OpenAI 兼容 · Claude / Gemini / GPT

一个密钥，接入
全部主流大模型

浮光AI 是 OpenAI 兼容的一站式模型网关。把 base_url 换成浮光，原有代码和客户端几乎不用改。

注册即送体验额度Gemini 全系官方 2 折多上游自动故障切换

curl https://aiz.naiyouai.com/v1/chat/completions \
  -H "Authorization: Bearer 你的Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [{"role": "user", "content": "请只回复：连接成功"}]
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(api_key="你的Key", base_url="https://aiz.naiyouai.com/v1")

resp = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{"role": "user", "content": "请只回复：连接成功"}],
)
print(resp.choices[0].message.content)

// npm install openai
import OpenAI from "openai";

const client = new OpenAI({ apiKey: "你的Key", baseURL: "https://aiz.naiyouai.com/v1" });

const resp = await client.chat.completions.create({
  model: "gemini-3.8-flash",
  messages: [{ role: "user", content: "请只回复：连接成功" }],
});
console.log(resp.choices[0].message.content);

响应200 OK

{
  "object": "chat.completion",
  "model": "gemini-3.8-flash",
  "choices": [
    { "message": { "role": "assistant", "content": "连接成功" }, "finish_reason": "stop" }
  ],
  "usage": { "prompt_tokens": …, "completion_tokens": …, "total_tokens": … }
}