本文以 Chat Completion（对话补全） 为例，演示注册 → 获取 Key → 调 API 的全流程。XHuoAPI 完全兼容 OpenAI 接口格式。
1. 注册账号并获取 API Key
- 打开 api.xhuoapi.ai/register 注册
- 登录后在「令牌」页面创建 API Key
- 复制 Key（以
sk- 开头）
API Key 是密钥级别的字符串，不要贴到前端 / 移动端代码或公开仓库——请用环境变量或密钥管理服务。
2. 发起请求
把 Key 设到环境变量：
export XHUOAPI_API_KEY="sk-your-key-here"
curl https://api.xhuoapi.ai/v1/chat/completions \
-X POST \
-H "Authorization: Bearer $XHUOAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'
from openai import OpenAI
client = OpenAI(
base_url="https://api.xhuoapi.ai/v1",
api_key="sk-your-key-here",
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in response:
print(chunk.choices[0].delta.content or "", end="")
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.xhuoapi.ai/v1",
apiKey: "sk-your-key-here",
});
const stream = await client.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Hello!" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
3. 读取响应
标准 OpenAI 格式响应：
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}
{
"error": {
"message": "Invalid API key provided.",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}
4. 从 OpenAI 迁移
只需修改两行代码：
client = OpenAI(
base_url="https://api.xhuoapi.ai/v1", # 改这里
api_key="sk-your-xhuoapi-key", # 改这里
)
# 其余代码完全不变！
5. 后续
图像生成
GPT-Image、Midjourney 等文生图
