BU 2.0

Browser Use's browser-driving model, released 27 Jan 2026: 83.3% accuracy versus 74.7% for BU 1.0 at the same speed (~62s per task), "matches Claude Opus 4.5 accuracy while being 40% faster". Invoked as ChatBrowserUse(model="bu-2-0"); $0.60/1M input and $3.50/1M output tokens.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.