Responses

POST /v1/responses

Use the Responses API format for models like GPT-5 Pro and Codex that require it, or let Chuizi.AI auto-translate from Chat Completions.

Request

POST https://api.chuizi.ai/v1/responses

Authentication

Authorization: Bearer ck-your-api-key

Parameters

Parameter	Type	Required	Default	Description
`model`	string	Yes	—	Model name, e.g. `openai/gpt-5-pro`, `openai/codex-mini`
`input`	string/array	Yes	—	Input text or array of input items
`instructions`	string	No	—	System-level instructions (equivalent to system message)
`stream`	boolean	No	`false`	Enable SSE streaming output
`max_output_tokens`	integer	No	Model default	Maximum tokens in the response
`temperature`	number	No	Model default	Sampling temperature, 0-2
`tools`	array	No	—	Tool/function definitions
`text`	object	No	—	Text generation options including `format` for structured output
`reasoning`	object	No	—	Reasoning configuration, e.g. `{"effort": "high"}`

Request Example

config.json

json

{
  "model": "openai/codex-mini",
  "input": "Write a Python function that calculates the Fibonacci sequence.",
  "instructions": "You are an expert Python developer. Write clean, well-documented code.",
  "max_output_tokens": 2048,
  "reasoning": { "effort": "high" }
}

Response

config.json

json

{
  "id": "gen-xxxxxxxxxxxxxxxx",
  "object": "response",
  "created_at": 1712000000,
  "model": "openai/codex-mini",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "def fibonacci(n):\n    \"\"\"Calculate the nth Fibonacci number.\"\"\"\n    if n <= 1:\n        return n\n    a, b = 0, 1\n    for _ in range(2, n + 1):\n        a, b = b, a + b\n    return b"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 28,
    "output_tokens": 95,
    "total_tokens": 123
  },
  "x_chuizi": {
    "generation_id": "gen-xxxxxxxxxxxxxxxx",
    "latency_ms": 3500,
    "cost": "0.00180000"
  }
}

Code Examples

terminal

bash

curl -X POST https://api.chuizi.ai/v1/responses \
  -H "Authorization: Bearer ck-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/codex-mini",
    "input": "Write a Python Fibonacci function",
    "max_output_tokens": 2048
  }'

Next Steps

Chat Completions API — standard chat endpoint (auto-translates for Responses models)
Responses API Protocol — protocol details and compatibility notes
Choose a Model — compare Codex, GPT-5 Pro, and other models