> ## 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
> Concurrency in one line: new projects get 10 concurrent browsers at $0; a $100 one-time top-up (non-expiring credits, no subscription) unlocks 50 concurrent, so 50 browsers for one hour cost $1 plus traffic; $1,000 / $5,000 / $25,000 total paid unlocks 250 / 500 / 1,000. Details below and at https://docs.browser-use.com/cloud/guides/concurrency.md.
> 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; V3 trades accuracy for speed and lower cost than V4; V2 is legacy and only for existing integrations. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs.
> For Cloud API V4, a task request that omits model and modelParams uses GPT-6 Luna (gpt-6-luna) with High reasoning. Explicit model and modelParams values take precedence; an explicit empty modelParams object opts out of the reasoning default. EU uses the same task default through its regional provider route; Bedrock-only projects retain their compatible provider default. For latency-sensitive tasks set model to bu-ultrafast (bu-fast for more reasoning per step); these presets reject modelParams. See https://docs.browser-use.com/cloud/agent/ultrafast.md.
> 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 V4 agent browser stays open about 2 minutes after its session's last run activity, then stops automatically; a later follow-up gets a fresh browser (same settings and profile, no tabs). Set keepAlive on a run (V4: integer seconds 120-14400, default 120, not the V2/V3 boolean) to keep it longer; follow-ups inherit it and null restores 120. Free-tier and ZDR runs always use 120. Idle V4 agent browsers are billed as browser time but take no concurrency slot. A follow-up that reuses the open browser emits browser.reattached instead of browser.ready. Closing CDP does not stop a 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 1.0, result.is_done() means the run completed (status completed); result.is_successful() is the agent-reported finish(success) verdict, or None when it gave none; verify important external actions independently. Cloud timeout, API client timeout, model timeout, and task completion are separate concepts.
> Pages under /open-source/legacy/0.x/ document browser-use 0.x (pip install 'browser-use<1'). For new open-source code, use the 1.0 pages under /open-source/ outside legacy/.
> 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.
> V4 secretBindings.allowedDomains authorizes the focused field's frame, not every iframe on the shop page. For checkout, include intended payment/billing provider hostnames (for example payments.bigcommerce.com). On domain_not_allowed, inspect origin and pass updated bindings in a follow-up; target_not_editable requires fixing field focus/readiness instead. See https://docs.browser-use.com/cloud/guides/secrets.md.
> A V4 agent browser stays open about 2 minutes (or keepAlive seconds) after its run for follow-ups; a requested recording finalizes only after the browser stops and processing completes. Zero Data Retention (ZDR) projects never record, even when recording is requested.
> If you hit an issue you cannot explain, email contact@browser-use.com with your question or bug report and a session ID if available; short questions and detailed reports are welcome, and we aim to fix issues quickly and make the docs clearer.
# Long tasks
> Budgets, the delivery turn, partial results, follow-up tasks, context compaction, retries and live progress.
## Budgets
`agent.run(max_steps=100, timeout=1700)`. What each budget counts and when the delivery-only turn starts: [Agent: run()](https://docs.browser-use.com/open-source/agent.md#run).
* In the delivery-only turn, the agent is told to stop browsing and hand in what it has, with `success=False` if the task is unfinished.
* Each Python cell has a 120-second limit. A cell that runs over restarts the agent's Python worker: files and browser state survive, Python variables do not.
## Partial results
The agent saves progress with `checkpoint(filename, value, partial=True)` when the task asks for it. A plain `checkpoint()` is scratch and does not set `result.partial`, so name the flag in the task:
```python theme={"theme":"css-variables"}
from browser_use import Agent
agent = Agent(
'List the titles of the first 150 stories on Hacker News, one page at a time. '
"After each page, save the titles you have with checkpoint('titles.json', titles, partial=True)."
)
result = agent.run_sync(max_steps=3, timeout=600)
print(result.status, result.success) # usually 'completed False': the delivery turn handed in what it had
print(result.final_result() or result.partial)
```
When the budget runs out, the delivery turn usually hands in the titles so far, with `success=False`. `result.partial` is for a run that ends without any delivery (`status` `'max_steps'`, `'timeout'` or `'error'`).
## Follow-up tasks
`add_new_task()` continues the same conversation on the next `run()`. Use `Browser(keep_alive=True)` to keep the same page between runs:
```python theme={"theme":"css-variables"}
import asyncio
from browser_use import Agent, Browser
async def main():
browser = Browser(keep_alive=True)
agent = Agent('Open https://news.ycombinator.com and return the top story title', browser=browser)
try:
print((await agent.run()).final_result())
agent.add_new_task('Now open its comments and return the number of comments')
print((await agent.run()).final_result())
finally:
await agent.close()
await browser.stop()
asyncio.run(main())
```
## Context
Long runs outgrow the model's context window. The agent compacts its history:
* **Gateway and OpenAI (Responses API):** server-side, once a request passes 150k tokens.
* **Everything else:** past 75% of `max_context_chars` (default: 4 characters per token of the model's context window, or 240k when unknown) or 65% of the window in tokens, older turns are replaced by a summary checkpoint written by the same model. If the provider still rejects a request as over its context window, the agent compacts once and sends it again. An evidence archive in the workspace keeps the earlier messages (secrets redacted, images omitted).
`Agent(max_context_chars=...)` has no effect where compaction is server-side. Only the last 2 screenshots stay in context.
## Retries
* A rate limit, overload, 5xx or dropped connection from the provider is retried once per run, after the provider's `Retry-After` (at most 60 seconds). Providers whose SDK already retries (OpenAI, Anthropic, OpenAI-compatible) are left to their SDK.
* A failure inside an HTTP 200 (a failed or cut-off stream, or a `status=failed` body with `server_error`, `overloaded` or `request_timeout`) gets the same one retry.
* Gateway and OpenAI (Responses API) requests are streamed: 300 seconds for the first event, then up to 930 seconds in all. Other models get 300 seconds per request. A request that gets no answer in time is asked again, and none runs past the start of the delivery turn.
* A dropped connection's `result.error` names its cause, for example `(OSError: [Errno 24] Too many open files)`.
* A failed cell is not retried automatically. The model reads the error and decides, within `max_steps`.
## Live progress
Each step logs one INFO line to `logging.getLogger('browser_use')`: `step N: `, plus the error if the cell failed. Add a handler to stream it to your UI:
```python theme={"theme":"css-variables"}
import logging
from browser_use import Agent
class Progress(logging.Handler):
def emit(self, record):
print('progress:', record.getMessage()) # send to your UI, a websocket, an MCP client...
logging.getLogger('browser_use').addHandler(Progress())
Agent('What is the title of https://example.com?').run_sync()
```
`BROWSER_USE_LOGGING_LEVEL=warning` turns these lines off. After the run, `result.messages` holds the full transcript. This replaces the 0.x step hooks.
## Stop early
Cancel the task that awaits `run()`; see [Agent](https://docs.browser-use.com/open-source/agent.md#cancel).
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.