Create a response
Creates a model response using the Responses API. Supports streaming (stream: true, server-sent events) and background mode (background: true). When streaming, each frame carries a named event: and a JSON data: payload, and the stream ends on a terminal event, one of response.completed, response.failed or response.incomplete; there is no [DONE] sentinel. If the run stalls, the stream can instead end on a data: line holding an error object. Lines starting with : are keep-alive comments. OpenAI-compatible, so existing Responses API code runs unmodified. Unrecognized fields are rejected with a 400 (unknown_parameter).
Authentication
Your ASI:One API key, sent as Authorization: Bearer <api_key>.
Request
The ASI:One model to use.
Text, or a list of input items, to generate a response for. Content parts are input_text, output_text and input_image. An input_image takes an image_url as a data: base64 URI or an https URL from a supported host (file_id is not supported), and a message takes up to 10 images.
System/developer instructions inserted ahead of the input.
If true, response events are streamed as server-sent events.
If true, run the response as a background task; poll it with the retrieve endpoint or stop it with cancel. Requires store: true.
Whether to persist the response so it can be retrieved by id. With false, the retrieve, cancel, delete and input items endpoints return a 404 for it.
A list of tools the model may call. Function tools can use the flat Responses shape or the nested Chat Completions shape, and can be grouped in a namespace. A web_search tool lets the model search the web. Other tool types are rejected with a 400. See the Tool Calling guide.
Controls which (if any) tool is called.
Output format configuration. text.format takes precedence over response_format.
ASI:One extension. Turns reasoning on or off on asi1-mini. The other models always reason; there an explicit false selects the shallowest depth. Used when reasoning.effort is absent. See the Reasoning guide.
ASI:One extension. The older way to size reasoning. On asi1 and asi1-ultra the value selects a depth rather than capping tokens. See the Reasoning guide.
Up to 16 key-value string pairs attached to the response.
Response headers
Correlation id for this request, present on every response: the caller-supplied X-Request-Id when one was sent, otherwise minted by the API. Backends log it and traces key on it, so cite it when reporting an issue.
Response
A response object, or an SSE stream of response events when stream is true.
Lifecycle status. queued and in_progress mean the run is still going; completed, failed, cancelled and incomplete are terminal.