Total Requests
-
-
Avg TPS
-
Tokens per second
Avg Latency
-
End-to-end
Success Rate
-
-
Semantic Cache
-
Hit rate
Avg Compression
-
Tokens saved
TPS Comparison
Latency Distribution
Error Breakdown
Model Comparison
Sort by: TPS | Latency
| Model | Requests | Success | Avg TPS | P50 Latency | P95 Latency | Avg Tokens In | Avg Tokens Out | Cache Read | Semantic | Upstream | Compressed | Reasoning | Errors |
|---|
Recent Requests
| Time | Model | Provider | Status | Latency | TPS | Tokens In | Tokens Out | Cache | Cache Source | Compressed | Reasoning |
|---|