Create Response

Create an OpenAI Responses-compatible completion through a workspace-billed provider.

Non-streaming requests have a maximum provider read time of 240 seconds. Use stream: true for work expected to take longer. The limit is an upper bound, not a guarantee that a response arriving exactly at the boundary can complete.

curl -X POST "https://loading/v1/llm/openai/v1/responses"

null

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}