## What is ModelStack?

ModelStack is a unified API gateway for AI models. Instead of managing separate API keys, SDKs, and billing accounts for each AI provider, ModelStack gives you one API, one key, and one bill.

## Key Features

<CardGroup cols={2}>
  <Card title="Unified API" icon="cable">
    Access Claude, GPT, Gemini, DeepSeek, and more through a single
    OpenAI-compatible endpoint. Switch models by changing one parameter.
  </Card>
  <Card title="50+ Models" icon="neurology">
    Anthropic Claude 4.x, OpenAI GPT-5.x, Google Gemini 3.x, DeepSeek V4,
    MiniMax M2, Qwen3, GLM 5 — all available instantly.
  </Card>
  <Card title="Simple Billing" icon="credit_card">
    Time-windowed spending caps reset every 5 hours. Purchase prepaid balance
    for additional usage — expires after 12 months.
  </Card>
  <Card title="Dashboard & Analytics" icon="analytics">
    Real-time usage analytics, request logs, model breakdown charts, and API key
    management from a single dashboard.
  </Card>
</CardGroup>

## How It Works

1. **Sign up** at [modelstack.cc](https://modelstack.cc/sign-up) and choose a plan
2. **Create an API key** from your dashboard
3. **Make requests** to `api.modelstack.cc` using any OpenAI-compatible SDK
4. **Switch models** freely — just change the `model` parameter

```bash
curl https://api.modelstack.cc/v1/chat/completions \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## Why ModelStack?

- **No provider lock-in** — switch between Anthropic, OpenAI, Google, DeepSeek, and more with zero code changes
- **OpenAI-compatible** — works with existing OpenAI SDKs in Python, Node.js, and any language
- **Predictable costs** — time-windowed spending caps reset every 5 hours; prepaid balance expires after 12 months
- **Built for developers** — simple REST API, streaming support, comprehensive error codes