30 秒快速上手

同一个目标——让模型「用一句话解释量子纠缠」——分别用三家原生格式调用。先在终端设好 Key：

PowerShellBash

$env:LIUGE_API_KEY = "sk-你的key"

export LIUGE_API_KEY="sk-你的key"

① OpenAI 格式 → /v1/chat/completions

curlPythonJavaScript

curl https://6geapi.com/v1/chat/completions \
  -H "Authorization: Bearer $LIUGE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [{"role": "user", "content": "用一句话解释量子纠缠"}]
  }'

from openai import OpenAI
client = OpenAI(base_url="https://6geapi.com/v1", api_key="你的Key")
r = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "用一句话解释量子纠缠"}],
)
print(r.choices[0].message.content)

import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://6geapi.com/v1", apiKey: process.env.LIUGE_API_KEY });
const r = await client.chat.completions.create({
  model: "gpt-5.6-sol",
  messages: [{ role: "user", content: "用一句话解释量子纠缠" }],
});
console.log(r.choices[0].message.content);

② Claude 格式 → /v1/messages

curlPythonJavaScript

curl https://6geapi.com/v1/messages \
  -H "Authorization: Bearer $LIUGE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "用一句话解释量子纠缠"}]
  }'

import anthropic
client = anthropic.Anthropic(base_url="https://6geapi.com", api_key="你的Key")
m = client.messages.create(
    model="claude-opus-5", max_tokens=1024,
    messages=[{"role": "user", "content": "用一句话解释量子纠缠"}],
)
print(m.content[0].text)

import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({ baseURL: "https://6geapi.com", apiKey: process.env.LIUGE_API_KEY });
const m = await client.messages.create({
  model: "claude-opus-5", max_tokens: 1024,
  messages: [{ role: "user", content: "用一句话解释量子纠缠" }],
});
console.log(m.content[0].text);

③ Gemini 格式 → /v1beta/interactions

curlPythonJavaScript

curl -X POST "https://6geapi.com/v1beta/interactions" \
  -H "Authorization: Bearer $LIUGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-proview",
    "input": "用一句话解释量子纠缠"
  }'

from google import genai
client = genai.Client(api_key="你的Key",
                      http_options={"base_url": "https://6geapi.com"})
it = client.interactions.create(model="gemini-3-pro-proview",
                                input="用一句话解释量子纠缠")
print(it.output_text)

import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: process.env.LIUGE_API_KEY,
                             httpOptions: { baseUrl: "https://6geapi.com" } });
const it = await ai.interactions.create({ model: "gemini-3-pro-proview", input: "用一句话解释量子纠缠" });
console.log(it.output_text);

下一步

跑通任意一条后，深入看对应端点的全部参数：Claude · OpenAI · Gemini。原理不清楚先读 架构与转发流程。