Introducing Cursor Router

This post introduces Cursor Router, an intelligent model routing system for teams and enterprises. It classifies requests before a model runs, routing to the best model based on query, context, task complexity, and domain. The system was trained on 600k+ live requests and evaluated across millions of live requests in an online A/B test, optimizing for user satisfaction (AFC) and cost savings. It offers three modes: Intelligence, Balance, and Cost, allowing users to adjust the cost-intelligence trade-off. The router is cache-aware in both training and evaluation. Online A/B tests were used for evaluation, measuring user satisfaction and code keep rate. Early access customers reported 30-50% cost savings with no decrease in quality. Cost per commit analysis showed lower costs for Intelligence and Balance modes compared to direct use of Opus 4.8 or Fable.