Settings
Usage
What you spent and where: tokens, cost, cache hit rate, broken down by day, model, project and session.
What the page shows
Usage is the record of work already done, measured in tokens rather than in Credits. Pick a date range (a preset or a custom span) and the page reports:
| Card | Meaning |
|---|---|
| Your Cost | What the range cost you. PandaOS Cloud turns are billed in Credits and contribute nothing here, which is why the label says your cost on a mixed account. |
| Total Tokens | Input plus output plus cache traffic, with the in/out split underneath. |
| Cache Hit Rate | How much of the context was served from cache instead of being re-sent. A high rate is why a long conversation stays affordable. |
| Sessions | How many chats ran in the range, and how many turns they took. |
Breakdowns
Below the cards, the same range is broken down three ways:
- By day, as a chart you can switch between metrics, to spot the day a long agent run happened.
- By model, so you can see what the expensive models actually cost you compared with the cheap ones.
- By project, expandable down to individual sessions, so a single runaway chat is findable.
The range you choose is remembered while the app is open, so leaving the page and coming back does not reset it.