51API

主题

Node.js 调用示例 ​

本页面提供 Node.js 调用 51API 的完整示例。

环境准备 ​

安装依赖 ​

bash
npm install openai
bash
yarn add openai
bash
pnpm add openai

配置 API Key ​

推荐使用环境变量存储 API Key：

bash
export NEWAPI_API_KEY="sk-你的密钥"
bash
set NEWAPI_API_KEY=sk-你的密钥
powershell
$env:NEWAPI_API_KEY="sk-你的密钥"

方式一：使用 OpenAI SDK（推荐） ​

基础对话 ​

javascript
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

async function chat() {
    const response = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: [
            { role: 'system', content: '你是一个有帮助的助手。' },
            { role: 'user', content: '你好！' }
        ]
    });

    console.log(response.choices[0].message.content);
}

chat();
javascript
const OpenAI = require('openai');

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

async function chat() {
    const response = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: [
            { role: 'system', content: '你是一个有帮助的助手。' },
            { role: 'user', content: '你好！' }
        ]
    });

    console.log(response.choices[0].message.content);
}

chat();

流式输出 ​

javascript
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

async function streamChat() {
    const stream = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: [{ role: 'user', content: '讲一个简短的故事' }],
        stream: true
    });

    process.stdout.write('AI: ');
    for await (const chunk of stream) {
        const content = chunk.choices[0]?.delta?.content || '';
        process.stdout.write(content);
    }
    console.log(); // 换行
}

streamChat();

多轮对话 ​

javascript
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

// 保存对话历史
const messages = [
    { role: 'system', content: '你是一个友好的助手。' }
];

async function chat(userInput) {
    // 添加用户消息
    messages.push({ role: 'user', content: userInput });

    // 发送请求
    const response = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: messages
    });

    // 获取回复
    const reply = response.choices[0].message.content;

    // 保存到历史
    messages.push({ role: 'assistant', content: reply });

    return reply;
}

// 多轮对话示例
async function main() {
    console.log('AI:', await chat('我叫小明'));
    console.log('AI:', await chat('我刚才说我叫什么？'));
}

main();

方式二：使用 fetch API ​

适合不想安装额外依赖的场景。

基础请求 ​

javascript
const API_KEY = process.env.NEWAPI_API_KEY;
const API_URL = 'https://www.51api.org/v1/chat/completions';

async function chat(message) {
    const response = await fetch(API_URL, {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
            'Authorization': `Bearer ${API_KEY}`
        },
        body: JSON.stringify({
            model: 'gpt-4o',
            messages: [{ role: 'user', content: message }]
        })
    });

    if (!response.ok) {
        throw new Error(`HTTP error! status: ${response.status}`);
    }

    const data = await response.json();
    return data.choices[0].message.content;
}

// 使用示例
chat('你好！').then(console.log).catch(console.error);

流式请求 ​

javascript
const API_KEY = process.env.NEWAPI_API_KEY;
const API_URL = 'https://www.51api.org/v1/chat/completions';

async function streamChat(message) {
    const response = await fetch(API_URL, {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
            'Authorization': `Bearer ${API_KEY}`
        },
        body: JSON.stringify({
            model: 'gpt-4o',
            messages: [{ role: 'user', content: message }],
            stream: true
        })
    });

    if (!response.ok) {
        throw new Error(`HTTP error! status: ${response.status}`);
    }

    const reader = response.body.getReader();
    const decoder = new TextDecoder();

    process.stdout.write('AI: ');

    while (true) {
        const { done, value } = await reader.read();
        if (done) break;

        const chunk = decoder.decode(value);
        const lines = chunk.split('\n');

        for (const line of lines) {
            if (line.startsWith('data:')) {
                const data = line.slice(5).trim();
                if (data === '[DONE]') break;

                try {
                    const json = JSON.parse(data);
                    const content = json.choices[0]?.delta?.content || '';
                    process.stdout.write(content);
                } catch (e) {
                    // 忽略解析错误
                }
            }
        }
    }

    console.log(); // 换行
}

streamChat('讲个笑话');

方式三：使用 axios ​

javascript
import axios from 'axios';

const API_KEY = process.env.NEWAPI_API_KEY;
const API_URL = 'https://www.51api.org/v1/chat/completions';

async function chat(message) {
    const response = await axios.post(API_URL, {
        model: 'gpt-4o',
        messages: [{ role: 'user', content: message }]
    }, {
        headers: {
            'Content-Type': 'application/json',
            'Authorization': `Bearer ${API_KEY}`
        }
    });

    return response.data.choices[0].message.content;
}

// 使用示例
chat('你好！').then(console.log).catch(console.error);

高级示例：Express API 服务 ​

创建一个简单的 API 服务，转发请求到 51API。

javascript
import express from 'express';
import OpenAI from 'openai';

const app = express();
app.use(express.json());

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

// 普通对话接口
app.post('/api/chat', async (req, res) => {
    try {
        const { message, model = 'gpt-4o' } = req.body;

        const response = await client.chat.completions.create({
            model,
            messages: [{ role: 'user', content: message }]
        });

        res.json({
            success: true,
            reply: response.choices[0].message.content,
            usage: response.usage
        });
    } catch (error) {
        res.status(500).json({
            success: false,
            error: error.message
        });
    }
});

// 流式对话接口
app.post('/api/chat/stream', async (req, res) => {
    try {
        const { message, model = 'gpt-4o' } = req.body;

        res.setHeader('Content-Type', 'text/event-stream');
        res.setHeader('Cache-Control', 'no-cache');
        res.setHeader('Connection', 'keep-alive');

        const stream = await client.chat.completions.create({
            model,
            messages: [{ role: 'user', content: message }],
            stream: true
        });

        for await (const chunk of stream) {
            const content = chunk.choices[0]?.delta?.content || '';
            if (content) {
                res.write(`data: ${JSON.stringify({ content })}\n\n`);
            }
        }

        res.write('data: [DONE]\n\n');
        res.end();
    } catch (error) {
        res.status(500).json({
            success: false,
            error: error.message
        });
    }
});

const PORT = process.env.PORT || 3000;
app.listen(PORT, () => {
    console.log(`Server running on port ${PORT}`);
});

图片分析示例 ​

javascript
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

async function analyzeImage(imageUrl) {
    const response = await client.chat.completions.create({
        model: 'gpt-4o',
        messages: [
            {
                role: 'user',
                content: [
                    { type: 'text', text: '这张图片里有什么？' },
                    {
                        type: 'image_url',
                        image_url: { url: imageUrl }
                    }
                ]
            }
        ],
        max_tokens: 300
    });

    return response.choices[0].message.content;
}

// 使用示例
analyzeImage('https://example.com/image.jpg')
    .then(console.log)
    .catch(console.error);

TypeScript 支持 ​

OpenAI SDK 原生支持 TypeScript：

typescript
import OpenAI from 'openai';
import type { ChatCompletionMessageParam } from 'openai/resources/chat';

const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1'
});

async function chat(messages: ChatCompletionMessageParam[]): Promise<string> {
    const response = await client.chat.completions.create({
        model: 'gpt-4o',
        messages
    });

    return response.choices[0].message.content || '';
}

// 使用示例
const messages: ChatCompletionMessageParam[] = [
    { role: 'system', content: '你是一个助手' },
    { role: 'user', content: '你好！' }
];

chat(messages).then(console.log);

常见问题 ​

报错 "ECONNREFUSED" 或连接超时 ​

  1. 检查网络连接
  2. 确认 API 地址正确：https://www.51api.org/v1
  3. 尝试增加超时时间：
javascript
const client = new OpenAI({
    apiKey: process.env.NEWAPI_API_KEY,
    baseURL: 'https://www.51api.org/v1',
    timeout: 60000 // 60 秒超时
});

报错 "Model not found" ​

检查你的令牌分组是否正确。详见 常见问题。

其他问题 ​

查看 完整常见问题

51API - 您的 AI 能力聚合平台

Copyright © 2024-2025 51API