BerriAI/litellm · error · ValueError

model_response is required

Error message

model_response is required

What it means

validate_input_kwargs raises when 'model_response' is missing or is not a litellm ModelResponse instance. The bridge fills this pre-allocated ModelResponse in place with choices/usage from the Responses API output. Normal completion calls create it in the main pipeline; only manual handler invocations can omit or mistype it.

Source

Thrown at litellm/completion_extras/litellm_responses_transformation/handler.py:134

        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")
        if headers is None or not isinstance(headers, dict):
            raise ValueError("headers is required")

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

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

        return ResponsesToCompletionBridgeHandlerInputKwargs(
            model=model,
            messages=messages,
            optional_params=optional_params,
            litellm_params=litellm_params,
            headers=headers,
            model_response=model_response,
            logging_obj=logging_obj,
            custom_llm_provider=custom_llm_provider,
            encoding=typed_kwargs.get("encoding"),
        )

    def completion(

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Use litellm.completion — the ModelResponse is created and threaded internally
2. If direct, build it: from litellm.types.utils import ModelResponse; kwargs['model_response'] = ModelResponse()
3. In tests, ensure mocks use ModelResponse instances or patch at the transport layer instead

Example fix

# before
kwargs = {..., "model_response": {"choices": []}}

# after
from litellm.types.utils import ModelResponse
kwargs = {..., "model_response": ModelResponse()}

from litellm.types.utils import ModelResponse

def has_valid_model_response(kwargs: dict) -> bool:
    return isinstance(kwargs.get("model_response"), ModelResponse)

from litellm.types.utils import ModelResponse

def is_model_response(v) -> bool:
    return isinstance(v, ModelResponse)

When it happens

Trigger: Passing model_response=None, a dict, or omitting the key when calling the bridge handler directly.

Common situations: Custom code that constructs a plain dict instead of litellm.types.utils.ModelResponse; tests with mock objects that fail the isinstance check.

Related errors

• model is required
• custom_llm_provider is required
• messages is required
• optional_params is required
• litellm_params is required

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/6c18c70d78c3dcf1. Report an issue: GitHub.