API 文档

🎁 免费试用 — 无需信用卡

注册邮箱即可获得 $1 免费额度（约 100 万 tokens），有效期 14 天

快速开始

TokenEase 提供统一的 API 接口，支持 DeepSeek、智谱 GLM、阿里 Qwen 等主流 AI 模型。

基础 URL

https://tokenease.io/v1

认证方式

在请求头中添加您的 API Key：

Authorization: Bearer YOUR_API_KEY

支持的模型

请求频率限制

聊天补全 API

使用对话补全接口，与 AI 模型进行多轮对话。

请求参数

请求示例

curl -X POST https://tokenease.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4",
    "messages": [
      {"role": "system", "content": "你是一个有用的助手。"},
      {"role": "user", "content": "Hello, who are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

响应示例

{
  "id": "chatcmpl-xxxxx",
  "object": "chat.completion",
  "created": 1748390400,
  "model": "deepseek-v4",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "你好！我是 TokenEase 的 AI 助手..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 150,
    "total_tokens": 170
  }
}

模型列表

获取所有可用模型及其详细信息。

响应示例

{
  "object": "list",
  "data": [
    {
      "id": "deepseek-v4",
      "object": "model",
      "name": "DeepSeek V4",
      "provider": "DeepSeek",
      "context_length": 64000,
      "price_per_1m_tokens": 0.5
    },
    {
      "id": "glm-5.1",
      "object": "model",
      "name": "GLM-5.1",
      "provider": "Zhipu AI",
      "context_length": 128000,
      "price_per_1m_tokens": 8
    },
    {
      "id": "qwen-plus",
      "object": "model",
      "name": "Qwen-Plus",
      "provider": "Alibaba",
      "context_length": 131072,
      "price_per_1m_tokens": 3
    }
  ]
}

错误码

🌟 Kimi K3 — 256K 长上下文 · 全球可访问

Kimi K3 是 Moonshot AI 2026 年旗舰模型，MMLU-Pro 全球第一（89.2%），超越 GPT-5 和 Claude 4 Opus。通过 TokenEase 一键接入，无需中国手机号、无需 Alipay。

🚀 为什么选 K3？

💵 K3 定价（按 1M tokens 计）

🎯 快速调用 K3（直接复制运行）

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": "用一句话介绍三体文明"}
    ],
    "max_tokens": 2000,
    "temperature": 1
  }'

from openai import OpenAI

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

# ⚠️ K3 是思考型模型，max_tokens 必须 >= 2000
response = client.chat.completions.create(
    model="kimi-k3",
    messages=[
        {"role": "user", "content": "用一句话介绍三体文明"}
    ],
    max_tokens=2000,  # 关键：不能低于 2000
    temperature=1     # K3 强制 temperature=1
)

print(response.choices[0].message.content)
print(f"Token 用量: {response.usage.total_tokens}")
print(f"成本: ${response.usage.prompt_tokens * 0.0000035 + response.usage.completion_tokens * 0.000018:.4f}")

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: '用一句话介绍三体文明' }
  ],
  max_tokens: 2000,
  temperature: 1
});

console.log(response.choices[0].message.content);
console.log('Token 用量:', response.usage.total_tokens);

from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

llm = ChatOpenAI(
    model="kimi-k3",
    openai_api_key="YOUR_API_KEY",
    openai_api_base="https://tokenease.io/v1",
    max_tokens=2000,
    temperature=1
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "你是一位严谨的天体物理学家"),
    ("user", "{question}")
])

chain = prompt | llm
response = chain.invoke({"question": "解释一下三体运动为什么不可解"})
print(response.content)

任务: 256K 长文档问答 + 代码生成
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GPT-5  (OpenRouter):  $0.50 / 千次请求
K3     (TokenEase):   $0.024 / 千次请求  ← 便宜 20 倍 ✅
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MMLU-Pro 准确率:  GPT-5  87.8%  vs  K3  89.2%  ← K3 反超 ✅
长上下文检索:    GPT-5  76%   vs  K3   100%  ← K3 完胜 ✅

🎮 在线 Playground — 零代码试跑 K3

不用装 Python，不用写代码。打开浏览器，输入 API Key，立即看到 K3 回答。

SDK 示例

Python

# 安装
pip install openai

# 使用
from openai import OpenAI

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

response = client.chat.completions.create(
    model="deepseek-v4",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

JavaScript / Node.js

// 安装
// 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: 'deepseek-v4',
  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": "deepseek-v4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

开始使用

立即注册，获取免费额度，体验 TokenEase 的强大功能。