Sign in

v1

latestOpenAPI 3.1.02026-07-224941145.6 KB

Create Response

Creates a model response for the given input using the Responses API.

post/v1/responses

Request body

model'gpt-5.6-terra' required

Model ID for the balanced GPT-5.6 Terra tier.

streamboolean

If true, stream partial response deltas using SSE.

temperaturenumber

Sampling temperature. Higher values make output more random.

frequency_penaltynumber

Penalizes repeated tokens based on their frequency in the text so far.

presence_penaltynumber

Penalizes tokens that have already appeared in the text.

max_output_tokensinteger

The maximum number of output tokens to generate.

stopstring

Sequences where the model will stop generating further tokens.

ninteger

How many response choices to generate.

toolsobject[]

A list of tools the model may call.

prompt_cache_optionsobject

Options for explicit prompt caching when supported.

tool_choicestring

Controls which (if any) tool is called by the model.

storeboolean

Whether to store the generated model response for later retrieval via API.

safety_identifierstring

Stable privacy-preserving identifier for the end user, used by safety systems.

userstring

A unique identifier representing your end-user.

Example request

{
  "model": "gpt-5.6-terra",
  "input": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "temperature": 1
}

Response

Response generated successfully

idstring required
objectstring required
created_atinteger required

Unix timestamp when the response was created.

completed_atinteger

Unix timestamp when the response was completed.

modelstring required
status'completed' | 'failed' | 'in_progress' | 'incomplete' required

Example response

{
  "id": "resp_0ed94fe7ec73cf560169afd97bba648194b8661d445cfa4244",
  "object": "response",
  "created_at": 1773132155,
  "completed_at": 1773132156,
  "model": "gpt-5.6-terra",
  "status": "completed",
  "output": [
    {
      "id": "msg_0ed94fe7ec73cf56",
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hi! How can I help you today?"
        }
      ]
    }
  ],
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "usage": {
    "input_tokens": 8,
    "output_tokens": 15,
    "total_tokens": 23
  }
}