BerriAI/litellm · error · ValueError

Bad Request: model is required for Anthropic Messages Reques

Error message

Bad Request: model is required for Anthropic Messages Request

What it means

Raised by LiteLLMAnthropicMessagesParamHandler when translating an Anthropic /v1/messages request body. The handler pops required kwargs and validates them before building an AnthropicMessagesRequest; 'model' is the first required field. This is a client-side 400-class validation error that fires before any provider call is made.

Source

Thrown at litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py:169

    ) -> tuple[ChatCompletionRequest | None, dict[str, str]]:
        """
        Translate Anthropic request params to OpenAI format, returning tool name mapping.

        This method handles truncation of tool names that exceed OpenAI's 64-character
        limit. The mapping allows restoring original names when translating responses.

        Returns:
            Tuple of (openai_request, tool_name_mapping)
            - tool_name_mapping maps truncated tool names back to original names
        """

        #########################################################
        # Validate required params
        #########################################################
        model: Final = kwargs.pop("model")
        messages: Final = kwargs.pop("messages")
        if not model:
            raise ValueError("Bad Request: model is required for Anthropic Messages Request")
        if not messages:
            raise ValueError("Bad Request: messages is required for Anthropic Messages Request")

        #########################################################
        # Created Typed Request Body
        #########################################################
        request_body: Final = AnthropicMessagesRequest(model=model, messages=messages, **kwargs)

        (
            translated_body,
            tool_name_mapping,
        ) = LiteLLMAnthropicMessagesAdapter().translate_anthropic_to_openai(anthropic_message_request=request_body)

        return translated_body, tool_name_mapping

    def translate_completion_output_params(
        self,
        response: ModelResponse,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Ensure the request body passed to the adapter contains a non-empty 'model' key matching the model to route to (e.g. 'claude-sonnet-4-5').
2. If you popped 'model' from kwargs earlier for routing decisions, pass it back in before calling the handler.
3. Check for typos in the key name ('model', not 'model_name' or 'modelId') in the request dict.
4. If using the pass-through endpoint, send the standard Anthropic Messages JSON body where 'model' is a top-level required field.

Example fix

// before
body = {"messages": [{"role": "user", "content": "hi"}], "max_tokens": 100}
openai_req, mapping = handler.translate_anthropic_request_body(**body)  # ValueError

// after
body = {"model": "claude-sonnet-4-5", "messages": [{"role": "user", "content": "hi"}], "max_tokens": 100}
openai_req, mapping = handler.translate_anthropic_request_body(**body)

def validate_anthropic_body(body: dict) -> None:
    if not body.get("model"):
        raise ValueError("request body must include a non-empty 'model' field")

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

try:
    result = handler.translate_anthropic_request_body(**body)
except ValueError as e:
    if "model is required" in str(e):
        return http_error(400, "model is required")
    raise

When it happens

Trigger: Calling the Anthropic experimental pass-through adapter (translate_anthropic_request_body / the params handler in transformation.py) with a kwargs dict that lacks a 'model' key or has model=None/empty string. Typical when a caller forwards a raw request body or constructs kwargs programmatically and forgets to inject the routed model name.

Common situations: Custom gateways that forward client JSON straight into the adapter without mapping the 'model' field; test fixtures that only set 'messages'; typos like 'model_name' instead of 'model'; code that pops 'model' earlier for routing and forgets to re-insert it.

Related errors

• Bad Request: messages is required for Anthropic Messages Req
• WebSearchInterception: missing follow-up messages
• Invalid first message. Should always start with 'role'='user
• Unable to parse anthropic tool result for message: {message}
• Unable to parse anthropic file message: {message}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/d2c1ef0b5f46b54a. Report an issue: GitHub.