Docs

Quick Start快速开始

TokenShovel uses an OpenAI-compatible request pattern for fast migration and enterprise model operations.TokenShovel 使用兼容 OpenAI 风格的请求结构，便于快速迁移和企业级模型运营。

Authentication

Use your TokenShovel API key as a bearer token. Never expose production keys in browser-side code.

Base URL

https://api.tokenshovel.io/v1

Python

from openai import OpenAI

client = OpenAI(
    api_key="TOKSH_YOUR_API_KEY",
    base_url="https://api.tokenshovel.io/v1"
)

completion = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Hello TokenShovel"}]
)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKENSHOVEL_API_KEY,
  baseURL: "https://api.tokenshovel.io/v1"
});

cURL

curl https://api.tokenshovel.io/v1/chat/completions \
  -H "Authorization: Bearer TOKSH_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.5","messages":[{"role":"user","content":"Hello"}]}'

Routing

Routing policies can prioritize availability, capability, provider preference, or business requirements.

SLA

Enterprise SLA and support terms are available through sales consultation.