TokenEase API Examples — Python, JavaScript, cURL, LangChain

1

Get Your API Key

Register at tokenease.io/register to get a free API key with 1M tokens. No credit card required.

Your API Key: te_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Base URL:     https://tokenease.io/v1

2

Pick Your Language

TokenEase is fully OpenAI-compatible. Use the official SDKs or any HTTP client.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Explain quantum computing in 3 sentences"}]
)

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

Tip: Swap model="deepseek-chat" for kimi-k3, glm-4-flash, qwen-plus, or doubao-pro.

import OpenAI from 'openai';

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

const response = await client.chat.completions.create({
    model: 'kimi-k3',
    messages: [{ role: 'user', content: 'Write a React hook for debounce' }]
});

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

curl https://tokenease.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_TOKENEASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="qwen-plus",
    openai_api_key="YOUR_TOKENEASE_API_KEY",
    openai_api_base="https://tokenease.io/v1",
    temperature=0.7
)

response = llm.invoke("What are the top 3 Python libraries for data visualization?")
print(response.content)

Tip: LangChain, LlamaIndex, and most OpenAI-compatible tools work out of the box. Just change base_url and api_key.

3

Streaming Responses (Real-Time Output)

For chat UIs, stream tokens as they arrive instead of waiting for the full response.

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="kimi-k3",
    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="")

4

Switch Models Instantly

Change one parameter to switch between 6 providers. No new API keys, no new accounts.

# Cheapest — great for bulk
model="glm-4-flash"  # $0.10/M input

# Best coding
model="deepseek-chat"  # $1.0/M input

# Long context
model="kimi-k3"  # 256K context

# General purpose
model="qwen-plus"  # Balanced quality/price

# Fast Chinese
model="doubao-pro"  # ByteDance

# Multimodal
model="hy3-preview"  # Tencent

Note: All models share the same endpoint, same authentication, same response format. Switching is literally changing one string.

Pro tip: Use glm-4-flash for drafts and deepseek-chat for final output to cut costs by 90%.

5

Deploy to Production

Ready patterns for common deployment scenarios.

# FastAPI backend (Python)
from fastapi import FastAPI
from openai import AsyncOpenAI

app = FastAPI()
client = AsyncOpenAI(api_key="YOUR_KEY", base_url="https://tokenease.io/v1")

@app.post("/chat")
async def chat(message: str):
    r = await client.chat.completions.create(
        model="deepseek-chat",
        messages=[{"role": "user", "content": message}]
    )
    return {"reply": r.choices[0].message.content}

API Examples & Quickstart

Get Your API Key

Pick Your Language

Streaming Responses (Real-Time Output)

Switch Models Instantly

Deploy to Production