openai/openai-python · error · ValueError

model must be provided when creating a new response

Error message

model must be provided when creating a new response

What it means

Raised by Responses.stream() when you pass any 'new response' argument (e.g. input is implied by other create args) but omit the required `model` parameter. The Responses API requires a model identifier whenever a new response is being created via the streaming helper. The SDK validates this client-side before making any network request.

Source

Thrown at src/openai/resources/responses/responses.py:1225

            "top_p": top_p,
            "truncation": truncation,
            "user": user,
            "background": background,
        }
        new_response_args_names = [k for k, v in new_response_args.items() if is_given(v)]

        if (is_given(response_id) or is_given(starting_after)) and len(new_response_args_names) > 0:
            raise ValueError(
                "Cannot provide both response_id/starting_after can't be provided together with "
                + ", ".join(new_response_args_names)
            )
        tools = _make_tools(tools)
        if len(new_response_args_names) > 0:
            if not is_given(input):
                raise ValueError("input must be provided when creating a new response")

            if not is_given(model):
                raise ValueError("model must be provided when creating a new response")

            if is_given(text_format):
                if not text:
                    text = {}

                if "format" in text:
                    raise TypeError("Cannot mix and match text.format with text_format")

                text = copy(text)
                text["format"] = _type_to_text_format_param(text_format)

            api_request: partial[Stream[ResponseStreamEvent]] = partial(
                self.create,
                input=input,
                model=model,
                tools=tools,
                context_management=context_management,
                conversation=conversation,

View on GitHub (pinned to 9917c6e28e)

Solutions

1. Pass a valid model, e.g. client.responses.stream(model='gpt-4o', input='hello')
2. If you meant to stream an existing response, pass response_id='resp_...' instead of create arguments
3. Ensure model isn't None or NOT_GIVEN due to an env/config lookup (e.g. os.environ.get('OPENAI_MODEL') returning None)

Example fix

// before
stream = client.responses.stream(input="hello")
// after
stream = client.responses.stream(model="gpt-4o", input="hello")

from openai._utils import is_given
if not is_given(model) or not model:
    raise ValueError('model is required to stream a new response')
stream = client.responses.stream(model=model, input='hello')

def has_model(kwargs: dict) -> bool:
    m = kwargs.get('model')
    return isinstance(m, str) and bool(m.strip())

try:
    stream = client.responses.stream(model=model, input='hi')
except ValueError as e:
    if 'model must be provided' in str(e):
        model = model or DEFAULT_MODEL
        stream = client.responses.stream(model=model, input='hi')
    else:
        raise

When it happens

Trigger: Calling client.responses.stream(input=...) or passing any create-only argument without model=..., e.g. client.responses.stream(input='hi', max_output_tokens=100) with no model. Only fires when len(new_response_args_names) > 0, i.e. at least one create argument was given.

Common situations: Migrating code from client.responses.create(stream=True) and forgetting to carry the model kwarg; refactoring where model was previously read from a config variable that is now None/NotGiven; copy-pasting a stream example that omits model.

Understand the failure class

Background: Missing required parameter errors: what 'X is required' and 'the required X param is missing' mean, and how to fix them — this error's family across 27 libraries.

Related errors

• id must be provided when streaming an existing response
• response_id must be provided when streaming an existing resp
• Expected a non-empty value for `response_id` but received {r
• Expected a non-empty value for `response_id` but received {r
• Cannot mix and match text.format with text_format

AI-assisted analysis of openai/openai-python@9917c6e28e (2026-08-28). Data as JSON: /api/errors/77eb4ae0722b51b3. Report an issue: GitHub.