Real-time monitoring and analytics for your AI API gateway infrastructure
Total Requests
47,293
+12% from yesterday
Average Latency
187ms
-8% improvement
Success Rate
99.8%
+0.2% uptime
Error Rate
0.2%
-0.1% reduction
Request Volume
Response Times
API Endpoints Performance
| Method | Endpoint | Requests/min | Avg Response | Success Rate | Status |
|---|---|---|---|---|---|
| POST | /v1/chat/completions | 234 | 245ms | 99.7% | Healthy |
| POST | /v1/embeddings | 156 | 123ms | 99.9% | Healthy |
| GET | /v1/models | 45 | 89ms | 100% | Healthy |
| POST | /v1/images/generations | 23 | 3.2s | 98.5% | Slow |
| POST | /v1/audio/transcriptions | 12 | 1.8s | 99.2% | Healthy |