API Documentation - TokenEase

Quick Start

TokenEase provides a unified API interface supporting DeepSeek, Zhipu GLM, Alibaba Qwen, and other mainstream AI models.

Base URL

https://tokenease.io/v1

Authentication

Include your API Key in the request header:

Authorization: Bearer YOUR_API_KEY

Supported Models

Kimi K3

$0.28 / 1M cached input ($3.50 fresh) · $18.00 / 1M output

Moonshot flagship · 256K context · top MMLU-Pro

Kimi K2.7 Code

$1.20 / 1M input tokens · $5.00 / 1M output tokens

Coding and agent workflows

Kimi K2.7 Code HighSpeed

$2.50 / 1M input tokens · $10.00 / 1M output tokens

Same K2.7 Code at higher throughput

GLM-4 Flash

$0.10 / 1M input tokens · $0.40 / 1M output tokens

Cheapest model on the gateway

Rate Limits

100

RPM (Requests/min)

10,000

TPM (Tokens/min)

1,000

RPD (Requests/day)

Chat Completions API

Use the chat completions endpoint for multi-turn conversations with AI models.

POST /chat/completions

Request Parameters

model string Model name, e.g. kimi-k3 or glm-4-flash

messages array Array of messages, each with role and content

temperature float Sampling temperature, 0-2, default 0.7

max_tokens integer Maximum number of tokens to generate

Request Example

curl -X POST https://tokenease.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, who are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Response Example

{
  "id": "chatcmpl-xxxxx",
  "object": "chat.completion",
  "created": 1748390400,
  "model": "kimi-k3",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm TokenEase AI assistant..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 150,
    "total_tokens": 170
  }
}

Models List API

Get all available models and their details.

GET /models

Response Example

{
  "currency": "USD",
  "models": [
    { "id": "hy3-preview", "provider": "tencent_hy", "context_window": 128000, "price_per_1m": 1.0, "supports_vision": true, "enabled": false, "disabled_reason": "upstream billing unsettled (503 model_unavailable)" },
    { "id": "kimi-k3", "provider": "kimi", "context_window": 256000, "price_per_1m": 0.28, "supports_vision": true, "enabled": true, "disabled_reason": null },
    { "id": "hy3-thinking", "provider": "tencent_hy", "context_window": 128000, "price_per_1m": 2.0, "supports_vision": false, "enabled": false, "disabled_reason": "upstream billing unsettled (503 model_unavailable)" },
    { "id": "kimi-k2.7-code", "provider": "kimi", "context_window": 256000, "price_per_1m": 1.2, "supports_vision": false, "enabled": true, "disabled_reason": null },
    { "id": "kimi-k2.7-code-highspeed", "provider": "kimi", "context_window": 256000, "price_per_1m": 2.5, "supports_vision": false, "enabled": true, "disabled_reason": null },
    { "id": "glm-4-flash", "provider": "zhipu", "context_window": 128000, "price_per_1m": 0.1, "supports_vision": false, "enabled": true, "disabled_reason": null },
    { "id": "deepseek-chat", "provider": "deepseek", "context_window": 128000, "price_per_1m": 1.0, "supports_vision": false, "enabled": false, "disabled_reason": "upstream_insufficient_balance" }
  ]
}

Error Codes

400 Bad Request Invalid request parameters

401 Unauthorized Invalid or expired API Key

403 Forbidden Insufficient balance or quota exceeded

429 Rate Limited Request rate limit exceeded

500 Server Error Internal server error

SDK Examples

Python

# Install
pip install openai

# Usage
from openai import OpenAI

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

response = client.chat.completions.create(
    model="kimi-k3",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

JavaScript / Node.js

// Install
// npm install openai

import OpenAI from 'openai';

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

const response = await client.chat.completions.create({
  model: 'kimi-k3',
  messages: [
    { role: 'user', content: 'Hello!' }
  ]
});

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

cURL

curl https://tokenease.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Get Started

Sign up now, get free credits, and experience the power of TokenEase.

View Pricing Back to Home