Windsurf Launches Adaptive Model Router and Removes Daily Limits for Max Users

Apr 8, 2026 · Updated Apr 25, 2026

Windsurf, an AI-native code editor from Cognition, launched an Adaptive model router—an intelligent system that selects the optimal model—and a redesigned model picker. These updates clarify the costs associated with different AI models while automating the selection process to balance performance and expense.

Quota friction often disrupts developer flow, especially when daily caps trigger during heavy coding sessions. By removing daily limits for Max plan users and providing explicit pricing context, Windsurf is shifting toward a more transparent, flexible usage model that better accommodates the non-linear nature of professional software development.

You can access these features by downloading the latest version of the Windsurf editor. The Adaptive model router is currently available at promotional rates of $0.50 per 1M input tokens and $2 per 1M output tokens for two weeks, while Max plan subscribers can now exhaust weekly quotas without daily throttling.

View the full update on windsurf.com

Windsurf

@windsurfApr 6

Today Windsurf is getting a few updates: an Adaptive model router, a redesigned model picker with more pricing context, and the removal of daily limits for Max. We heard you loud and clear on pricing being too opaque and, in some cases, too restrictive. These updates are meant to address that.

21285

View on X