2 min lesson
Legacy plans: why one chat can burn many requests
Rebuild the parts of "Legacy plans: why one chat can burn many requests", then say why each one matters.
Step 1 of 2
Legacy plans: why one chat can burn many requests
The most confusing billing ticket on legacy request-based plans is a single chat that burned a surprising number of requests. The answer is a mechanism, not a bug, and walking it through calmly is what closes the ticket.
- Max Mode
- Available only on legacy request-based plans. It extends a model's context window beyond the default limit and is billed at the model's API rate plus 20%.
- Why one chat adds up
- A long chat on a big context window is billed at that raised rate, so it can consume many requests. That is pricing working as designed.
- The fix on a legacy plan
- If the user doesn't need the larger context, turn Max Mode off.
- Current plans
- Usage is tokens drawn from one weekly pool at model-specific rates, shared across Agent, CLI and Cloud AgentsAgents that run in a Cursor-managed virtual machine, check out the repo, do the work and open a pull request, then shut down, with no load on your laptop. Press Enter for the full definition.. Third-party models bill at API list price from prepaid credit.
Walk the user through the mechanism: on a legacy plan, Max Mode trades a bigger context window for a higher request count.
"That chat isn't a glitch. You were on Max Mode, which extends the context window and is billed at the model's API rate plus 20% on your legacy plan, so one long chat can consume many requests. If you don't need the larger context, turn Max Mode off. Current plans work differently: usage is tokens drawn from a weekly pool."