get
https://app.revenium.ai/api/v2/analytics/token-breakdown-by-type
Returns token consumption over time grouped by token type: Input, Output, Cache Read, and Cache Creation. Useful for understanding prompt caching effectiveness — the ratio of Cache Read to Input tokens indicates how much of the prompt is being served from cache.
Recent Requests
Log in to see full request history
| Time | Status | User Agent | |
|---|---|---|---|
Retrieving recent requests… | |||
Loading…