2 min lesson
Composer and Auto
Put yourself in this case. "A platform lead worried about runaway spend asks how their engineers should choose models. What's the strongest, most concrete answer?" Give the clearest next step.
Step 1 of 2
Composer and Autothe daily driver and the router
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. is Cursor's own model line, and Composer 2.5The current Composer release, better at long-running tasks and at judging when a job needs a light touch versus deep work. Press Enter for the full definition. sits on the current roster beside Cursor's Grok 4.7Cursor and SpaceXAI's current lead Cursor model, in the weekly pool at $2 per million input tokens and $6 per million output, with a 256k context window and a 500k variant; above 256k input tokens it bills at 2x the standard rate. Press Enter for the full definition., 4.6 and 4.5 models. It is the recommended default for execution. The additional-usage rates show why: Composer 2.5 lists at $0.50 per million input tokens and $2.50 per million output tokens, against $4 in and $20 out for Claude Opus 5.5Anthropic's top Opus-tier model in Cursor at $4 per million input tokens and $20 per million output, 20% below Claude Opus 5, which it replaces. Press Enter for the full definition..
Auto modeCursor's automatic model router with Cost, Balance and Intelligence options that trade price against model capability. Press Enter for the full definition. is the surface of the Cursor Router, and it has three modes: Cost, Balance and Intelligence. Cost is the classic Auto logic, optimizes token spend and is the only mode on individual plans. Balance and Intelligence need the Router, which is currently available only on Teams and Enterprise plans, and they bill at the list price of whichever model a request is routed to. Admins control the Router: it is on by default for Teams, Enterprise must enable it manually and the underlying model display is hidden by default. The docs do not say which model each mode routes to, so don't promise engineers a specific one.
When a platform lead asks "which model," they're really asking how to keep spend predictable while output stays good. Answer with the loop (plan with a frontier model, execute with 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.), the standard-versus-thinking split so engineers self-select reasoning power, and Auto for people who don't want to think about it. Add the plan caveat: individual plans get Cost mode only, while Balance and Intelligence routing is a Teams and Enterprise setting an admin controls. That reframes the question from a taste debate into a governable habit, which is the answer that lands with someone responsible for the bill.
Learn more
Full explanation
Full explanation
When the model question comes, don't say "it depends." Name the two model categories, the plan-expensive/implement-cheap loop and what Auto does on an individual plan versus a Teams plan. Then tie it to the customer's concern: predictable spend with good output. Depth on model selection is one of the clearest signals that you actually use the product, because it's the question every platform team raises and most candidates fumble.
Learn more
Optional practice
Test yourself on Composer and Auto
QA customer on an individual plan asks you to turn on Balance routing for their engineers. What do you tell them?