Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
通过 cURL、Python 和 Node.js 的完整示例，演示如何向 Sub2API 发起 AI 模型调用并理解响应。
https://sub2api.ruilinlu.com。
/v1/chat/completions 接口，向模型发送一条简单消息。
curl https://sub2api.ruilinlu.com/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "你好！请用中文回复。"}
]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://sub2api.ruilinlu.com",
api_key=os.getenv("OPENAI_API_KEY"),
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "你好！请用中文回复。"}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://sub2api.ruilinlu.com",
apiKey: process.env.OPENAI_API_KEY,
});
const response = await client.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "你好！请用中文回复。" }],
});
console.log(response.choices[0].message.content);
{
"id": "chatcmpl-xxx",
"object": "chat.completion",
"created": 1710000000,
"model": "gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "你好！很高兴为你服务。"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 10,
"total_tokens": 22
}
}
choices[0].message.content 包含模型生成的回复内容，usage.total_tokens 显示了本次请求消耗的总 Token 数。
model 参数即可。
{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "你好"}]
}
{
"model": "claude-xxx",
"messages": [{"role": "user", "content": "你好"}]
}
{
"model": "gemini-xxx",
"messages": [{"role": "user", "content": "你好"}]
}
Authorization: Bearer YOUR_API_KEY 是否配置正确。
更多排查方法请参考 401 错误处理。