BerriAI/litellm · error · BedrockError

Error parsing received text={outputText}. Error-{e}

Error message

Error parsing received text={outputText}.
Error-{e}

What it means

Assignment failure while writing outputText into the model response: the extracted text could not be set on choices[0].message.content because the response object lacked the expected shape, and the handler appends the parse exception for diagnosis.

Source

Thrown at litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py:383

            )

        try:
            if (
                outputText is not None
                and len(outputText) > 0
                and hasattr(model_response.choices[0], "message")
                and getattr(model_response.choices[0].message, "tool_calls", None) is None
            ):
                model_response.choices[0].message.content = outputText
            elif (
                hasattr(model_response.choices[0], "message")
                and getattr(model_response.choices[0].message, "tool_calls", None) is not None
            ):
                pass
            else:
                raise Exception()
        except Exception as e:
            raise BedrockError(
                message=f"Error parsing received text={outputText}.\nError-{e}",
                status_code=raw_response.status_code,
            )

        ## CALCULATING USAGE - bedrock returns usage in the headers
        bedrock_input_tokens: Final = raw_response.headers.get("x-amzn-bedrock-input-token-count", None)
        bedrock_output_tokens: Final = raw_response.headers.get("x-amzn-bedrock-output-token-count", None)

        prompt_tokens: Final = int(bedrock_input_tokens or litellm.token_counter(messages=messages))

        completion_tokens: Final = int(
            bedrock_output_tokens
            or litellm.token_counter(
                text=model_response.choices[0].message.content,
                count_response_tokens=True,
            )
        )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check outputText for malformed or unexpected content from the model.
2. Retry the request; parsing failures can be transient.
3. Upgrade litellm if the provider response format changed.

When it happens

Trigger: Thrown at litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py:383 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/527157ed324f8c02. Report an issue: GitHub.