Create a model response

POST

/responses

The Responses API is available for supported OpenAI, Anthropic, and Google Gemini models. It
supports text input, input item arrays, function tools, web search tools, streaming, and OpenAI
text format options. With stream: true events are sent as server-sent events. Responses
streaming does not currently attach a debug object to its events.

Request

Header Params

Body Params application/jsonRequired

Example

{
    "model": "openai/gpt-5.1-codex-mini",
    "input": "Hello!"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/responses' \
--header 'x-opengateway-user-id;' \
--header 'x-opengateway-session-id;' \
--header 'x-sionic-task-id;' \
--header 'Content-Type: application/json' \
--data '{
    "model": "openai/gpt-5.1-codex-mini",
    "input": "Hello!"
}'

Responses

🟢200OK

application/json

A response object, or an SSE event stream when stream is true.

Headers

Body

Example

{
    "id": "resp_abc123",
    "object": "response",
    "created_at": 1734567890,
    "model": "openai/gpt-5.1-codex-mini",
    "status": "completed",
    "output": [
        {
            "type": "message",
            "id": "msg_abc123",
            "status": "completed",
            "role": "assistant",
            "content": [
                {
                    "type": "output_text",
                    "text": "Hello! How can I help you today?"
                }
            ]
        }
    ],
    "usage": {
        "input_tokens": 20,
        "output_tokens": 10,
        "total_tokens": 30,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens_details": {
            "reasoning_tokens": 0
        }
    }
}

🟠400Bad Request

🟠401Unauthorized

🟠402

🟠429

🔴500Server Error

🔴503Service Unavailable

🔴529

Modified at 2026-10-27 15:03:30

Create chat completion

Create a message (Anthropic Messages format)