Generate with Responses

POST /v1/responses

OpenAI Responses-compatible generation. Send model and input, which can be a string or supported structured input items. Read generated text from message content inside output[] rather than a universal top-level text field, and inspect item types instead of assuming output[0] is text. Adding stream: true returns SSE, typically response.output_text.delta and response.completed. Each endpoint requires a model whose supported_endpoints includes that exact path. These APIs forward the selected model's protocol, so optional parameters and response details can vary by local worker or remote provider. Local models keep inputs on the device; a configured remote model receives the request sent to it.

Guide and examplesLanguage and vision·All endpoints

Request body

application/jsonRequired

Responses

{
  "id": "resp_example",
  "object": "response",
  "status": "completed",
  "model": "Qwen/Qwen3.5-4B",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hello!"
        }
      ]
    }
  ]
}