BerriAI/litellm · error · Timeout

BedrockException: Timeout Error - {error_str}

Error message

BedrockException: Timeout Error - {error_str}

What it means

Bedrock-specific: Timeout raised when the AWS error text contains 'Connect timeout on endpoint URL' or 'timed out' — the HTTP connection to the Bedrock runtime endpoint could not be established or the call exceeded the client timeout before any response.

Source

Thrown at litellm/litellm_core_utils/exception_mapping_utils.py:883

            llm_provider="bedrock",
            response=getattr(original_exception, "response", None),
        )
    elif "AccessDeniedException" in error_str:
        raise PermissionDeniedError(
            message=f"BedrockException PermissionDeniedError - {error_str}",
            model=model,
            llm_provider="bedrock",
            response=getattr(original_exception, "response", None),
        )
    elif "throttlingException" in error_str or "ThrottlingException" in error_str:
        raise RateLimitError(
            message=f"BedrockException: Rate Limit Error - {error_str}",
            model=model,
            llm_provider="bedrock",
            response=getattr(original_exception, "response", None),
        )
    elif "Connect timeout on endpoint URL" in error_str or "timed out" in error_str:
        raise Timeout(
            message=f"BedrockException: Timeout Error - {error_str}",
            model=model,
            llm_provider="bedrock",
        )
    elif "Could not process image" in error_str:
        raise litellm.InternalServerError(
            message=f"BedrockException - {error_str}",
            model=model,
            llm_provider="bedrock",
        )
    elif hasattr(original_exception, "status_code"):
        if original_exception.status_code == 500:
            raise ServiceUnavailableError(
                message=f"BedrockException - {original_exception.message}",
                llm_provider="bedrock",
                model=model,
                response=httpx.Response(
                    status_code=500,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. If connect-timeout: verify network egress to bedrock-runtime.<region>.amazonaws.com:443 (curl -I) and add a VPC endpoint or NAT gateway in private subnets.
2. If generation-timeout: raise litellm.completion(..., timeout=...) or set litellm.request_timeout.
3. Enable streaming so long generations deliver tokens incrementally.
4. Retry with num_retries for transient network blips.

Example fix

# before
resp = litellm.completion(model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0", messages=msgs)

# after
resp = litellm.completion(model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0", messages=msgs, timeout=900, num_retries=2, stream=True)

import socket

def bedrock_endpoint_reachable(region: str, timeout: float = 5.0) -> bool:
    host = f"bedrock-runtime.{region}.amazonaws.com"
    try:
        socket.create_connection((host, 443), timeout=timeout).close()
        return True
    except OSError:
        return False

import litellm

def is_bedrock_timeout(e: BaseException) -> bool:
    return isinstance(e, litellm.Timeout) and getattr(e, "llm_provider", "") == "bedrock"

try:
    resp = litellm.completion(model="bedrock/...", messages=msgs, timeout=900, num_retries=2)
except litellm.Timeout:
    raise RuntimeError("bedrock unreachable or too slow — check VPC egress/NAT and timeout budget")

When it happens

Trigger: botocore failing to reach bedrock-runtime.<region>.amazonaws.com (network egress blocked, DNS failure, VPC without NAT), slow corporate proxies, or the request exceeding litellm's configured timeout (default 600s) on very long generations.

Common situations: Containers/lambda in a VPC without internet route or a bedrock VPC endpoint, firewall rules blocking port 443 to AWS, DNS misconfiguration, cross-region latency, or oversized prompts making the model exceed the client timeout.

Understand the failure class

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

Related errors

• Timeout error occurred.
• BedrockException: Context Window Error - {error_str}
• BedrockException Invalid Authentication - {error_str}
• BedrockException PermissionDeniedError - {error_str}
• BedrockException: Rate Limit Error - {error_str}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/9bfbff13dcbd0dd3. Report an issue: GitHub.