Responses Format

Create a model response using the official OpenAI Responses API format.

This endpoint only supports models that officially support the OpenAI Responses API. Do not use Claude, DeepSeek, or other models that only support Chat Completions or Messages format on this endpoint.

Try It

POST/v1/responseshttps://api-platform.ope.ai

Authentication

Use Bearer token authentication.

• Header: Authorization: Bearer <api-key>
• Example: Authorization: Bearer sk-xxxxxx

Request Body（application/json）

Field	Type	Required	Description
model	string	Yes	Model ID
input	string | array	Yes	Input content; pass a string or an official Responses input item array
instructions	string	No	System or developer instructions inserted into the model context
max_output_tokens	integer	No	Maximum tokens the response can generate
previous_response_id	string	No	Previous response ID for continuing context
stream	boolean	No	Whether to use SSE streaming
temperature	number	No	Sampling temperature
top_p	number	No	Nucleus sampling parameter
tools	array	No	Official Responses tools array
tool_choice	string | object	No	Tool selection strategy
parallel_tool_calls	boolean	No	Whether to allow parallel tool calls
reasoning	object	No	Reasoning model options, such as effort and summary
text	object	No	Text output configuration
truncation	string	No	Context truncation strategy
metadata	object	No	Metadata
include	array	No	Official extra fields to include in the response
store	boolean	No	Whether to store the response
user	string	No	End-user identifier
max_tool_calls	integer	No	Maximum total tool calls for this response

Request Examples

cURL

curl -X POST "https://api-platform.ope.ai/v1/responses" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "input": "Introduce OPEAI Platform in one sentence."
  }'

JavaScript

const res = await fetch("https://api-platform.ope.ai/v1/responses", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.OPEAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-5",
    input: "Introduce OPEAI Platform in one sentence.",
  }),
});

console.log(await res.json());

Python

import os
import requests

resp = requests.post(
    "https://api-platform.ope.ai/v1/responses",
    headers={"Authorization": f"Bearer {os.environ['OPEAI_API_KEY']}"},
    json={
        "model": "gpt-5",
        "input": "Introduce OPEAI Platform in one sentence.",
    },
    timeout=60,
)

print(resp.json())

Input Array Example

{
  "model": "gpt-5",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Introduce OPEAI Platform in one sentence."
        }
      ]
    }
  ]
}

Response Example

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1762499410,
  "status": "completed",
  "model": "gpt-5",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "OPEAI Platform is a unified API platform for accessing multiple AI model capabilities.",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 18,
    "output_tokens": 22,
    "total_tokens": 40
  }
}

Official reference: OpenAI Responses API