Unclear It is not clear whether the per-million-token estimate is shown to users anywhere.
What
Claude Code has a warning about usage quota, the amount you may use, that is tied to resuming a session. Its logic has been reorganised. It now reads its settings through a server-controlled switch, tengu_eager_brooks. It can also work out what percentage of quota a million tokens would use for a model with a one-million-token context. Tokens are the small pieces of text that usage is counted in.
The way it works out the percentage and the source of your plan tier is unchanged.
Why
The per-million-token figure gives an estimate of quota cost at that size of context.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
It is not clear whether the per-million-token estimate is shown to users anywhere.