LLM API Gateway - Route to 11 Chinese Models from One Endpoint

What Is an LLM API Gateway?

An LLM API gateway sits between your application and multiple language model providers, providing a unified interface to access all of them. Instead of managing separate API keys, endpoints, and SDK configurations for each provider, you connect once and route to any model.

  Your App                    AI Token Hub                Model Providers
  ─────────                   ────────────                ───────────────
                    ┌─────────────────────────┐
  OpenAI SDK  ───▶  │  /v1/chat/completions   │  ───▶  DeepSeek API
  (any client)      │                         │  ───▶  Alibaba Qwen API
                    │  Smart Model Routing    │  ───▶  Zhipu GLM API
  model="deepseek"  │                         │  ───▶  Moonshot Kimi API
  model="qwen3"     │  Unified Auth & Billing │
  model="kimi-k3"   └─────────────────────────┘

Why AI Token Hub as Your LLM Gateway?

🔌 Single Integration

One API key, one endpoint, one SDK integration. Access all 11 models through the same interface.

💸 Unified Billing

One bill for all models. No need to manage separate accounts with DeepSeek, Alibaba, Zhipu, and Moonshot.

🔄 Model Switching

Switch models by changing a single string. Test DeepSeek, then Qwen, then Kimi — no code changes needed.

🌍 Global Access

Access Chinese LLMs from anywhere. No Chinese phone number, bank account, or business license required.

🆓 Free Tier

GLM-4-flash is completely free. Test your integration without spending a cent.

⚡ Low Latency

Optimized routing ensures fast response times. Most models return within 1-3 seconds for typical requests.

All 11 Models Available Through the Gateway

Model ID	Provider	Context	Input	Output	Type
deepseek-v4	DeepSeek	128K	$0.28/1M	$0.42/1M	Flagship
deepseek-v3	DeepSeek	128K	$0.28/1M	$0.42/1M	Stable
deepseek-r1	DeepSeek	128K	$0.55/1M	$2.19/1M	Reasoning
deepseek-v4-flash	DeepSeek	128K	$0.07/1M	$0.14/1M	Fast
qwen3.6-flash	Alibaba	128K	$0.02/1M	$0.08/1M	Cheap
qwen3-flash	Alibaba	128K	$0.02/1M	$0.08/1M	Fast
qwen-plus	Alibaba	128K	$0.40/1M	$1.20/1M	Balanced
qwen-max	Alibaba	128K	$1.60/1M	$6.40/1M	Premium
glm-4-flash	Zhipu	128K	FREE	FREE	Free tier
glm-4-air	Zhipu	128K	$0.03/1M	$0.11/1M	Lightweight
kimi-k3	Moonshot	128K	$0.15/1M	$0.60/1M	Long context

Integration Guide

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1",
    api_key="your-api-key"
)

# List all models available through the gateway
models = client.models.list()

# Route to any model by name
for model_id in ["deepseek-v4", "qwen3-flash", "kimi-k3"]:
    response = client.chat.completions.create(
        model=model_id,
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(f"{model_id}: {response.choices[0].message.content[:50]}...")
            

cURL

# List models
curl https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1/models \
  -H "Authorization: Bearer your-api-key"

# Chat with deepseek-v4
curl https://eaf9553505eeb8f5-115-190-107-107.serveousercontent.com/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4","messages":[{"role":"user","content":"Hello!"}]}'
            

Who Uses LLM API Gateways?

🏗️ AI Agent Builders

Route agent tasks to the most cost-effective model. Use cheap models for simple tasks, expensive ones for complex reasoning.

🚀 Startups

Minimize AI costs while building your product. Switch models as better ones become available without rewriting code.

📊 Data Teams

Process large volumes of text cheaply. Classify, extract, and summarize data at 100x lower cost than GPT-4.

🔬 Researchers

Compare model outputs across providers. Test hypotheses with different models without managing multiple accounts.

Get Started with AI Token Hub

Your LLM API gateway to 11 Chinese models. No credit card required.

Start Now API Documentation View Pricing