Cursor Launches Cursor Router to Optimize LLM Selection and Reduce Costs
Cursor has launched "Cursor Router," an intelligent model routing system designed to automatically select the optimal large language model (LLM) for a given task. The feature is currently available across all surfaces for Teams and Enterprise plans. This system allows development teams to achieve frontier-quality coding assistance while reducing LLM API costs by up to 60%. It addresses the industry-wide challenge of balancing high performance with the high costs of advanced AI models. Administrators can configure the router per team, allow or block specific models, set defaults, and disable certain optimization modes. Early access testing showed no drop-off in quality compared to routing all requests to Claude 3 Opus.
## BACKGROUND
Cursor is an AI-first code editor designed to help developers write and review code using AI agents. LLM routing is a technique that analyzes prompt difficulty to direct tasks to the most cost-effective model tier, using cheaper models for simple tasks and reserving expensive frontier models for complex ones.