BerriAI/litellm · error · ImportError

Missing boto3 to call bedrock. Run 'pip install boto3'.

Error message

Missing boto3 to call bedrock. Run 'pip install boto3'.

What it means

LiteLLM's Bedrock request-signing path needs botocore's SigV4Auth to sign requests; when the import fails it raises this ImportError telling you boto3/botocore is not installed. It occurs while preparing a signed AWS request, before any network call is made.

Source

Thrown at litellm/llms/bedrock/common_utils.py:1475

    ) -> tuple:
        """
        Sign AWS request using Signature Version 4.

        Args:
            service_name: AWS service name ("bedrock" or "s3")
            data: Request data (string or dict)
            endpoint_url: Full endpoint URL
            optional_params: Optional parameters containing AWS credentials
            method: HTTP method (default: POST)

        Returns:
            Tuple of (signed_headers, signed_data)
        """
        try:
            from botocore.auth import SigV4Auth
            from botocore.awsrequest import AWSRequest
        except ImportError:
            raise ImportError("Missing boto3 to call bedrock. Run 'pip install boto3'.")

        # Get AWS credentials using existing methods
        aws_region_name: Final = self._base_aws._get_aws_region_name(optional_params=optional_params, model="")
        credentials: Final = self._base_aws.get_credentials(
            aws_access_key_id=optional_params.get("aws_access_key_id"),
            aws_secret_access_key=optional_params.get("aws_secret_access_key"),
            aws_session_token=optional_params.get("aws_session_token"),
            aws_region_name=aws_region_name,
            aws_session_name=optional_params.get("aws_session_name"),
            aws_profile_name=optional_params.get("aws_profile_name"),
            aws_role_name=optional_params.get("aws_role_name"),
            aws_web_identity_token=optional_params.get("aws_web_identity_token"),
            aws_sts_endpoint=optional_params.get("aws_sts_endpoint"),
        )

        # Prepare the request data
        method_upper: Final = method.upper()
        if method_upper == "GET":

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. pip install boto3 (or pip install 'boto3[bedrock]') in the active interpreter
2. Add boto3 to your requirements.txt/pyproject dependencies alongside litellm
3. Verify with: python -c "import botocore.auth" in the same venv the app runs in

Example fix

# before: ImportError at request time
# after
pip install "boto3[bedrock]"
python -c "from botocore.auth import SigV4Auth; print('ok')"

def boto3_available() -> bool:
    try:
        import botocore.auth, botocore.awsrequest  # noqa: F401
        return True
    except ImportError:
        return False

assert boto3_available(), "pip install boto3 before using bedrock provider"

try:
    resp = await client.sign_and_call(...)
except ImportError as e:
    if 'boto3' in str(e):
        sys.exit("AWS provider unavailable: install boto3 or switch to a non-Bedrock model")

When it happens

Trigger: Running LiteLLM with the bedrock provider in an environment where 'pip install boto3[bedrock]' was never run, or where botocore was uninstalled/upgraded away; also slim Docker images that omit optional AWS extras.

Common situations: Installing litellm without the [extra_proxy] or AWS extras, CI images trimmed for size, dependency resolvers downgrading/removing botocore, or virtualenv mismatch where the app runs in a different interpreter than the one where boto3 was installed.

Related errors

• Missing boto3 to call bedrock. Run 'pip install boto3'.
• Missing botocore to use AWS SigV4 authentication. Run 'pip i
• Model needs to be set for bedrock
• BedrockException: Context Window Error - {error_str}
• BedrockException Invalid Authentication - {error_str}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/86c692ce8017f15b. Report an issue: GitHub.