BerriAI/litellm · error · ValueError

messages parameter is required for Converse input

Error message

messages parameter is required for Converse input

What it means

When the CountTokens request is detected as Converse-format (messages-based), the 'messages' array must be present and non-empty. An absent, empty, or falsy messages value raises this ValueError before any AWS call.

Source

Thrown at litellm/llms/bedrock/count_tokens/transformation.py:264

        Validate the incoming count tokens request.
        Supports both Converse and InvokeModel input formats.

        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. Include at least one message: [{'role': 'user', 'content': [{'text': '...'}]}]
2. If you meant InvokeModel-style input, use its native fields (e.g. inputText/prompt) so detection picks the right branch

Example fix

# before
req = {'model': model}

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

def has_converse_messages(req: dict) -> bool:
    return isinstance(req.get("messages"), list) and len(req["messages"]) > 0

When it happens

Trigger: Sending {'model': m} plus Converse markers (or no InvokeModel-style fields) without messages; sending messages: [] or omitting it entirely after input-shape detection classifies the request as Converse.

Common situations: Clients that send generic requests with only model + system prompt, or code paths that strip empty message arrays as a 'cleanup' step before calling count tokens.

Related errors

• model parameter is required
• messages must be a list
• Message {i} must be a dictionary
• 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/fba3f3b32dc74384. Report an issue: GitHub.