Dashboard
Inference Requests
2.41M
+14.2%
Active Models
38
+3 this week
Median Latency
47ms
-12.3%
Error Rate
0.14%
+0.02%
Inference Endpoints
6 active| Endpoint | Model | P99 Latency | Throughput | Errors | Status | |
|---|---|---|---|---|---|---|
| /v1/chat/completions | Aether-70B | 142ms | 1,847 rpm | 0.04% | Online | ··· |
| /v1/embeddings | Aether-Embed-v2 | 38ms | 4,210 rpm | 0.01% | Online | ··· |
| /v1/completions | Aether-7B | 67ms | 2,938 rpm | 0.12% | Online | ··· |
| /v1/images/generate | Aether-Vision | 2.4s | 312 rpm | 1.83% | Degraded | ··· |
| /v1/audio/transcribe | Aether-Audio | 890ms | 574 rpm | 0.28% | Online | ··· |
| /v1/rerank | Aether-Rerank | 52ms | 1,127 rpm | 0.02% | Online | ··· |