Timeseries queries
Time-bucketed cache metrics over a window. Every timeseries query must includeinterval (or the deprecated intervalInSeconds). Each example below posts JSON to:
Authorization: Bearer <your_api_key> and Content-Type: application/json. To keep the snippets short, only the JSON body is shown; the wrapper is identical to the Overview Quick Start.
The examples below pin the model side with
{"fieldName": "virtualModelName", "operator": "IS_NULL", "value": true}. Flip to false for virtual-model-only series.Hourly savings by namespace
Hourly savings by namespace
Track cost savings per namespace over time:
Hourly p99 lookup latency by cache type
Hourly p99 lookup latency by cache type
Watch for regressions in cache lookups:
Hourly tokens read from cache
Hourly tokens read from cache
Track cache read volume per cache type:
Hourly hits vs misses
Hourly hits vs misses
Volume by
cacheLookupStatus over time:Daily savings over a week
Daily savings over a week
Daily cost savings across a 7-day window:
5-minute lookup latency in an incident window
5-minute lookup latency in an incident window
Fine-grained breakdown to investigate a regression:
Hourly savings for semantic cache only
Hourly savings for semantic cache only
Combine cache-type filter with namespace breakdown: