AI Agent News/stories/browser-use-1-0-6-makes-bu-4-0-the-default-model-raising-token-costs.md

Browsers

Browser Use 1.0.6 makes BU 4.0 the default model, raising token costs

Release 1.0.6 of the browser-use Python package makes BU 4.0 the default model for agents that do not set an llm. BU 4.0 tokens cost 15 times as much as bu-fast, so runs without an explicit model will cost more.

Source: github.com/browser-use/browser-use/releases/tag/1.0.6

Release 1.0.6 of the browser-use package makes BU 4.0 the default model. Agent(task) and ChatBrowserUse() now run bu-4.0 on the Browser Use gateway instead of bu-fast. Developers can pass llm='bu-4.0-mini' for simple tasks at the lowest cost, or llm='bu-4.0-pro' for the hardest ones.

BU 4.0 tokens are priced at $1.80 per million input tokens and $9.00 per million output tokens, against $0.12 and $0.60 for bu-fast. The default mode also runs at high rather than medium reasoning. In one short test task, the cost rose from $0.0014 to $0.022. Passing llm='bu-fast' keeps the previous model and price.

The release also changes first-run behavior. The first run without a key opens a Browser Use login and continues after approval. Cloud browsers now print their live-view link, and judge gotchas stay grounded in what the run observed.

Why it matters if you build agents

Agents that omit the llm argument will now spend considerably more per token after upgrading, so check token budgets first. Pinning llm='bu-fast' preserves the old model and price, while bu-4.0-mini is the cheaper BU 4.0 option for simple steps.

Scripts or CI jobs that run without a stored key will now hit a login prompt on first run, so plan for that before deploying.

Get stories like this every weekday

One short email with the day's agent tooling news.

Subscribe