# BU Ultrafast is live By Steven Van · 2026-10-31 The bu-ultrafast model has a 22-second median task time and is available on all US Browser Use Cloud plans, with priority-rate token billing. BU Ultrafast, [Browser Use]()'s fastest browser agent, is now on every Browser Use Cloud plan in the US, including the free plan. It was behind a waitlist until Oct 30, as [announced]() on October 31. ## Speed and cost The median Ultrafast task takes 22 seconds and costs $0.0064. The default agent on GPT-6 Luna takes 79 seconds and costs $0.0098, so Ultrafast is more than 3x faster and cheaper per task. The figures are medians of completed runs from Oct 16 to 29, 2026, with at most 1,000 runs per project. Ultrafast covers 12,238 runs across 134 projects. The default agent covers 146,120 runs across 9,473 projects. In the 8 projects with 20 or more runs on both, Ultrafast was faster and cheaper in all 8. Cost is the model and search charge per run, and browser and proxy are billed separately. ## How to use it Set model to bu-ultrafast in the run request. Nothing else changes. The example in the announcement posts a task such as "Find the cheapest flight from SFO to JFK next Friday" to the /api/v4/runs endpoint with that model value. For more reasoning per step, bu-fast is the same agent. Anyone who joined the waitlist already has access and has nothing to do. ## Pricing bu-ultrafast runs GPT-6 Luna on OpenAI's priority tier, so tokens bill at priority rates, which are 2x standard. bu-fast bills at standard rates, and so does bu-ultrafast on HIPAA projects. Both models work on the free plan. [![]()]() ![Browser Use]() Browser Use Open-source browser automation platform for AI agents — let LLMs drive a real browser to research, fill forms, scrape, and complete multi-step tasks. [View Browser Use →]() Sources [Original source]() [Read BU Ultrafast is live on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/blog/browser-use-bu-ultrafast-is-live