BerriAI/litellm · error · BedrockError

Timeout error occurred.

Error message

Timeout error occurred.

What it means

The synchronous Bedrock image-generation request exceeded the configured httpx timeout and httpx.TimeoutException was raised; litellm maps it to BedrockError with status_code=408 and the fixed message 'Timeout error occurred.'. Image generation on Bedrock commonly takes tens of seconds, so the default timeout is frequently too short.

Source

Thrown at litellm/llms/bedrock/image_generation/image_handler.py:124

                prompt=prompt,
                model_response=model_response,
                client=(client if client is not None and isinstance(client, AsyncHTTPHandler) else None),
            )

        if client is None or not isinstance(client, HTTPHandler):
            client = _get_httpx_client()
        try:
            response: Final = client.post(
                url=prepared_request.endpoint_url,
                headers=prepared_request.prepped.headers,
                data=prepared_request.body,
            )
            response.raise_for_status()
        except httpx.HTTPStatusError as err:
            error_code: Final = err.response.status_code
            raise BedrockError(status_code=error_code, message=err.response.text)
        except httpx.TimeoutException:
            raise BedrockError(status_code=408, message="Timeout error occurred.")
        ### FORMAT RESPONSE TO OPENAI FORMAT ###
        model_response = self._transform_response_dict_to_openai_response(
            model_response=model_response,
            model=model,
            logging_obj=logging_obj,
            prompt=prompt,
            response=response,
            data=prepared_request.data,
        )
        return model_response

    async def async_image_generation(
        self,
        prepared_request: BedrockImagePreparedRequest,
        timeout: float | httpx.Timeout | None,
        model: str,
        logging_obj: LitellmLogging,
        prompt: str,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Pass a larger timeout explicitly: litellm.image_generation(..., timeout=300).
2. Reduce output cost: fewer images (numberOfImages=1), smaller width/height, fewer inference steps.
3. Retry once on timeout — the request is idempotent from the client's perspective.
4. If persistent, check network egress/proxy latency to the bedrock-runtime endpoint.

Example fix

# before
resp = litellm.image_generation(model="bedrock/stability.stable-image-core-1:0", prompt=p)

# after
resp = litellm.image_generation(model="bedrock/stability.stable-image-core-1:0", prompt=p, timeout=300)

try:
    resp = litellm.image_generation(model=model, prompt=p, timeout=300)
except BedrockError as e:
    if e.status_code == 408:
        resp = litellm.image_generation(model=model, prompt=p, timeout=600)  # one timed retry
    else:
        raise

When it happens

Trigger: litellm.image_generation(..., timeout=N) or the default client timeout being smaller than the actual generation time; slow models (e.g. stability.stable-diffusion-xl with many steps) on loaded endpoints.

Common situations: Using the default timeout for high-resolution/multi-image jobs, network bottlenecks, oversized prompts, or proxy-side latency.

Understand the failure class

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• Model needs to be set for bedrock
• BedrockException: Timeout Error - {error_str}
• completion_response must be of type ImageResponse for bedroc
• Timeout error occurred.
• Timeout error occurred.

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/eba596ec28b840ec. Report an issue: GitHub.