edit(model=M, image=img, prompt=p)
except Exception as e:
    if "No image URL in BFL result" in str(e):
        return await litellm.aimage_edit(model=M, image=img, prompt=p)  # transient null sample
    raise

When it happens

Trigger: The polling endpoint returns JSON with status 'Ready' but no result.sample key (renamed field, null sample, or a different response shape from a new BFL API version or custom api_base).

Common situations: BFL ships an API revision that renames the sample field; pointing api_base at a BFL-compatible gateway that returns a slightly different schema; race where the job flips to Ready before the artifact is attached.

Related errors

• Error parsing BFL response: {e}
• No polling_url in BFL response
• Error apply_db_fixes: {str(e)}
• Error in response object format, got None
• BFL_API_KEY is not set. Please set it via environment variab

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/1e1e18315a19bf2a. Report an issue: GitHub.