Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Usage & LimitsArea: what it touches
Internal ChangesKind: in v2.1.301,
Internal ChangesSection of the release
What
Tokens are the small chunks of text that models read and write, and they are what usage is measured in. Claude Code now keeps a separate running total of the tokens a session has spent, alongside its existing record of model usage. The total counts four kinds:
Input tokens
Output tokens
Tokens read from the cache
Tokens written to the cache
Why
This is a building block. A separate token count could later support limits or reports based on tokens. Nothing you see changes because of it on its own.
