BerriAI/litellm · error · ValueError

model parameter is required

Error message

model parameter is required

What it means

Validation in the Bedrock CountTokens transformation: the request payload must include a 'model' field before the request can be transformed and sent. Both Converse-style and InvokeModel-style inputs require it, since the model is embedded in the AWS endpoint path.

Source

Thrown at litellm/llms/bedrock/count_tokens/transformation.py:256

        }
        """
        input_tokens: Final = bedrock_response.get("inputTokens", 0)

        return {"input_tokens": input_tokens}

    def validate_count_tokens_request(self, request_data: dict[str, Any]) -> None:
        """
        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")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Include a non-empty 'model' in the request_data sent to count tokens
2. Default it from your routing config before calling LiteLLM: request_data.setdefault('model', model)

Example fix

# before
resp = await handler.count_tokens({'messages': msgs}, ...)

# after
resp = await handler.count_tokens({'model': 'anthropic.claude-3-5-sonnet-20240620-v1:0', 'messages': msgs}, ...)

def validate_count_tokens_request(req: dict) -> None:
    if not req.get("model"):
        raise ValueError("model parameter is required")

def has_model(req: dict) -> bool:
    return isinstance(req, dict) and isinstance(req.get("model"), str) and bool(req["model"].strip())

When it happens

Trigger: Calling count tokens with a payload containing only messages/inputText but no 'model' key, or model set to an empty string / None (falsy values are rejected).

Common situations: Building the request dict dynamically and skipping model when it was passed as a separate argument, or a client that assumes the proxy infers the model from config.

Related errors

• messages parameter is required for Converse input
• 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/bdea424ccc358275. Report an issue: GitHub.