Inference Platform

Control Plane Dashboard

Production operator view for routing, usage, cache efficiency, and rapid prompt validation.

API healthy Redis online Demo mode Routing: smart-router

P95 Latency

218ms

-11% vs baseline

Cache Hit Ratio

67.4%

+9% vs baseline

Requests (24h)

1.4M

+23% vs baseline

Cost / 1K req

$4.82

-6% vs baseline

Live Playground

Generate With Backend API

POST /api/v1/generate

Demo mode is enabled. Responses and logs are simulated for preview.

Usage Trend

24h Request Volume

Operational Activity

  • API key rotation policy enabled
  • Rate limiting bumped for tenant enterprise-a
  • Fallback route triggered 12 times in the last hour
  • Prometheus scrape health is stable

Request Logs

Recent Requests

No request logs yet for this user.