mirror of
https://github.com/browser-use/browser-use.git
synced 2026-09-14 19:59:47 +08:00
Saurav Panda
5953df7d2f
0.13.8 shipped bu-2-0-mini-preview as the ChatBrowserUse default, which means Agent(task=...) with no llm - and every bare ChatBrowserUse() - silently moved onto a preview model on upgrade, with no code change on the caller's side. Two problems with that. A preview id can change behaviour or be renamed, so it is the wrong thing to reach by omission. And per-token price is the wrong yardstick for an agent: total cost is tokens-per-step times steps, and steps is a function of model quality, so a cheaper-per-token model that needs more steps to finish can cost more and take longer. We do not yet have a per-task benchmark number for mini to say which way that goes. bu-2-0-mini-preview stays a first-class option: still accepted, still priced, still what the examples demonstrate. It is just opted into by name now rather than landed on by default. Revisit once the benchmark number exists.
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
"""
|
|
Example of the fastest + smartest LLM for browser automation.
|
|
|
|
Setup:
|
|
1. Get your API key from https://cloud.browser-use.com/new-api-key
|
|
2. Set environment variable: export BROWSER_USE_API_KEY="your-key"
|
|
"""
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
from browser_use import Agent, ChatBrowserUse
|
|
|
|
load_dotenv()
|
|
|
|
if not os.getenv('BROWSER_USE_API_KEY'):
|
|
raise ValueError('BROWSER_USE_API_KEY is not set')
|
|
|
|
|
|
async def main():
|
|
# A bare `ChatBrowserUse()` gives you `bu-2-0`, the premium default (as does 'bu-latest').
|
|
# `bu-2-0-mini-preview`, used below, is cheaper and faster per token but is in preview, so
|
|
# you opt into it by name rather than getting it by default.
|
|
# ChatBrowserUse can also route to provider-prefixed models (e.g. 'anthropic/claude-sonnet-4-6',
|
|
# 'openai/gpt-5.5', 'google/gemini-3-pro') through the same gateway - see
|
|
# browser_use_provider_models.py.
|
|
agent = Agent(
|
|
task='Find the number of stars of the browser-use repo',
|
|
llm=ChatBrowserUse(model='bu-2-0-mini-preview'),
|
|
)
|
|
|
|
# Run the agent
|
|
await agent.run()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
asyncio.run(main())
|