API 直接调用教程 - XiDao Api 文档

Overview

XiDao Api is fully compatible with OpenAI API format. You can use any HTTP client to call directly. Here is the basic info:

Base URL

# 国内节点
https://api.xidao.online/v1

# 全球加速节点
https://global.xidao.online/v1

🔑

Authentication Add in HTTP Header:
Authorization: Bearer sk-你的API_KEY

支持的 API 端点

Endpoint	Method	Description
`/v1/chat/completions`	POST	Chat Completions (most common)
`/v1/models`	GET	Get available model list
`/v1/embeddings`	POST	Text vectorization
`/v1/images/generations`	POST	Image generation
`/v1/audio/speech`	POST	Text-to-Speech (TTS)
`/v1/audio/transcriptions`	POST	Speech-to-Text (STT)

cURL 调用示例

Basic Chat

bash

curl https://api.xidao.online/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的API_KEY" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [
      {"role": "system", "content": "你是一个有帮助的助手。"},
      {"role": "user", "content": "你好，请介绍一下你自己。"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

GPT Model Call

bash

curl https://api.xidao.online/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的API_KEY" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {"role": "user", "content": "用 Python 写一个快速排序"}
    ]
  }'

Get Model List

bash

curl https://api.xidao.online/v1/models \
  -H "Authorization: Bearer sk-你的API_KEY"

Python 调用示例

Using openai Library (Recommended)

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

# 基本对话
response = client.chat.completions.create(
    model="claude-sonnet-4-5-20250929",
    messages=[
        {"role": "system", "content": "你是一个有帮助的编程助手"},
        {"role": "user", "content": "解释一下什么是递归"}
    ]
)

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

Streaming Output

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

stream = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "写一首关于编程的诗"}],
    stream=True
)

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

print()

Using requests Library (Native HTTP)

python

import requests

response = requests.post(
    "https://api.xidao.online/v1/chat/completions",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer sk-你的API_KEY"
    },
    json={
        "model": "gemini-2.5-flash",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)

data = response.json()
print(data["choices"][0]["message"]["content"])

Node.js / JavaScript 调用示例

Using openai Library

javascript

import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'sk-你的API_KEY',
    baseURL: 'https://api.xidao.online/v1'
});

const response = await client.chat.completions.create({
    model: 'claude-sonnet-4-5-20250929',
    messages: [
        { role: 'system', content: '你是有帮助的助手' },
        { role: 'user', content: '什么是 REST API?' }
    ]
});

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

Using fetch (No Dependencies)

javascript

const response = await fetch('https://api.xidao.online/v1/chat/completions', {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        'Authorization': 'Bearer sk-你的API_KEY'
    },
    body: JSON.stringify({
        model: 'gpt-5',
        messages: [{ role: 'user', content: 'Hello!' }]
    })
});

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

Streaming Output (SSE)

Streaming output allows AI responses to display character by character, improving user experience.

Python Streaming Example

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

stream = client.chat.completions.create(
    model="claude-sonnet-4-5-20250929",
    messages=[{"role": "user", "content": "详细解释机器学习"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

Node.js Streaming Example

javascript

import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'sk-你的API_KEY',
    baseURL: 'https://api.xidao.online/v1'
});

const stream = await client.chat.completions.create({
    model: 'gpt-5',
    messages: [{ role: 'user', content: '讲一个故事' }],
    stream: true
});

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

Embeddings (Text Vectorization)

Convert text to vector representation for semantic search, RAG, clustering, etc.

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="人工智能正在改变世界"
)

vector = response.data[0].embedding
print(f"向量维度: {len(vector)}")
print(f"前5个值: {vector[:5]}")

Image Generation

Generate images via API using DALL-E 3 or Midjourney.

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="一只穿着宇航服的猫在月球上看地球",
    size="1024x1024",
    quality="standard"
)

image_url = response.data[0].url
print(f"图片 URL: {image_url}")

错误处理

python

from openai import OpenAI, AuthenticationError, RateLimitError, APIError

client = OpenAI(
    api_key="sk-你的API_KEY",
    base_url="https://api.xidao.online/v1"
)

try:
    response = client.chat.completions.create(
        model="claude-sonnet-4-5-20250929",
        messages=[{"role": "user", "content": "Hello"}]
    )
    print(response.choices[0].message.content)
    
except AuthenticationError:
    print("错误: API Key 无效")
except RateLimitError:
    print("错误: 请求过于频繁，请稍后重试")
except APIError as e:
    print(f"API 错误: {e.message}")

Common Error Codes

Status Code	Meaning	Solution
`401`	Authentication failed	Check if API Key is correct
`402`	Insufficient balance	Top up and retry
`404`	Model not found	Check if model ID is correct
`429`	Rate limit exceeded	Reduce request frequency
`500`	Server error	Retry later or contact support