mirror of
https://github.com/browser-use/browser-use.git
synced 2026-09-14 19:59:47 +08:00
4cbc5dfa4d
ChatBrowserUse now accepts provider-prefixed model ids (anthropic/*, openai/*, google/*) alongside the bu-* aliases and browser-use/* models, so a single BROWSER_USE_API_KEY can reach them. bu-* aliases and the bu-latest -> bu-2-0 normalization are unchanged; bare ids are rejected with guidance toward the provider/model form. Also matches provider-prefixed Claude Sonnet ids in the Agent llm_screenshot_size auto-config, so the screenshot optimization isn't lost when Claude is reached via ChatBrowserUse. Adds an example, a README FAQ entry, and tests. ENG-5060
47 lines
1.2 KiB
Python
47 lines
1.2 KiB
Python
"""
|
|
Point ChatBrowserUse at provider-prefixed models via the Browser Use gateway.
|
|
|
|
`ChatBrowserUse` isn't limited to the `bu-*` models - it also accepts
|
|
provider-prefixed ids:
|
|
|
|
- 'anthropic/claude-sonnet-4-6'
|
|
- 'openai/gpt-5.5'
|
|
- 'google/gemini-3-pro'
|
|
|
|
A single `BROWSER_USE_API_KEY` reaches Claude, GPT, and Gemini without
|
|
juggling separate OpenAI / Anthropic / Google keys. For the best speed and
|
|
cost, the default `bu-*` models are still recommended.
|
|
|
|
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')
|
|
|
|
# Swap this for any provider-prefixed id the gateway supports, e.g.
|
|
# 'openai/gpt-5.5' or 'google/gemini-3-pro'
|
|
MODEL = 'anthropic/claude-sonnet-4-6'
|
|
|
|
|
|
async def main():
|
|
agent = Agent(
|
|
task='Find the number of stars of the browser-use repo',
|
|
llm=ChatBrowserUse(model=MODEL),
|
|
)
|
|
await agent.run()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
asyncio.run(main())
|