Total Requests
—
across all models
Throughput
—
requests / second avg
Tokens Processed
—
total tokens served
Error Rate
—
of all requests
Request Volume
Hourly request count by model
Throughput
Requests per second
Latency Distribution
Average p50 / p95 / p99 over window
Model Breakdown
Per-model performance summary
| Model | Requests | p50 ms | p95 ms | Errors |
|---|---|---|---|---|
| Loading… | ||||