Quick Start

CiYuanX provides a unified API for accessing hundreds of AI models through a single endpoint. Get started in minutes with a simple integration.

TIP

Looking for information on free models and rate limits? Check the FAQ.

Using the OpenAI SDK

The simplest way is to use the official OpenAI SDK — just change the base_url and you're ready to go.

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://ciyuanx.io/v1",
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-api-key-here",
  baseURL: "https://ciyuanx.io/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-4.1",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

Calling the CiYuanX API directly

You can also invoke the API with plain HTTP requests.

INFO

Use our interactive request builder to generate API requests.

Python

import requests

response = requests.post(
    "https://ciyuanx.io/v1/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "gpt-4.1",
        "messages": [
            {"role": "user", "content": "Hello!"}
        ],
    },
)

print(response.json())

TypeScript

const response = await fetch("https://ciyuanx.io/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-4.1",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});

console.log(await response.json());

Curl

curl https://ciyuanx.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Next steps

Our API also supports advanced features like streaming and batch processing. See the Chat Completions API reference for details.

The API also supports streaming.

Supported models

We support a wide range of AI models, including but not limited to:

OpenAI models

• GPT-5.4
• GPT-5.5
• GPT-5.4-mini

Anthropic models

• Claude-3 Opus 4.7
• Claude-3 Sonnet 4.6
• Claude-3 Haiku 4.5