Skip to main content

Quick Start

Follow the steps below to integrate within a few minutes.

Step 1: Get an API Key​

Sign up and create an API Key in the console. Keep the key secure and never expose it in client-side or front-end code.

Step 2: Configure Base URL​

Replace the official OpenAI endpoint with the Qiyiguo AI endpoint:

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.manysky.top/v1"
)
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MANYSKY_API_KEY,
  baseURL: "https://api.manysky.top/v1"
});

Step 3: Call a Model​

Use a single interface to call multiple models:

Chat Completions
resp = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Hello"}]
)
print(resp.choices[0].message.content)
Chat Completions
const resp = await client.chat.completions.create({
  model: "claude-sonnet-4-20250514",
  messages: [{ role: "user", content: "Hello" }]
});
console.log(resp.choices[0].message.content);
  • Store and inject API keys securely on the server side
  • Add retry and timeout mechanisms for critical requests
  • Combine with Error Codes & Retry to improve robustness