BerriAI/litellm · error · RuntimeError

Error parsing chunk: {e},\nReceived chunk: {chunk}

Error message

Error parsing chunk: {e},\nReceived chunk: {chunk}

What it means

Except-handler in ModelResponseIterator chunk parsing: _common_chunk_parsing_logic raised while transforming the raw chunk into a ModelResponse; both the exception and the offending chunk are embedded so the malformed payload can be inspected.

Source

Thrown at litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:3367

    def __next__(self):
        try:
            chunk: Final = self.response_iterator.__next__()
        except StopIteration:
            if self.chunk_type == "accumulated_json" and self.accumulated_json:
                result: Final = self.handle_accumulated_json_chunk(chunk="", is_final=True)
                if result is not None:
                    return result
            raise StopIteration
        except ValueError as e:
            raise RuntimeError(f"Error receiving chunk from stream: {e}")

        try:
            return self._common_chunk_parsing_logic(chunk=chunk)
        except StopIteration:
            raise StopIteration
        except ValueError as e:
            raise RuntimeError(f"Error parsing chunk: {e},\nReceived chunk: {chunk}")

    # Async iterator
    def __aiter__(self):
        self.async_response_iterator = self.streaming_response.__aiter__()
        return self

    async def __anext__(self):
        try:
            chunk: Final = await self.async_response_iterator.__anext__()
        except StopAsyncIteration:
            if self.chunk_type == "accumulated_json" and self.accumulated_json:
                result: Final = self.handle_accumulated_json_chunk(chunk="", is_final=True)
                if result is not None:
                    return result
            raise StopAsyncIteration
        except ValueError as e:
            raise RuntimeError(f"Error receiving chunk from stream: {e}")

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Inspect the logged chunk and parse error; the stream chunk format was unexpected.
2. Check for proxy interference or an API schema change.

Example fix

# log chunk content and adapt parsing or upgrade litellm.

When it happens

Trigger: Triggered when parsing a Vertex AI Gemini stream chunk raises an exception.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/73c95bf2690e77e3. Report an issue: GitHub.