OpenAI-Compatible · No VPN needed

Chinese AI Models
10× Cheaper.

Access DeepSeek, Qwen, and more via a single OpenAI-compatible API. Drop-in replacement. No Chinese phone number required.

Start Free → View Docs

10×

Cheaper than GPT-4

<200ms

Avg latency

99%

Uptime SLA

Integration

Two lines to switch.
Everything else stays.

from openai import OpenAI

# Just change these two lines ↓
client = OpenAI(
    api_key="sk-your-qiongqi-key",
    base_url="https://api.qiongqiai.com/v1"
)

# Everything else stays exactly the same
response = client.chat.completions.create(
    model="qwen-plus",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

// Just change these two lines ↓
const client = new OpenAI({
  apiKey: "sk-your-qiongqi-key",
  baseURL: "https://api.qiongqiai.com/v1",
});

// Everything else stays exactly the same
const res = await client.chat.completions.create({
  model: "qwen-plus",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(res.choices[0].message.content);

curl https://api.qiongqiai.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-qiongqi-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-plus",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Available Models

Pick the right model
for your use case.

Qwen

qwen-turbo

Fastest response. Great for high-volume, simple tasks.

$0.05 / 1M tokens

Qwen

qwen-plus

Best balance of speed and quality. Recommended for most apps.

$0.15 / 1M tokens

Qwen

qwen-max

Maximum capability. Complex reasoning and analysis tasks.

$0.40 / 1M tokens

DeepSeek

deepseek-v3

Exceptional at coding and logical reasoning. Low latency.

$0.20 / 1M tokens

DeepSeek

deepseek-r1

Deep chain-of-thought reasoning. Best for hard problems.

$0.60 / 1M tokens

Coming Soon

More models

GLM, Yi, Moonshot and more being added regularly.

Stay tuned

Price Comparison

Why pay more
for the same result?

Model	QiongQi AI	OpenAI Equivalent	Savings
Fast / Turbo	$0.05	$0.60 (GPT-4o mini)	12× cheaper
Balanced	$0.15	$2.50 (GPT-4o)	16× cheaper
Premium	$0.40	$15.00 (GPT-4 Turbo)	37× cheaper
Reasoning	$0.60	$15.00 (o1)	25× cheaper

* Prices per million tokens (input). OpenAI prices as of 2025.

Pricing

Simple, transparent
pricing.

Starter

^$9

per month

2M tokens / month
All models included
20 req/min rate limit
Email support

Get Started

Chinese AI Models 10× Cheaper.

Chinese AI Models
10× Cheaper.