Now supporting DeepSeek-V3 & R1

Access China's Best
AI Models — Globally

One unified API to access Zhipu GLM, MiniMax, Kimi, DeepSeek and more. Instant delivery, transparent pricing, enterprise-grade reliability.

6+ AI Models
99.9% Uptime SLA
<100ms Global Latency
50+ Countries

Trusted by developers worldwide

China's Leading AI,
One API Away

From reasoning to multimodal, access the most advanced Chinese AI models through a single, OpenAI-compatible endpoint.

Live

Kimi k1.5

Moonshot AI's long-context champion. Process entire books, codebases, or lengthy conversations with ease.

200K Context Long Doc
Live

MiniMax abab6.5

Powerful multimodal model excelling at voice, text, and image understanding. Built for interactive AI agents.

Voice Vision Agent
Live

Qwen2.5-Max

Alibaba Cloud's flagship model. Exceptional at tool use, structured output, and enterprise workflows.

Tools JSON Enterprise
Live

Baichuan 4

Optimized for Chinese business scenarios. Strong performance in legal, medical, and financial domains.

Chinese Industry

Built for Global
Developers

We remove the friction of accessing China's best AI. No Chinese business entity required. Pay in USD. Get support in English.

OpenAI-Compatible API

Drop-in replacement. Change one base URL and start using GLM, DeepSeek, or Kimi instantly.

Global Edge Network

Requests routed through our global PoPs. Sub-100ms latency to North America, Europe, and Southeast Asia.

Real-Time Usage Dashboard

Monitor token consumption, latency, and costs per model. Export logs for compliance and debugging.

Enterprise Security

SOC 2 Type II certified. End-to-end encryption. Dedicated VPC options for enterprise customers.

example.py
import openai

client = openai.OpenAI(
    base_url="https://api.mixtoken.cn/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "user",
         "content": "Explain quantum computing"}
    ],
    stream=True
)

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

Transparent, Pay-As-You-Go
Token Pricing

No hidden fees. No minimum commitment. Volume discounts available for enterprises.

Model Input (per 1M) Output (per 1M) Context Features
DeepSeek-V3 $0.14 $0.28 64K General Fast
DeepSeek-R1 $0.55 $2.19 64K Reasoning Chain-of-Thought
GLM-4-Plus $0.50 $0.50 128K Multilingual Code
Kimi k1.5 $0.60 $0.60 200K Long Context
MiniMax abab6.5 $0.40 $0.80 32K Voice Vision
Qwen2.5-Max $0.38 $0.76 128K Tools JSON
Baichuan 4 $0.35 $0.70 128K Chinese Industry
All prices in USD. Volume discounts apply at >100M tokens/month. Contact sales for enterprise pricing.

Get Started in
5 Minutes

Our OpenAI-compatible API means zero learning curve. Use your favorite SDK — Python, Node.js, Go, or curl.

01

Create Account

Sign up with email or GitHub. Get $5 free credits instantly.

02

Generate API Key

Create and scope your keys. Set rate limits and IP restrictions.

03

Change Base URL

Point your OpenAI client to https://api.mixtoken.cn/v1

Read Full Docs
bash
$ curl https://api.mixtoken.cn/v1/chat/completions \\
-H "Authorization: Bearer $TOKEN" \\
-H "Content-Type: application/json" \\
-d '{
"model": "deepseek-v3",
"messages": [{"role":"user","content":"Hello!"}]
}'
{
"id": "chat-xyz",
"object": "chat.completion",
"choices": [{
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?"
}
}]
}

Ready to Build with China's Best AI?

Join thousands of developers using MixToken to access Zhipu, DeepSeek, Kimi, and more. Start free, scale as you grow.