Skip to main content
POST
{base_url}
/
v1
/
responses
Error
A valid request URL is required to generate request examples
{
  "created_at": 123,
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "id": "<string>",
  "model": "<string>",
  "object": "<string>",
  "output": [
    {
      "arguments": "<string>",
      "call_id": "<string>",
      "content": [
        {
          "annotations": [
            {}
          ],
          "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>"
    }
  ],
  "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

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

​
include
string[]
​
input

string or []ResponsesInputElement — see docs for array form

​
instructions
string
​
max_output_tokens
integer
​
metadata
object
​
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
​
safety_identifier
string
​
service_tier
string
​
store
boolean
​
stream
boolean
​
stream_options
object
​
temperature
number
​
text
any
​
tool_choice
any

string or object

​
tools
object[]
​
top_logprobs
integer
​
top_p
number
​
truncation
string
​
user
string

Response

JSON response or SSE stream when stream=true

​
created_at
integer
​
error
object
​
id
string
​
model
string
​
object
string

"response"

​
output
object[]
​
provider
string
​
status
string

"completed", "failed", "in_progress"

​
usage
object