Edge Router

Routes tasks to cheapest available backend: local (free) → cloud GPU ($0.01) → quantum ($0.10).

API

Base: https://edge-router.gpupulse.dev/api/v1 (or localhost:3825)

Route (recommend)

curl -X POST "$BASE/route" -H "Content-Type: application/json" \
  -d '{"task_type": "inference"}'

Execute (route + run)

curl -X POST "$BASE/execute" -H "Content-Type: application/json" \
  -d '{"task_type": "inference", "payload": {"model": "llama3.2:1b", "prompt": "hello"}}'

Task Types

• inference → local first, cloud fallback
• training → cloud GPU
• quantum → Wukong 72Q
• auto → cheapest available

Other

• GET /backends — list + status
• GET /stats — routing statistics
• GET /health — health check