How to Access DeepSeek V4, Qwen 3.7, and GLM-4 from Outside China (No VPN Needed)

#python #api #llm #beginners

Chinese LLMs have gotten incredibly good — and they just topped global rankings again. DeepSeek V4, Qwen 3.7, and GLM-4 compete with or beat GPT on many benchmarks, and they're a fraction of the cost.

But if you're outside China, actually using their APIs is a pain:

📵 Need a Chinese phone number for registration
🪪 ID verification (Chinese national ID or passport)
🔀 Separate accounts, API keys, and billing for each provider
💳 Payment requires Chinese payment methods (Alipay/WeChat Pay)

That's a lot of friction just to try a model. Let me show you a simpler way.

TunanAPI: One Endpoint for All Chinese LLMs

TunanAPI is a unified OpenAI-compatible API that lets you access the best Chinese models from anywhere in the world. One API key, one endpoint, PayPal billing.

Quick Start (3 steps)

Step 1: Get your API key

Visit tunanapi.com, sign up with your email, and top up with PayPal. You'll get an API key instantly — no Chinese phone number or ID required.

Step 2: Install the OpenAI SDK

pip install openai

Step 3: Make your first request

from openai import OpenAI

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

# Try DeepSeek V4 Flash — fast and affordable
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

That's it. If you've used the OpenAI API before, you already know how to use this.

Available Models & Pricing

Model	Best For	Input/1M tokens	Output/1M tokens
GLM-4-Flash	Free-tier tasks	$0.05	$0.05
Qwen3.5-Flash	Ultra-cheap production	$0.35	$1.39
DeepSeek V4 Flash	Fast, affordable tasks	$0.70	$1.40
MiniMax M3	Coding & reasoning	$1.20	$4.80
GLM-4-Plus	Chinese + English	$1.39	$1.39
Qwen3.7-Plus	Balanced performance	$1.39	$5.56
Qwen3.7-Max	General purpose, 1M context	$2.08	$6.25
DeepSeek V4 Pro	Complex reasoning	$2.18	$4.35

Compare to Anthropic's newly announced Fable 5 at $10/$50 — our Qwen3.7-Max at $2.08/$6.25 is 8x cheaper for similar flagship-tier performance.

Streaming Example (Node.js)

import OpenAI from 'openai';

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

const stream = await client.chat.completions.create({
  model: 'qwen3.7-plus',
  messages: [{ role: 'user', content: 'Write a haiku about programming' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Works With Your Favorite Frameworks

LangChain:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.tunanapi.com/v1",
    api_key="your-key",
    model="deepseek-chat"
)

Vercel AI SDK:

import { createOpenAI } from '@ai-sdk/openai';

const tunan = createOpenAI({
  baseURL: 'https://api.tunanapi.com/v1',
  apiKey: 'your-key',
});

cURL:

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