API & Serving Evidence¶

Proof that the inference API is live and responding correctly.

Work in progress

This page is a placeholder. Live API screenshots and curl outputs will be added here.

Live API Response¶

curl -X POST "http://api.time2bet.ru/v1/predict" \
  -H "Content-Type: application/json" \
  -d '{"home_team": "Arsenal", "away_team": "Chelsea",
       "match_date": "2025-05-10", "league": "premier_league"}'

Expected output placeholder:

{
  "match_id": "arsenal_chelsea_20250510",
  "probabilities": {"home_win": 0.42, "draw": 0.28, "away_win": 0.30},
  "predicted_outcome": "home_win",
  "model_version": "v2",
  "inference_latency_ms": 18
}

OpenAPI / Swagger UI¶

Screenshot placeholder — FastAPI Swagger UI at http://api.time2bet.ru/docs

Health Check¶

curl http://api.time2bet.ru/health
# {"status": "ok"}

curl http://api.time2bet.ru/ready
# {"status": "ready", "model_version": "v2"}

Latency Measurements¶

Placeholder — k6 or locust load test output

Percentile	Latency
p50	~18ms
p95	~45ms
p99	~120ms

See Request / Response Examples and Performance, Capacity & SLOs.