FAQ

Common questions and solutions.

Which model should I use?

• Claude Opus 5 (claude-opus-5) — maximum intelligence for difficult, long-horizon work.
• GPT-5.6 (gpt-5.6) — fast on complex tasks.
• Gemini 3.5 Flash (gemini-3.5-flash) — fast for simpler tasks.
• MiniMax M3 (minimax-m3, default) — cheapest for simple and high-volume tasks.

See Models for the complete V4 picker and pricing.

How do I get the live browser URL?

The V4 run’s browser.ready event contains live_view_url. Embed it in an iframe or open it in a browser.

created = await client.runs.create("Go to example.com")
await client.runs.wait_for_completion(created.id)
events = await client.runs.events(created.id, limit=100)
ready = next(event for event in events.events if event.type == "browser.ready")
print(ready.data["live_view_url"])

Poll events until browser.ready appears if you need the URL while the run is still active. See Human in the loop for a complete flow.

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 vs v4 — which should I use?

Use v4 for new agent integrations. It is designed for long-horizon work:

• Run-focused API with a cheap status polling endpoint
• Conversation sessions with queued and interrupting follow-ups
• Persistent workspaces and turn-scoped file attachments
• Incremental events for custom UIs and monitoring
• Per-run cost totals, cost caps, and optional judgement

V3 remains available for existing integrations and older features that have not moved to V4, including server-side structured-output schemas and automatic script caching. V2 is the legacy API closest to the open-source browser agent.

# v4 (recommended for new agent runs)
from browser_use_sdk.v4 import AsyncBrowserUse

# v3 (existing session-based integrations)
from browser_use_sdk.v3 import AsyncBrowserUse as AsyncBrowserUseV3