Skip to main content

​
Which model should I use?

  • Claude Opus 4.6 (claude-opus-4.6) — most capable. Use for the hardest tasks that need maximum accuracy.
  • Claude Sonnet 4.6 (claude-sonnet-4.6, default) — best balance of capability and cost. Use for complex multi-step workflows.
  • GPT-5.4 mini (gpt-5.4-mini) — fast and efficient. Good for simple, well-defined tasks.

​
How do I get the live browser URL?

live_url is returned on session creation. Embed it in an iframe or open it in a browser. 
session = await client.sessions.create(task="Go to example.com")
print(session.live_url)

​
Getting blocked by a website

Stealth and proxies are active by default. If you’re still getting blocked:
  • Use a profile with logged-in cookies to bypass login walls.
  • Try a different proxy country to match the target region.
If it still doesn’t work, contact support inside the Cloud Dashboard — send us a link to the page where you’re getting blocked.

​
Rate limited (429 errors)

The SDK auto-retries 429 responses with exponential backoff. If persistent, you may need more concurrent sessions — contact support.

​
v2 vs v3 — which should I use?

v3 is the recommendation for everything. It’s a premium agent (not available in open source) that is significantly more capable than v2:
  • Much better at complex tasks and multi-step workflows
  • Much better at large data extraction
  • File system with persistent memory across tasks
  • Task scheduling with 1,000+ integrations (Gmail, Slack, and more)
v2 is the closest to the open-source experience — pure browser automation, nothing else. If the open source already works great for your use case, v2 is the natural fit. For everything else, use v3. 
# v3 (recommended)
from browser_use_sdk.v3 import AsyncBrowserUse

# v2 (simple browser-only tasks)
from browser_use_sdk.v2 import AsyncBrowserUse