---
title: Synapse-Base Inference API
emoji: 🧠
colorFrom: blue
colorTo: purple
sdk: docker
pinned: true
license: cc-by-nc-4.0
---

# 🧠 Synapse-Base Inference API

High-performance chess move prediction API powered by Synapse-Base v3.0.

## 🎯 Features

- **Deep Search Algorithm**: Advanced alpha-beta pruning with move ordering
- **CPU Optimized**: Runs efficiently on 2 vCPU + 16GB RAM
- **REST API**: Simple POST endpoint for move generation
- **Model**: 38.1M parameter hybrid CNN-Transformer

## 📡 API Endpoint

### `POST /get-move`

**Request:**
```json
{
  "fen": "rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1",
  "depth": 3,
  "time_limit": 5000
}
```

**Response:**
```json
{
  "best_move": "e2e4",
  "evaluation": 0.25,
  "depth_searched": 3,
  "nodes_evaluated": 15234,
  "time_taken": 1247
}
```

## 🔧 Parameters

- **fen** (required): Current board position in FEN notation
- **depth** (optional): Search depth (1-5, default: 3)
- **time_limit** (optional): Max time in milliseconds (default: 5000)

## 💻 Local Testing

```bash
docker build -t synapse-inference .
docker run -p 7860:7860 synapse-inference
```

## 📊 Performance

- **Average Response Time**: 1-3 seconds per move
- **Memory Usage**: ~4GB RAM
- **Concurrent Requests**: Up to 4 simultaneous

## ⚠️ Rate Limits

Free tier: 100 requests/hour per IP

---

Built with ❤️ by GambitFlow