Request Latency
0 ms avg
My Workspace
Lumen Observability
Monitor Lumen request health in real time with governed metrics from the execution pipeline.
Sections
Workspace pages
Lumen Observability Dashboard
Request latency, model latency, cache hit rate, cost per request, and failure rate.
Loading metrics…
Model Latency
0 ms avg
Cache Hit Rate
0%
Cost per Request
$0.000000 avg
Failure Rate
0%
Usage by Model
| Model | Requests | Cost (USD) | Avg Latency (ms) | Cache Hit % | Failure % |
|---|