openai/openai-python · error · ValueError

input must be provided when creating a new response

Error message

input must be provided when creating a new response

What it means

Raised by Responses.stream() when you pass new-response arguments (e.g. model) but omit `input`. A streaming response creation requires an input payload; without it the SDK cannot construct the create request, so it fails before any network call.

Source

Thrown at src/openai/resources/responses/responses.py:1222

            "text": text,
            "tool_choice": tool_choice,
            "top_logprobs": top_logprobs,
            "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,

View on GitHub (pinned to 9917c6e28e)

Solutions

1. Provide input: client.responses.stream(model=..., input="hello") or a list of input items
2. If you meant to continue a previous conversation, use response_id (continuation mode) instead of re-sending model
3. Ensure conditional input-building code always yields at least one item

Example fix

# before
stream = client.responses.stream(model="gpt-4o")
# after
stream = client.responses.stream(model="gpt-4o", input="Summarize this transcript...")

if input is None or (isinstance(input, list) and not input):
    if response_id is None:
        raise ValueError("input is required to create a new streamed response")

def has_stream_input(input) -> bool:
    return bool(input is not None) and (not isinstance(input, list) or len(input) > 0)

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

When it happens

Trigger: client.responses.stream(model="gpt-4o") with no input= argument (input defaults to NOT_GIVEN).

Common situations: Assuming a prompt from a previous turn persists (it does not — each create is stateless unless using previous_response_id), or building the input list conditionally and skipping it when empty.

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

• Cannot provide both response_id/starting_after can't be prov
• Didn't receive a `response.completed` event.
• Expected to have received `response.created` before `{event.
• Expected a non-empty value for `response_id` but received {r
• WebSocket connection closed with unsent messages

AI-assisted analysis of openai/openai-python@9917c6e28e (2026-08-28). Data as JSON: /api/errors/694b7df2d598561e. Report an issue: GitHub.