tokenstat
tokenstat

Help center

Reading your usage

Most tokens are cache reads, which cost less than fresh input. Learn how to interpret token totals, context size, and list-rate costs.

2 guides in Reading your usage.

Why cache reads dominate your token count
Most of your tokens are cache reads, and they cost a fraction of fresh input. That is why a raw token number tells you almost nothing, and why a big context is not the expense people assume.
How confident is each number, and what confidence actually means
Every event carries exact, strong, or derived. It is a statement about identity and double counting, not about arithmetic, and knowing the difference tells you which totals can drift.

Human-led and verified · AI-assisted content · AI tools may help draft, edit, maintain, and improve grammar or clarity. Nothing is published automatically; every change is reviewed by the human maintainer.