API 参考文档

接口概述

云智AI API 遵循 RESTful 设计原则，通过标准的 HTTP 请求进行交互，并返回 JSON 格式的数据，所有模型均采用官方镜像/Ollma/本地部署。您的请求都应发送至我们的付费端点进行中转

付费端点：

https://chat.jkyai.top/v1/chat/completions/

身份认证

所有对 API 的请求都需要通过 API 密钥进行认证。您需要在 HTTP 请求的 Authorization 头部中提供您的密钥。

密钥格式为 Bearer YOUR_API_KEY，请将 YOUR_API_KEY 替换为您在控制台获取的密钥。

Authorization: Bearer sk-512e722ec9abba0bf9bb8b8ed606603749a0b9bdcb27973a

注意: 请妥善保管您的API密钥，不要在客户端代码或公开仓库中泄露。所有通过您密钥发起的请求都将被计费!

请求格式

聊天补全接口（Chat Completions）是我们的核心接口。您需要向该接口发送一个 POST 请求，请求体为 JSON 格式。

• 方法: POST
• 地址: https://chat.jkyai.top/v1/chat/completions/
• 头部:
  • Content-Type: application/json
  • Authorization: Bearer YOUR_API_KEY

参数说明

请求参数

返回参数 (非流式)

{
  "id": "chatcmpl-xxxxxxxxxxxx",
  "object": "chat.completion",
  "created": 1721369688,
  "model": "gpt-4o-mini-2024-07-18",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！有什么可以帮助你的吗？"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  }
}

返回参数 (流式)

当 stream: true 时，您会收到一系列事件。每个事件都是一个 JSON 对象，最后一个事件为 [DONE]。

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1721369700,"model":"gpt-4o-mini-2024-07-18","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1721369700,"model":"gpt-4o-mini-2024-07-18","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1721369700,"model":"gpt-4o-mini-2024-07-18","choices":[{"index":0,"delta":{"content":"好！"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1721369700,"model":"gpt-4o-mini-2024-07-18","choices":[{"index":0,"delta":{},"finish_reason":"stop","usage":{"prompt_tokens":10,"completion_tokens":12,"total_tokens":22}}]}

data: [DONE]

错误码

如果请求失败，API会返回一个标准的HTTP错误码和一个包含详细信息的JSON对象。

代码示例

下面是在不同编程语言中调用聊天补全API的示例。请记得将 YOUR_API_KEY 替换为您的真实密钥。

cURL

curl https://chat.jkyai.top/v1/chat/completions/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o-mini-2024-07-18",
    "messages": [
      {
        "role": "system",
        "content": "你是一个乐于助人的AI助手。"
      },
      {
        "role": "user",
        "content": "你好，请做个自我介绍。"
      }
    ]
  }'

Python

import requests
import json

api_key = "YOUR_API_KEY"
url = "https://chat.jkyai.top/v1/chat/completions/"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {api_key}"
}

data = {
    "model": "gpt-4o-mini-2024-07-18",
    "messages": [
        {"role": "system", "content": "你是一个乐于助人的AI助手。"},
        {"role": "user", "content": "你好，请做个自我介绍。"}
    ],
    "stream": False # 设置为True以使用流式传输
}

response = requests.post(url, headers=headers, data=json.dumps(data))

if response.status_code == 200:
    print(response.json())
else:
    print(f"请求失败，状态码: {response.status_code}")
    print(response.text)

Node.js (axios)

const axios = require('axios');

const apiKey = 'YOUR_API_KEY';
const url = 'https://chat.jkyai.top/v1/chat/completions/';

const headers = {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${apiKey}`
};

const data = {
    model: 'gpt-4o-mini-2024-07-18',
    messages: [
        { role: 'system', content: '你是一个乐于助人的AI助手。' },
        { role: 'user', content: '你好，请做个自我介绍。' }
    ]
};

axios.post(url, data, { headers })
    .then(response => {
        console.log(response.data);
    })
    .catch(error => {
        console.error('请求出错:', error.response ? error.response.data : error.message);
    });

PHP (cURL)

<?php

$apiKey = 'YOUR_API_KEY';
$url = 'https://chat.jkyai.top/v1/chat/completions/';

$headers = [
    'Content-Type: application/json',
    'Authorization: Bearer ' . $apiKey
];

$data = [
    'model' => 'gpt-4o-mini-2024-07-18',
    'messages' => [
        ['role' => 'system', 'content' => '你是一个乐于助人的AI助手。'],
        ['role' => 'user', 'content' => '你好，请做个自我介绍。']
    ]
];

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
curl_close($ch);

if ($http_code == 200) {
    echo $response;
} else {
    echo "请求失败，HTTP状态码: " . $http_code . "\n";
    echo "响应内容: " . $response;
}

?>

计费标准

我们采用基于Token用量的统一定价模式，无论您选择哪款语言大模型，计费标准都保持一致，让您可以专注于业务创新，无需担心复杂的定价策略【兼容OpenAI格式，您可以通过请求日志查看相关费用】