Create a model response (Responses API)

GoModel API reference for POST /v1/responses: Create a model response (Responses API).

POST {base_url}/v1/responses

Error

A valid request URL is required to generate request examples

200

{
  "created_at": 123,
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "id": "<string>",
  "model": "<string>",
  "object": "<string>",
  "output": [
    {
      "arguments": "<string>",
      "call_id": "<string>",
      "content": [
        {
          "annotations": [
            {}
          ],
          "file_data": "<string>",
          "file_id": "<string>",
          "file_url": "<string>",
          "filename": "<string>",
          "image_url": {
            "detail": "<string>",
            "media_type": "<string>",
            "url": "<string>"
          },
          "input_audio": {
            "data": "<string>",
            "format": "<string>"
          },
          "text": "<string>",
          "type": "<string>"
        }
      ],
      "id": "<string>",
      "name": "<string>",
      "role": "<string>",
      "status": "<string>",
      "type": "<string>",
      "extra_content": {}
    }
  ],
  "previous_response_id": "<string>",
  "provider": "<string>",
  "status": "<string>",
  "usage": {
    "completion_tokens_details": {
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "input_tokens": 123,
    "output_tokens": 123,
    "prompt_tokens_details": {
      "audio_tokens": 123,
      "cached_tokens": 123,
      "image_tokens": 123,
      "text_tokens": 123
    },
    "raw_usage": {},
    "total_tokens": 123
  }
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Responses API request

context_management · any

conversation · string object

Conversation accepts either a conversation ID string or an object with id.

include · string[]

input · string object[]

string or []ResponsesInputElement — see docs for array form

instructions · string

max_output_tokens · integer

metadata · object

Show child attributes

model · string

parallel_tool_calls · boolean

previous_response_id · string

prompt · any

prompt_cache_retention · string

provider · string

Gateway routing hint; stripped before upstream execution.

reasoning · object

Show child attributes

safety_identifier · string

service_tier · string

store · boolean

stream · boolean

stream_options · object

Show child attributes

temperature · number

text · any

tool_choice · any

string or object

tools · object[]

Show child attributes

top_logprobs · integer

top_p · number

truncation · string

user · string

Response

200

application/json

JSON response or SSE stream when stream=true

created_at · integer

error · object

Show child attributes

id · string

model · string

object · string

"response"

output · object[]

Show child attributes

previous_response_id · string

PreviousResponseID names the response this one was chained from, as OpenAI echoes it; stored snapshots follow it to rebuild the history.

provider · string

status · string

"completed", "failed", "in_progress"

usage · object

Show child attributes