How to Use Chinese LLMs (Qwen, DeepSeek, GLM) Without a Chinese Phone Number

A developer has documented methods for overseas developers to access Chinese LLMs such as Qwen, DeepSeek, and GLM without requiring a Chinese phone number. The most practical solution is using a gateway service like TokenMaster, which provides API access to these models by simply changing the base URL, bypassing the +86 phone verification requirement. The guide compares costs and reliability of various approaches, including virtual phone numbers and Alibaba Cloud International, concluding that gateway services offer the best balance of low cost and high reliability.

If you've tried signing up for any Chinese AI service, you've seen the same message: Please enter your phone number +86 to receive a verification code. This single requirement blocks most overseas developers from accessing some of the best-performing and most cost-effective LLMs on the market. This guide covers every workaround I've found — from least to most practical. China's major AI labs produce world-class models: But every single one requires: Services like SMS-activate and 5sim offer temporary Chinese phone numbers for ~$1-2. The problem: Chinese providers have gotten aggressive about flagging virtual numbers. Your account gets banned within days. You lose any balance you've added. ❌ Not recommended — too unreliable for production use. The most practical solution is a gateway that handles the China-side complexity for you. These services: What this means for you: Migration example Python : Before — can't access Chinese models at all client = OpenAI api key="..." Only works for OpenAI After — full access to Chinese models client = OpenAI base url="https://api.tokenmaster.com/v1", api key="tm-..." response = client.chat.completions.create model="deepseek-v4-pro", messages= {"role": "user", "content": "Hello "} No SDK changes. No VPN. No Chinese phone number. Just swap the base URL. Some providers like Alibaba Cloud's international portal offer English-language signup, but the model selection is limited and pricing is higher than domestic rates. Qwen via Alibaba Cloud International: DeepSeek Direct: Assuming 10M input + 2M output tokens per month: | Method | Monthly Cost | Setup Friction | Reliability | |---|---|---|---| | GPT-4o Direct | ~$38 | Low | High | | Chinese LLMs via Gateway | ~$7 | Low | High | | Virtual Phone Numbers | ~$5 + risk of losing account | Medium | Low | | Alibaba Cloud International | ~$15-20 | Medium | Medium | A good gateway will give you access to at least these models: | Model | Family | Cost Input/1M | Key Strength | |---|---|---|---| | DeepSeek V4 Flash | DeepSeek | $0.18 | Speed + low cost | | DeepSeek V4-Pro | DeepSeek | $0.50 | Coding + reasoning | | Qwen 3.7-Max | Qwen | $1.00 | Long context 256K | | Qwen 3.5-Flash | Qwen | $0.30 | High throughput | | GLM-4.5 | GLM | $0.80 | Reasoning | | GLM-4-Flash | GLM | $0.20 | Cost-effective | When evaluating a gateway for Chinese LLM access: If you want to try this today: pip install openai pip install openai python from openai import OpenAI client = OpenAI base url="https://api.tokenmaster.com/v1", api key="your-key-here" response = client.chat.completions.create model="qwen-3.7-max", messages= {"role": "user", "content": "Write a Python function to sort a list"} print response.choices 0 .message.content The +86 phone requirement is frustrating, but it's no longer a hard blocker. Gateway services have matured to the point where accessing Chinese LLMs from overseas is as simple as changing a base URL. Given the quality improvements and cost advantages, it's worth exploring — especially if your API bill is growing. Not affiliated with any service mentioned. Just a developer who spent way too long dealing with this problem and wants to save others the headache.