OpenCodex

API 文档

兼容 OpenAI SDK，单一端点访问 DeepSeek、Qwen、Claude、Gemini、GPT-4 等所有模型。

基础 URL

https://opencodex.hk/api/v1

认证

所有 API 请求需要在 HTTP Header 中携带 API Key。在控制台创建 API Key。

Authorization: Bearer YOUR_API_KEY

快速开始

使用 cURL 或 PowerShell 快速测试 API 连接

cURL 示例

curl -X POST https://opencodex.hk/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-live-YOUR_API_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

PowerShell 示例

Invoke-RestMethod -Uri "https://opencodex.hk/api/v1/chat/completions" -Method POST -Headers @{'Authorization'='Bearer sk-live-YOUR_API_KEY';'Content-Type'='application/json'} -Body '{"model":"deepseek-chat","messages":[{"role":"user","content":"Hello!"}]}'

代码示例

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-live-YOUR_API_KEY",
    base_url="https://opencodex.hk/api/v1"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    temperature=0.7,
    max_tokens=2048
)

print(response.choices[0].message.content)

JavaScript / TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-live-YOUR_API_KEY',
  baseURL: 'https://opencodex.hk/api/v1'
});

const response = await client.chat.completions.create({
  model: 'deepseek-chat',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ],
  temperature: 0.7,
  max_tokens: 2048
});

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

cURL

curl -X POST https://opencodex.hk/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-live-YOUR_API_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7,
    "max_tokens": 2048
  }'

错误码

API 可能返回的常见错误码及说明

状态码错误码描述
400Bad Request请求参数错误（如缺少必填字段、格式不正确）
401UnauthorizedAPI Key 无效、过期或格式错误（必须以 sk-live- 开头）
402Payment Required积分余额不足，请充值后再试
429Too Many Requests请求过于频繁，触发速率限制，请稍后重试
500Internal Server Error服务器内部错误，请稍后重试或联系客服

最佳实践

🔑 API Key 安全

  • 不要将 API Key 硬编码在前端代码中，使用环境变量存储
  • 定期轮换 API Key，避免泄露
  • 为不同应用创建不同的 API Key，便于管理和撤销

⚡ 性能优化

  • 复用连接池，避免频繁建立 HTTPS 连接
  • 合理设置 max_tokens，避免生成过长的回复
  • 使用流式输出提升用户体验，减少等待时间

🔧 兼容的工具

我们的 API 完全兼容以下主流 AI 编程工具：

CursorClaude CodeContinueGitHub CopilotTraeClineCodeiumTabnineWindsurf

技术支持

如有任何问题，欢迎通过以下方式联系我们：

📧 邮件支持📚 文档价格

聊天补全

发送消息列表给模型，获取回复。完全兼容 OpenAI /v1/chat/completions 格式。

接口地址

POST /v1/chat/completions

请求参数

参数名类型必填说明
modelstring✓模型 ID，如 deepseek-chat, gpt-4o, claude-3-sonnet
messagesarray✓对话消息数组，包含 role (system/user/assistant) 和 content
max_tokensinteger最大生成 token 数，默认 4096
temperaturenumber温度参数 (0-2)，控制随机性，默认 1
top_pnumber核采样参数 (0-1)，默认 1
streamboolean是否使用流式输出，默认 false
stoparray|string停止序列，遇到此内容时停止生成

请求体

{
  "model": "deepseek-chat",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "temperature": 0.7,
  "max_tokens": 2048,
  "stream": false
}

响应示例

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

流式传输

设置 stream: true 可以逐字接收模型输出，适合实时对话场景。

请求体

{
  "model": "deepseek-chat",
  "messages": [{ "role": "user", "content": "Hello!" }],
  "stream": true
}

流式响应示例

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1700000000,"model":"deepseek-chat","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1700000000,"model":"deepseek-chat","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1700000000,"model":"deepseek-chat","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

可用模型列表

获取当前账号有权访问的所有模型 ID 列表。

GET /v1/models

余额查询

查询当前账号的剩余积分余额。

GET /v1/balance

SDK 示例

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://opencodex.hk/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://opencodex.hk/api/v1",
  apiKey: process.env.OPENCODEX_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [{ role: "user", content: "Hello!" }],
});

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

错误码

状态码含义
200请求成功
400请求参数错误（如缺少必填字段）
401API Key 无效或已过期
402积分余额不足，请充值
429请求过于频繁，触发速率限制
500服务器内部错误

准备好开始构建了吗？

注册即送 500 免费积分，无需信用卡。

免费注册