1 min lesson
The core token-efficient loop
Use "Letting a frontier model write all your code burns the token budget fast" to say what you would do next.
Step 1 of 2
The core token-efficient loopplan expensive, implement cheap
The single most-repeated cost-and-quality pattern across Cursor's own engineers: use your smartest thinking modelA reasoning model (shown with a brain icon in Cursor's picker) that spends extra compute before answering; reach for it on complex, nuanced work and a standard model for fast, simple tasks. Press Enter for the full definition. in Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. to generate and validate a plan, then hand off to a cheaper, faster coding model to execute the to-dos. Letting a frontier model write all your code burns the token budget fast - you don't need the expensive reasoning model once the plan exists. This is the loop you coach platform teams to standardize, because it saves both tokens and time.
“If your engineers are running an expensive frontier model for everything, they'll blow through the token budget fast. The pattern we recommend is plan with the smart model, then switch to a cheaper, faster one - ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. - to actually write the code. The frontier model only has to reason about the approach, not output all the code. That one habit is the biggest lever on both cost and quality.”