API Documentation

Detailed integration guide and API reference to help you quickly integrate the TokenWorks LLM API and AI gateway

1Quick Start

Start using the TokenWorks API in three simple steps:

Register a TokenWorks account and log in to the dashboard
Create an API Key in the dashboard
Use your API Key to call our endpoints

Tip: New users receive free trial credits upon registration — no credit card required.

2Base URL

The API base URL is below. All requests use HTTPS:

text

https://www.token8341.com/v1

Chat Completions endpoint:

text

POST https://www.token8341.com/v1/chat/completions

Note: This endpoint is fully compatible with the OpenAI Chat Completions API format. You can directly use the OpenAI SDK.

3Authentication

TokenWorks uses Bearer Token authentication. Include your API Key in the request header:

text

Authorization: Bearer sk-your-api-key-here

You can create and manage your keys in the 'API Keys' section of the dashboard. Never expose your API Key in public repositories or client-side code.

4Supported Models

Model ID	Model Name	Provider
gpt-4o	GPT-4o	OpenAI
gpt-4o-mini	GPT-4o Mini	OpenAI
claude-3-5-sonnet	Claude 3.5 Sonnet	Anthropic
claude-4-sonnet	Claude 4 Sonnet	Anthropic
gemini-2-0-pro	Gemini 2.0 Pro	Google
deepseek-v3	DeepSeek-V3	DeepSeek
qwen-max	Qwen-Max	Alibaba Cloud

More models are being added continuously. Stay tuned for updates.

5Code Examples

curl

bash

curl https://www.token8341.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key-here" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Python (openai SDK)

python

from openai import OpenAI

client = OpenAI(
    base_url="https://www.token8341.com/v1",
    api_key="sk-your-api-key-here"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Node.js (openai SDK)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://www.token8341.com/v1",
  apiKey: "sk-your-api-key-here",
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "user", content: "Hello!" },
  ],
});

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

6Error Codes

When an API request fails, the following HTTP status codes and error information are returned:

json

{
  "error": {
    "message": "Insufficient balance",
    "type": "insufficient_balance",
    "code": 402
  }
}

Status Code	Name	Description
400	Bad Request	请求参数错误，请检查请求体格式
401	Unauthorized	API Key 无效或缺失，请检查 Authorization 请求头
402	Insufficient Balance	账户余额不足，请充值后重试
404	Not Found	请求的模型或接口不存在
429	Rate Limit	请求频率过高，请稍后重试
500	Internal Server Error	服务内部错误，请联系技术支持
503	Service Unavailable	模型服务暂时不可用，请稍后重试