开发者文档

API 开发文档

快速集成指南与完整 API 参考

接口风格

OpenAI Compatible

基础地址

api.uaiapi.com

快速接入路径

创建账户并生成 API Token

使用 OpenAI SDK 或 HTTP 请求直接接入

在控制台查看额度、日志与密钥管理

快速开始

注册账户

在官网注册一个免费账户

获取密钥

在控制台创建 API Key

发起请求

使用 OpenAI SDK 或 HTTP 请求调用 API

BASE URL

https://api.uaiapi.com

认证方式

在请求头中携带 API Key 进行认证：

Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Token 以 sk- 开头，可在API Token 管理页面创建与管理。

模型列表

GET/v1/models

请求示例

bash

curl https://api.uaiapi.com/v1/models \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxx"

响应示例

json

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1700000000,
      "owned_by": "uaiapi"
    }
  ]
}

对话补全

POST/v1/chat/completions

请求参数

参数	类型	必填	说明
model	string	是	模型 ID，如 gpt-4o
messages	array	是	对话消息列表
stream	boolean	否	是否流式返回，默认 false
temperature	number	否	采样温度，0-2
max_tokens	integer	否	最大输出 token 数

curl

bash

curl https://api.uaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

响应示例

json

{
  "id": "chatcmpl-xxxxxxxxxxxx",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Python

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uaiapi.com/v1",
    api_key="sk-xxxxxxxxxxxxxxxxxx",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

Node.js

javascript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uaiapi.com/v1',
  apiKey: 'sk-xxxxxxxxxxxxxxxxxx',
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
});

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

流式响应示例

curl (SSE)

bash

curl -N https://api.uaiapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "stream": true,
    "messages": [
      {"role": "user", "content": "请用三句话介绍流式输出"}
    ]
  }'

流式返回片段（SSE）

text

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hel"}}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"lo"}}]}
data: [DONE]

Python (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uaiapi.com/v1",
    api_key="sk-xxxxxxxxxxxxxxxxxx",
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Node.js (OpenAI SDK)

javascript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uaiapi.com/v1',
  apiKey: 'sk-xxxxxxxxxxxxxxxxxx',
});

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  stream: true,
  messages: [{ role: 'user', content: 'Hello!' }],
});

for await (const chunk of stream) {
  const delta = chunk.choices?.[0]?.delta?.content;
  if (delta) process.stdout.write(delta);
}

错误代码

HTTP 状态码	错误类型	说明
400	invalid_request_error	请求参数错误
401	authentication_error	API Key 无效或缺失
402	insufficient_quota	额度不足
429	rate_limit_error	请求频率超限
404	model_not_found	模型不可用
502	upstream_error	上游服务商错误
500	server_error	内部服务器错误