BerriAI/litellm · error · ValueError

Message {i} must be a dictionary

Error message

Message {i} must be a dictionary

What it means

Per-message structural validation for Converse-style count-tokens input: every element of 'messages' must be a dict. A string, tuple, or None element at index i raises ValueError naming the offending index.

Source

Thrown at litellm/llms/bedrock/count_tokens/transformation.py:271

            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. Convert every turn to {'role': ..., 'content': ...} dicts
2. Sanitize: messages = [m if isinstance(m, dict) else {'role': 'user', 'content': [{'text': str(m)}]} for m in messages]

Example fix

# before
req = {'model': m, 'messages': ['hello', 'hi']}

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

for i, m in enumerate(req.get("messages", [])):
    if not isinstance(m, dict):
        raise TypeError(f"Message {i} must be a dictionary")

def is_valid_message(m) -> bool:
    return isinstance(m, dict) and isinstance(m.get("role"), str) and ("content" in m)

When it happens

Trigger: messages = ['hello world', ...] where plain strings were passed instead of message objects, or mixed lists where one element is a content block rather than a message.

Common situations: Porting code from chat APIs that accept plain-string turns, or array spreads that accidentally inline content blocks.

Related errors

• messages must be a list
• 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/34736f53a762b65d. Report an issue: GitHub.