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. OpenAI-compatible, so existing Responses API code runs unmodified.
Request
This endpoint expects an object.
modelstringRequired
The ASI:One model to use.
inputstring or list of objectsRequired
Text, or a list of input items, to generate a response for. Input item content parts are text; an image part is rejected with a 400. Send images to /v1/chat/completions as an image_url content part.
instructionsstringOptional
System/developer instructions inserted ahead of the input.
streambooleanOptionalDefaults to false
If true, response events are streamed as server-sent events.
backgroundbooleanOptionalDefaults to false
If true, run the response as a background task; poll it with the retrieve endpoint or stop it with cancel.
storebooleanOptionalDefaults to true
Whether to persist the response so it can be retrieved by id.
previous_response_idstringOptional
The id of a previous response to continue from.
max_output_tokensintegerOptional>=1
Upper bound on tokens generated for the response.
temperaturedoubleOptional0-2
Sampling temperature.
top_pdoubleOptional0-1
Nucleus sampling probability mass.
toolslist of objectsOptional
A list of tools the model may call, in either the flat Responses shape or the nested Chat Completions shape. See the Tool Calling guide.
tool_choiceenum or map from strings to anyOptional
Controls which (if any) tool is called.
parallel_tool_callsbooleanOptional
Whether the model may call several tools in one turn.
textobjectOptional
Output format configuration. text.format takes precedence over response_format.
reasoningobjectOptional
Reasoning configuration. See the Reasoning guide.
enable_thinkingbooleanOptional
ASI:One extension. Whether the model reasons before answering. Used when reasoning.effort is absent.
thinking_budgetintegerOptional0-16384
ASI:One extension. Maximum tokens the model may spend reasoning.
metadatamap from strings to stringsOptional
Up to 16 key-value string pairs attached to the response.
Response
A response object, or an SSE stream of response events when stream is true.
statusenum
Lifecycle status. queued and in_progress mean the run is still going; completed, failed, cancelled and incomplete are terminal.
usageobject
Token usage for the response.
