System Status
Real-time performance metrics for all AI services
Overview
Total Requests
-
Success Rate
-
Last 24 hours
Avg Latency
-
End-to-end
Avg Throughput
-
tokens / second
Services
Updated --Provider
Model
Requests
Status
Latency
Throughput
Loading...
Historical Trends
No trend data available
All metrics are calculated over a 24-hour rolling window.
Data refreshes automatically every 30 seconds.