Files
browser-use__browser-use/examples/models/browser_use_provider_models.py
Saurav Panda 4cbc5dfa4d feat(llm): accept provider-prefixed models in ChatBrowserUse
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
2026-06-10 12:03:51 +05:30

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())