BerriAI/litellm · error · ValueError

model is required

Error message

model is required

What it means

validate_input_kwargs on ResponsesToCompletionBridgeHandler raises this when the kwargs dict is missing 'model' or it is not a str. These kwargs are normally assembled internally by litellm's completion pipeline; a user only sees this error when invoking the bridge handler directly (it is an internal API) or when a fork/older pipeline fails to thread the model through.

Source

Thrown at litellm/completion_extras/litellm_responses_transformation/handler.py:110

        response_obj: Final = getattr(completed, "response", None) if completed else None
        if response_obj is None:
            raise ValueError("Stream ended without a completed response")

        hidden_params: Final = getattr(stream_iter, "_hidden_params", None)
        response: Final = self._coerce_response_object(response_obj, hidden_params)
        if not isinstance(response, ResponsesAPIResponse):
            raise ValueError("Stream completed response is invalid")
        return response

    def validate_input_kwargs(self, kwargs: dict) -> ResponsesToCompletionBridgeHandlerInputKwargs:
        from litellm import LiteLLMLoggingObj
        from litellm.types.utils import ModelResponse

        typed_kwargs: Final[dict[str, object]] = kwargs

        model: Final = typed_kwargs.get("model")
        if model is None or not isinstance(model, str):
            raise ValueError("model is required")

        custom_llm_provider: Final = typed_kwargs.get("custom_llm_provider")
        if custom_llm_provider is None or not isinstance(custom_llm_provider, str):
            raise ValueError("custom_llm_provider is required")

        messages: Final = typed_kwargs.get("messages")
        if messages is None or not isinstance(messages, list):
            raise ValueError("messages is required")

        optional_params: Final = typed_kwargs.get("optional_params")
        if optional_params is None or not isinstance(optional_params, dict):
            raise ValueError("optional_params is required")

        litellm_params: Final = typed_kwargs.get("litellm_params")
        if litellm_params is None or not isinstance(litellm_params, dict):
            raise ValueError("litellm_params is required")

        headers: Final = typed_kwargs.get("headers")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Call litellm.completion()/acompletion() instead of the bridge handler directly — it constructs all required kwargs for you
2. If calling directly, include model as a non-empty string in the kwargs dict
3. Check the ResponsesToCompletionBridgeHandlerInputKwargs TypedDict (handler.py:16) for the full required key set

Example fix

# before
handler = ResponsesToCompletionBridgeHandler()
result = await handler.acompletion({"messages": msgs, ...})  # no model

# after
result = await litellm.acompletion(model="openai/gpt-4o", messages=msgs)

def has_model_kwarg(kwargs: dict) -> bool:
    return isinstance(kwargs.get("model"), str) and bool(kwargs["model"])

def is_valid_bridge_kwargs(kwargs: dict) -> bool:
    return isinstance(kwargs.get("model"), str)

When it happens

Trigger: Instantiating ResponsesToCompletionBridgeHandler and calling its async_completion or validate_input_kwargs with a hand-built kwargs dict that omits 'model' or sets it to a non-string (e.g. None, int).

Common situations: Custom integrations or tests that call the bridge handler directly instead of litellm.completion; copy-pasted kwargs from an older litellm version whose pipeline keys changed.

Related errors

• custom_llm_provider is required
• messages is required
• optional_params is required
• litellm_params is required
• headers is required

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/005334db1c263946. Report an issue: GitHub.