Responses

Create a response

post

Creates a streaming or non-streaming response using OpenResponses API format

Authorizations

apiKey

AuthorizationstringRequired

API key as bearer token in Authorization header

Body

application/json

Request schema for Responses endpoint

inputany ofOptional

Input for a response request - can be a string or array of items

Example: [{"role":"user","content":"What is the weather today?"}]

stringOptional

or

instructionsstring · nullableOptional

tool_choiceany ofOptional

string · enumOptionalPossible values:

or

string · enumOptionalPossible values:

or

string · enumOptionalPossible values:

or

or

parallel_tool_callsboolean · nullableOptional

modelstringOptional

modelsstring[]Optional

max_output_tokensnumber · nullableOptional

temperaturenumber · max: 2 · nullableOptional

top_pnumber · nullableOptional

top_logprobsinteger · max: 20 · nullableOptional

max_tool_callsinteger · nullableOptional

presence_penaltynumber · min: -2 · max: 2 · nullableOptional

frequency_penaltynumber · min: -2 · max: 2 · nullableOptional

top_knumberOptional

prompt_cache_keystring · nullableOptional

previous_response_idstring · nullableOptional

backgroundboolean · nullableOptional

safety_identifierstring · nullableOptional

storebooleanOptionalDefault: false

service_tierstring · enumOptionalDefault: autoPossible values:

truncationall ofOptional

string · enum · nullableOptionalPossible values:

and

anyOptionalExample: auto

streambooleanOptionalDefault: false

routestring · enum · nullableOptionalDeprecated

DEPRECATED Use providers.sort.partition instead. Backwards-compatible alias for providers.sort.partition. Accepts legacy values: "fallback" (maps to "model"), "sort" (maps to "none").

Possible values:

userstring · max: 128Optional

A unique identifier representing your end-user, which helps distinguish between different users of your app. This allows your app to identify specific users in case of abuse reports, preventing your entire app from being affected by the actions of individual users. Maximum of 128 characters.

session_idstring · max: 128Optional

A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 128 characters.

Responses

200

Successful response

application/jsontext/event-stream

400

Bad Request - Invalid request parameters or malformed input

application/json

401

Unauthorized - Authentication required or invalid credentials

application/json

402

Payment Required - Insufficient credits or quota to complete request

application/json

404

Not Found - Resource does not exist

application/json

408

Request Timeout - Operation exceeded time limit

application/json

413

Payload Too Large - Request payload exceeds size limits

application/json

422

Unprocessable Entity - Semantic validation failure

application/json

429

Too Many Requests - Rate limit exceeded

application/json

500

Internal Server Error - Unexpected server error

application/json

502

Bad Gateway - Provider/upstream API failure

application/json

503

Service Unavailable - Service temporarily unavailable

application/json

524

Infrastructure Timeout - Request timed out at our edge network

application/json

529

Provider Overloaded - Provider is temporarily overloaded

application/json

post

/responses

HTTPcURLJavaScriptPython

POST /api/v1/responses HTTP/1.1
Host: app.interactive.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 347

{
  "model": "anthropic/claude-4.5-sonnet-20250929",
  "input": [
    {
      "type": "message",
      "content": "Hello, how are you?",
      "role": "user"
    }
  ],
  "temperature": 0.7,
  "top_p": 0.9,
  "tools": [
    {
      "type": "function",
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string"
          }
        }
      }
    }
  ]
}

{
  "id": "resp-abc123",
  "object": "response",
  "created_at": 1704067200,
  "model": "gpt-4",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "id": "msg-abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you today?",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 10,
    "output_tokens": 25,
    "total_tokens": 35,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "tools": [],
  "tool_choice": "auto",
  "parallel_tool_calls": true,
  "error": null,
  "incomplete_details": null,
  "temperature": null,
  "top_p": null,
  "max_output_tokens": null,
  "metadata": null,
  "instructions": null
}