# OpenAI Responses

OpenAI Responses

## Endpoint and authentication

`POST https://api.tu-zi.com/v1/responses`

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Body parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| model | string | Yes | Model name to call. Example: gpt-4.1-mini |
| input | string \| array | Yes | User input as plain text or a structured array. Example: 介绍一下这个模型 |
| stream | boolean | No | Whether to enable streaming responses. Form initial value (not an upstream default): false Example: false |
| temperature | number | No | Controls sampling randomness. Form initial value (not an upstream default): 0.7 Range in this definition: 0 ~ 2 Example: 0.7 |
| max_output_tokens | number | No | Maximum output token budget, potentially including internal reasoning. Allow sufficient budget to avoid truncation. Form initial value (not an upstream default): 512 Range in this definition: 1 ~ 128000 Example: 512 |
| top_p | number | No | Nucleus sampling probability threshold. Form initial value (not an upstream default): 1 Range in this definition: 0 ~ 1 Example: 1 |
| input[] | object | No | Array input items use type to distinguish messages and tool results. |
| tools | array | No | Tools supported by the model. |
| tool_choice | string \| object | No | Tool-selection policy when supported. |
| text | object | No | Text or structured-output configuration when supported. |

## Minimal request example

```json
{
  "model": "YOUR_MODEL",
  "input": "Hello"
}
```

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request POST 'https://api.tu-zi.com/v1/responses' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "YOUR_MODEL",
  "input": "Hello"
}'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/v1/responses"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"model\":\"YOUR_MODEL\",\"input\":\"Hello\"}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
// Node.js 20+
const url = "https://api.tu-zi.com/v1/responses";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "model": "YOUR_MODEL",
  "input": "Hello"
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| output[] | object | Output items; inspect type before parsing. |
| output[].content[].text | string | Text output. |
| usage | object | Request usage. |
| id | string | Response ID. |
| status | string | Response status; handle failed or incomplete responses. |
| error | object \| null | Error object on failure. |
| incomplete_details | object \| null | Reason for incomplete output. |
| output[].type | string | Distinguishes message, function_call and other output items. |
| usage.input_tokens | integer | Input token count. |
| usage.output_tokens | integer | Output token count. |
| usage.total_tokens | integer | Total token count. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "id": "resp_example",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "content": [
        {
          "type": "output_text",
          "text": "Hello"
        }
      ]
    }
  ]
}
```

## Streaming

With stream=true handle SSE event/type including response.output_text.delta, response.completed and error.

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-openai-response

Related protocol guide: https://api.tu-zi.com/docs/api/openai

This export contains documentation and examples only, without real credentials, account data or user requests.