Distribution queries
Aggregated snapshots of cache metrics over a time window. Every 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 (and swap groupBy: ["modelName"] for groupBy: ["virtualModel"]) for virtual-model-only cache stats.Top namespaces by tokens served from cache
Top namespaces by tokens served from cache
Sum of
cacheReadInputTokens per namespace. Surfaces which buckets do the most work:Lookup latency percentiles by cache type
Lookup latency percentiles by cache type
p50, p90, and p99 lookup latency grouped by cache type:
Savings by model
Savings by model
Sum of cost savings per underlying model:
Semantic cache only
Semantic cache only
Restrict to a specific cache type and break savings down by model:
Filter namespaces by prefix
Filter namespaces by prefix
Use
STRING_STARTS_WITH on cacheNamespace, handy when prod and staging share a cache type:Hit vs miss breakdown
Hit vs miss breakdown
Group by
cacheLookupStatus to see hits vs misses per cache type:Tokens written vs read
Tokens written vs read
Compare cache-creation tokens to cache-read tokens per namespace: