README.md

metadata

title: Nexus-Core Inference API
emoji: ⚡
colorFrom: green
colorTo: blue
sdk: docker
pinned: false
license: cc-by-nc-4.0

⚡ Nexus-Core Inference API

Fast and efficient chess move prediction API powered by Nexus-Core v2.0.

🎯 Model Info

• Parameters: 13M (ResNet-based)
• Speed: Ultra-fast inference (~0.5-1s per move)
• Strength: ~2000-2200 ELO
• Architecture: Pure CNN value network

📡 API Endpoint

POST /get-move

Request:

{
  "fen": "rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1",
  "depth": 4,
  "time_limit": 3000
}

Response:

{
  "best_move": "e2e4",
  "evaluation": 0.21,
  "depth_searched": 4,
  "nodes_evaluated": 8432,
  "time_taken": 856
}

🔧 Parameters

• fen (required): Board position
• depth (optional): 1-6, default 4
• time_limit (optional): Max time in ms, default 3000

💻 Performance

• Average Response: 0.5-1 second @ depth 4
• Memory Usage: ~2GB RAM
• Concurrent Requests: 4-6 simultaneous

---

Part of GambitFlow AI Suite 🚀