API Status & Monitoring

Real-time health monitoring of all AI model APIs. Track latency, error rates, and usage costs.

Auto-refresh every 60s ·
-
Total Calls (1h)
-
Errors (1h)
-
Error Rate
-
Avg Latency
-
Operational
-
Degraded
Providers
Models
Endpoints
Cost (24h)
Recent Errors
Provider Status Total Calls Errors Error Rate Avg Latency Min / Max Last Checked
Loading...
Model Provider Calls Errors Error Rate Avg Latency Tokens Used Cost
Loading...
Endpoint Total Calls Errors Error Rate Avg Latency Total Cost
Loading...
Cost by Provider (Last 24h)
Loading...
Recent Errors (Last 24h)
Loading...