Singapore node — live and serving

AI compute,
built for Southeast Asia

High-performance AI inference API deployed in Singapore. OpenAI-compatible. Pay-per-token. No USD card required.

99.9%
Uptime SLA
<50ms
Avg latency
45
Tokens/sec
7×24
Support

Available models

One API key, all models. Switch models with a single parameter change.

LLM Available

DeepSeek-R1 7B

Reasoning model with chain-of-thought capability. Great for complex analysis, coding, and math.

Context 128K
Speed 45 tok/s
Coming soon Q3 2026

DeepSeek-R1 32B

Larger reasoning model with enhanced accuracy. Requires A10 GPU — arriving in Johor Bahru.

Context 128K
GPU NVIDIA A10
Coming soon Q4 2026

Llama 3.3 70B

Meta's flagship model for enterprise workloads. Multilingual support covering SEA languages.

Context 128K
Languages Multilingual

Simple, transparent pricing

Pay only for what you use. No monthly fees, no hidden costs. Billed in CNY — settle in your local currency.

Starter

For testing and prototyping

¥0.02 / 1K tokens
  • 30 requests/min
  • All available models
  • Streaming support
  • API key dashboard
Get API key
Popular

Business

For production workloads

¥0.015 / 1K tokens
  • 200 requests/min
  • Priority queue
  • Usage analytics
  • Multiple API keys
  • Email support
Contact sales

Enterprise

For high-volume & custom needs

Custom
  • Unlimited requests
  • Dedicated GPU capacity
  • Custom models
  • SLA guarantee
  • Dedicated support
  • Invoice & contract
Contact us
All prices in CNY. 1K tokens ≈ 750 English words. Volume discounts available for >10M tokens/month.

What you can build

From chatbots to code generation — one API, endless possibilities.

Chatbots & assistants

Build multilingual customer service chatbots for Southeast Asian markets.

Code generation

Integrate AI coding assistants into your IDE or CI/CD pipeline.

Document analysis

Summarize, extract, and analyze business documents in seconds.

Translation

Real-time translation across English, Chinese, Vietnamese, Thai, Malay, and more.

Two lines to get started

OpenAI-compatible API. If your code works with OpenAI, it works with us — just change the base URL.

request.sh
curl https://api.chengqiukeji.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "deepseek-r1:7b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'
from openai import OpenAI

client = OpenAI(
    base_url="https://api.chengqiukeji.com/v1",
    api_key="sk-your-api-key"
)

response = client.chat.completions.create(
    model="deepseek-r1:7b",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")
import OpenAI from "openai";

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

const response = await client.chat.completions.create({
    model: "deepseek-r1:7b",
    messages: [{ role: "user", content: "Hello!" }],
    stream: true
});

for await (const chunk of response) {
    process.stdout.write(chunk.choices[0].delta.content || "");
}
$client = new GuzzleHttp\Client();

$response = $client->post('https://api.chengqiukeji.com/v1/chat/completions', [
    'headers' => [
        'Authorization' => 'Bearer sk-your-api-key',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'model' => 'deepseek-r1:7b',
        'messages' => [['role' => 'user', 'content' => 'Hello!']],
    ],
]);

echo $response->getBody();

Why ChengQiu AI

Built specifically for the Southeast Asian market.

Low latency

Deployed in Singapore with direct peering to SEA networks. Under 50ms from Jakarta, Bangkok, Manila.

Compliant & secure

HTTPS encrypted. API key isolation. No data stored after inference. GDPR-ready.

Cost-effective

Pay-per-token with no minimum spend. Up to 70% cheaper than US-based providers.

Local support

Team based in China and Singapore. We understand SEA business culture and requirements.

How it works

From your app to the GPU in under 50ms.

Your app

OpenAI SDK or HTTP

API gateway

Auth + billing + rate limit

GPU inference

NVIDIA T4 · Singapore

HTTPS:443 → Nginx (TLS + reverse proxy) → 8080 → FastAPI (auth + billing) → 11434 → Ollama (GPU)

Ready to build with AI?

Get your API key in seconds. No credit card required to start.