BerriAI/litellm · error · ValueError

Error in response object format, got None

Error message

Error in response object format, got None

What it means

In _transform_response_dict_to_openai_response the Bedrock image response body is parsed with response.json(); if the parsed value is None (body was 'null', empty, or not a JSON object), LiteLLM raises ValueError. It means Bedrock (or whatever answered at api_base) returned a 2xx response whose JSON body is null rather than an image payload. The raw body is debug-logged via verbose_logger before the check, which helps diagnosis.

Solutions

1. Enable litellm debug logging to capture the raw response.text just before the failure
2. If a gateway or proxy is in the path, reproduce the same request against real Bedrock to isolate it
3. Verify the model actually supports the image generation API you invoked (e.g. it is a Nova Canvas / Stability image model)

try:
    resp = litellm.image(model=model, prompt=prompt)
except ValueError as e:
    if "Error in response object format" in str(e):
        log.error("bedrock returned 2xx with null body; check gateway/api_base")
    raise

When it happens

Trigger: Bedrock image call returns HTTP 200 with a null or empty JSON body: seen with gateways/proxies at a custom api_base that mis-handle the response, truncated responses, or routing a non-image model to the image generation API.

Common situations: Custom api_base pointing at a corporate gateway that returns null on success, model/router misconfiguration, behavior changes after upstream updates.

Related errors

• AgentCore: Failed to read/parse JSON response body
• completion_response must be of type ImageResponse for…
• err.response.text
• Error in response object format, got None
• Error parsing BFL response

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/6e89e82e5a7a81f9. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bedrock/image_generation/image_handler.py:324

        response: httpx.Response,
        data: dict,
    ) -> ImageResponse:
        """
        Transforms the Image Generation response from Bedrock to OpenAI format
        """

        ## LOGGING
        if logging_obj is not None:
            logging_obj.post_call(
                input=prompt,
                api_key="",
                original_response=response.text,
                additional_args={"complete_input_dict": data},
            )
        verbose_logger.debug("raw model_response: %s", response.text)
        response_dict: Final = response.json()
        if response_dict is None:
            raise ValueError("Error in response object format, got None")

        config_class: Final = self.get_config_class(model=model)

        config_class.transform_response_dict_to_openai_response(
            model_response=model_response,
            response_dict=response_dict,
        )

        return model_response

View on GitHub (pinned to 77b7c6c40c)