BerriAI/litellm · error · ValueError

messages must be a list

Error message

messages must be a list

What it means

Type check inside Converse-format validation: 'messages' must be a Python list. Passing a single message dict, a string, or any other type raises ValueError with this message.

Source

Thrown at litellm/llms/bedrock/count_tokens/transformation.py:267

        Args:
            request_data: The request payload

        Raises:
            ValueError: If the request is invalid
        """
        if not request_data.get("model"):
            raise ValueError("model parameter is required")

        input_type: Final = self._detect_input_type(request_data)

        if input_type == "converse":
            # Validate Converse format (messages-based)
            messages: Final = request_data.get("messages", [])
            if not messages:
                raise ValueError("messages parameter is required for Converse input")

            if not isinstance(messages, list):
                raise ValueError("messages must be a list")

            for i, message in enumerate(messages):
                if not isinstance(message, dict):
                    raise ValueError(f"Message {i} must be a dictionary")

                if "role" not in message:
                    raise ValueError(f"Message {i} must have a 'role' field")

                if "content" not in message:
                    raise ValueError(f"Message {i} must have a 'content' field")
        else:
            # For InvokeModel format, we need at least some content to count tokens
            # The content structure varies by model, so we do minimal validation
            if len(request_data) <= 1:  # Only has 'model' field
                raise ValueError("Request must contain content to count tokens")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Wrap a single message in a list: messages=[msg] not messages=msg
2. Add an assertion before the call: assert isinstance(req['messages'], list)

Example fix

# before
req = {'model': model, 'messages': {'role': 'user', 'content': [...]}}

# after
req = {'model': model, 'messages': [{'role': 'user', 'content': [...]}]}

if not isinstance(req.get("messages"), list):
    raise TypeError("messages must be a list of message dicts")

def is_message_list(v) -> bool:
    return isinstance(v, list) and all(isinstance(m, dict) for m in v)

When it happens

Trigger: Calling count tokens with messages being a single message object ({'role':...}) instead of a list of messages, or with a JSON-decoded payload where messages was serialized as something else.

Common situations: SDK wrappers that accept one message for convenience, or deserialization bugs that wrap/unwrap the array incorrectly.

Related errors

• Message {i} must be a dictionary
• model parameter is required
• messages parameter is required for Converse input
• Message {i} must have a 'role' field
• Message {i} must have a 'content' field

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/ed895d2b1800d680. Report an issue: GitHub.