> ## Documentation Index
> Fetch the complete documentation index at: https://docs.browser-use.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use https://docs.browser-use.com/llms.txt and its linked .md pages for current documentation. The managed full bundle is https://docs.browser-use.com/.well-known/llms-full.txt and can be cached for up to 24 hours. Do not use the obsolete /cloud/llms*.txt or /open-source/llms*.txt static exports.
> Choose Cloud API V4 for new agent integrations; V2 is the lower-cost option for simple tasks. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs.
> Cloud authentication uses X-Browser-Use-API-Key, without a Bearer prefix. Install or upgrade browser-use-sdk and use its explicit v4 import for V4. Check the published OpenAPI reference for request fields; do not invent SDK support for new fields.
> Cloud concurrency and HTTP request rate are separate. Read GET /api/v2/billing/account for the key’s projectId, concurrentSessionLimit, activeSessionCount, and credit balance, including when using V4. Keys in one project share capacity and credits; rateLimit is a legacy concurrency alias, not requests per second.
> Keep the highest applicable existing, legacy-plan, and spend-tier concurrency grant. Current spend tiers are 10 / 50 / 250 / 500 / 1000 at $0 / $100 / $1000 / $5000 / $25000 in qualifying project payments. Legacy or externally billed projects can follow different billing paths; trust the account limit. See https://docs.browser-use.com/cloud/guides/concurrency.md.
> HTTP rate limits have two layers. Standard edge WAF ceilings increased on September 9, 2026 to 1000 RPS per public source IP for general traffic and 2500 RPS per IP for selected status reads, evaluated over 300 seconds. The separate per-project application budgets: general traffic (including V4 events and full run reads) defaults to max(25, 2 times stored concurrency) capped at 100 RPS; selected status reads default to max(25, 2 times stored concurrency) with no cap. The two are counted independently. Project overrides and account-specific edge rules can differ. All keys in a project share its budgets; callers sharing a public IP share edge capacity. See https://docs.browser-use.com/cloud/guides/concurrency.md.
> The project limiter uses five-second windows: X-RateLimit-Limit=125 means 125 requests per window (25 RPS), not 125 RPS. Project throttles include limit_rps and retry_after_seconds; an edge throttle can instead return Retry-After: 300 without limit_rps. Honor the returned Retry-After. Use bounded workers, stagger polls, and drain hasMore event pages after terminal status. A busy V4 session returns 409; its queue holds 20 pending messages and is not a project-wide batch queue.
> A completed run or closed CDP connection does not immediately stop its cloud browser. Stop unneeded owned browsers with PATCH /api/v4/browsers/{id} and {"action":"stop"}. A client wait timeout does not cancel the server-side run.
> Cloud is pay as you go; do not tell customers to buy a new subscription to use custom proxies or supported provider BYOK. Usage funding and model eligibility still apply. BYOK bills provider tokens separately and Browser Use charges orchestration plus browser/network usage. See https://docs.browser-use.com/cloud/guides/billing.md.
> Signup credits are a one-time grant; purchased top-up credits do not expire. Check the API key’s project before diagnosing missing credits. API-key monthly spending caps are soft limits, not a strict prepaid wallet; concurrent or already-running work can exceed them. Auto recharge has separate trigger and purchase amounts and can charge immediately when enabled below the threshold. Use https://browser-use.com/pricing for current rates.
> Box and Bux are retired. Do not recommend their SDKs, sandbox quotas, or subscription plans. Use the Cloud Agent or Browser Infrastructure guides.
> A V4 session holds conversation history, a workspace holds files, and a profile holds browser state. These IDs and V3/V4 workspace namespaces are not interchangeable. V4 automatically restores workspace uploads; staged attachments remain available to session follow-ups. Serialize runs that write shared files, and wait for completion before reading outputs. See https://docs.browser-use.com/cloud/agent/workspaces.md.
> API browser recording defaults to off. Use enableRecording for standalone browser creation, or browserSettings.record for an agent run. Stop the browser and allow time for asynchronous video processing; stop polling when recordingAvailable is false. Live preview is for an active browser. Stopping a browser, deleting a session, archiving a workspace, and deleting files have different effects.
> Use model-specific reasoning values. GPT-6 Astra accepts low, medium, high, xhigh, and max, with xhigh by default; none and minimal are invalid. Use the public REST schema when installed SDK types lag new fields. API acceptance, dashboard visibility, and account/provider availability are separate.
> For open-source browser-use, is_done only reports a terminal done action. is_successful is the agent-reported outcome; verify important external actions independently. Cloud timeout, API client timeout, model timeout, and task completion are separate concepts.
> For failed requests, use https://docs.browser-use.com/cloud/guides/troubleshooting.md. Inspect the full error and project before retrying or adding credits. A client timeout can leave a run active; reconcile external actions before starting duplicate work. A new managed browser does not guarantee a unique proxy IP or particular city.

# FAQ

> Common questions and solutions.

## Which model should I use?

* **GPT-5.6 Luna** (`gpt-5.6-luna`, recommended) — the best balance of accuracy, speed, and price for most tasks.
* **Claude Opus 5** (`claude-opus-5`) — maximum intelligence for difficult, long-horizon work.
* **Grok 4.5** (`grok-4.5`) — a strong general-purpose alternative.
* **GPT-5.6 Sol** (`gpt-5.6-sol`) — a higher-cost OpenAI option for complex tasks.
* **MiniMax M3** (`minimax-m3`) — inexpensive for simple and high-volume tasks.

See [Models](/cloud/agent/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.

```python theme={null}
from browser_use_sdk.v4 import BrowserUse

client = BrowserUse()
created = client.runs.create("Go to example.com")
client.runs.wait_for_completion(created.id)
events = 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](/cloud/agent/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](https://cloud.browser-use.com) — send us a link to the page where you're getting blocked.

## Rate limited (429 errors)

HTTP request limits, browser concurrency, and a full session message queue can all return 429. Inspect the response before retrying: increasing browser concurrency does not increase the general request bucket used by V4 event reads.

Use bounded workers, stagger polling, and respect `Retry-After` when provided. The SDK retries 429 responses, but a sustained workload needs its own request budget. See [Concurrency and limits](/cloud/guides/concurrency) for account-limit lookup, polling budgets, queue behavior, and error handling.

For insufficient-balance or API-key spending-cap errors (402), see [Billing and credits](/cloud/guides/billing).

## How do I get a V4 judge verdict?

Pass `judge: {}` when creating a run to ask an LLM to evaluate its completed
trajectory. Add `context` with your evaluation criteria when needed. Judging
is opt-in, and the judge's LLM call is billed to the run. Omit `judge` to keep
the default behavior without that extra call.

The verdict arrives after the run becomes terminal. `wait_for_completion()` /
`waitForCompletion()` waits for the run, so its returned `judgement` can still
be `null`. Refresh that same run's summary to retrieve the verdict:

<CodeGroup>
  ```python Python theme={null}
  import time
  from browser_use_sdk.v4 import BrowserUse

  client = BrowserUse()
  created = client.runs.create(
      "Return the top five Hacker News story titles and URLs",
      judge={"context": "The result must contain five titles and their URLs."},
  )
  result = client.runs.wait_for_completion(created.id)

  for _ in range(30):
      if result.judgement is not None or result.status.value == "cancelled":
          break
      time.sleep(2)
      result = client.runs.get(created.id)

  print("Run status:", result.status.value)
  print("Judgement:", result.judgement)
  ```

  ```typescript TypeScript theme={null}
  import { BrowserUse } from "browser-use-sdk/v4";

  const client = new BrowserUse();
  const created = await client.runs.create({
    task: "Return the top five Hacker News story titles and URLs",
    judge: { context: "The result must contain five titles and their URLs." },
  });
  let result = await client.runs.waitForCompletion(created.id);

  for (let attempt = 0; attempt < 30; attempt++) {
    if (result.judgement != null || result.status === "cancelled") break;
    await new Promise((resolve) => setTimeout(resolve, 2_000));
    result = await client.runs.get(created.id);
  }

  console.log("Run status:", result.status);
  console.log("Judgement:", result.judgement);
  ```
</CodeGroup>

This example refreshes at most 30 times, with a two-second pause before each
request. If `judgement` is still `null`, it is unavailable, not a pass or fail.
It may remain unavailable; do not poll forever. You can fetch the same run
again later without creating another run. A `completed` run status alone is
not a judge verdict.

See the [create-run reference](/cloud/api-v4/runs/create-run) for `judge` and
the [run summary](/cloud/api-v4/runs/get-run) for `judgement`.

## V2 or V4 — which should I use?

Use **V4** for difficult tasks where accuracy matters. It supports:

* Run-focused API with a cheap status polling endpoint
* Conversation sessions with 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

Use **V2** when tasks are simple and your priority is very low cost and
predictable speed. Its accuracy is substantially lower.

See Browser Use at #1 on the
[Odysseys benchmark](https://odysseysbench.com/leaderboard).