Cursor Router is Cursor's new built-in model routing system that automatically selects the right AI model for every coding request. Instead of sending every task to the same expensive frontier model, it classifies each request and dispatches it to the most cost-effective model capable of handling it. The result, according to Cursor's own A/B tests across millions of live requests, is frontier-quality output at 60% lower cost.
The problem with picking one model
About 60% of Cursor users stick to a single model as their daily driver. That sounds reasonable, but it means routine tasks like renaming a variable, writing a docstring, or tweaking a CSS class all get priced at the same rate as a complex multi-file refactor. AI spend grows much faster than output quality when every request hits a frontier model, regardless of whether it needs one.
The fix seems obvious in retrospect: classify the request first, then route it. But doing this well is harder than it sounds. You need to know what each model is actually good at, account for the cost of switching models mid-conversation (cache misses), and measure success in a way that reflects real developer behavior, not just benchmark scores.
How the classifier works
At its core, Cursor Router is a classifier trained on 600k+ live requests and evaluated in an online A/B test across millions of live requests, optimizing for user satisfaction as a reward. It looks at the query, surrounding context, task complexity, and domain before deciding where to send the request.
Don't miss what's next in AI
Join 300,000+ engineers and researchers who get the signal, not the noise.
- Full access to in-depth AI research breakdowns
- Be the first to know what's trending before it hits mainstream
- Daily curated papers, repos, and industry moves