Getting Started with TokenEase

What is TokenEase?

TokenEase is a unified API gateway for Chinese AI models. Instead of signing up for 5 different providers, you get one API key that works with:

• DeepSeek V4 - Best reasoning and coding
• GLM-5.1 - Top Chinese language model
• Qwen-Plus - Strong multilingual capabilities
• Kimi K2.6 - 2M token context window
• Doubao Pro - Fastest responses

All models use the OpenAI-compatible API format. If you've used OpenAI's API before, you already know how to use TokenEase.

Step 1: Get Your Free API Key

Step 2: Make Your First API Call

Choose your preferred language and run the code below. Replace your_api_key_here with your actual key.

Python

# Install: pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://tokenease.io/v1",
    api_key="your_api_key_here"
)

response = client.chat.completions.create(
    model="deepseek",
    messages=[{"role": "user", "content": "Hello! What can you help me with?"}]
)

print(response.choices[0].message.content)

Node.js

// Install: npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'https://tokenease.io/v1',
    apiKey: 'your_api_key_here'
});

const response = await client.chat.completions.create({
    model: 'deepseek',
    messages: [{ role: 'user', content: 'Hello! What can you help me with?' }]
});

console.log(response.choices[0].message.content);

cURL

curl https://tokenease.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your_api_key_here" \
  -d '{
    "model": "deepseek",
    "messages": [{"role": "user", "content": "Hello! What can you help me with?"}]
  }'

Step 3: Try Different Models

Changing models is as simple as changing one string:

# DeepSeek for coding
response = client.chat.completions.create(
    model="deepseek",
    messages=[{"role": "user", "content": "Write a Python function to reverse a string"}]
)

# GLM for Chinese content
response = client.chat.completions.create(
    model="zhipu",
    messages=[{"role": "user", "content": "写一首关于春天的诗"}]
)

# Qwen for translation
response = client.chat.completions.create(
    model="qwen",
    messages=[{"role": "user", "content": "Translate 'Hello world' to Japanese, French, and German"}]
)

# Kimi for long documents
response = client.chat.completions.create(
    model="kimi",
    messages=[
        {"role": "system", "content": "Summarize the following article:"},
        {"role": "user", "content": "[paste a 50,000 word article here]"}
    ]
)

Model	Best For	Speed
deepseek	Coding, reasoning, writing	Fast
zhipu	Chinese content, structured data	Fast
qwen	Translation, multilingual	Fast
kimi	Long documents, analysis	Moderate
doubao	Quick chat, low latency	Fastest

Step 4: Streaming Responses

For a better user experience, stream responses word by word:

stream = client.chat.completions.create(
    model="deepseek",
    messages=[{"role": "user", "content": "Tell me a short story"}],
    stream=True
)

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

What's Next?

Now that you've made your first API call, here are some next steps:

• Build a chatbot - See our complete chatbot tutorial
• Migrate from OpenAI - Follow our migration guide
• Build multi-model apps - Learn smart model routing
• Check your usage - Monitor token consumption in your dashboard
• Upgrade your plan - When free credit runs out, choose a plan that fits your needs

Common Issues

Issue	Solution
401 Unauthorized	Check your API key is correct and includes the te- prefix
429 Rate Limited	Wait a moment and retry, or upgrade your plan
Empty response	Check that messages is properly formatted as an array
Model not found	Use exact model names: deepseek, zhipu, qwen, kimi, doubao