Browser Use logo
Browser Automation · Multimodal Browse Agents

Browser Use

Browser Use is a browser automation platform for AI agents. Describe a task in plain English and a hosted agent runs it in a managed stealth browser, returning structured JSON. Open-source Python library, CDP-compatible browsers and purpose-built models included.

Active Free plan Freemium API available 13+ Verified by Guidaio
Overview

What is Browser Use?

Browser Use is the infrastructure layer that lets AI agents operate a real web browser. It comes in three families, separated by who controls the browser and where the agent runs. Hosted Agents, reached through API V4, take a goal written in ordinary language, carry it out in a managed stealth browser and hand back a structured result; the caller keeps control of the task, the model, the files, the browser settings and the output schema. Browser Infrastructure drops the agent entirely and rents remote managed Chromium browsers, driven from the Python or TypeScript SDK, a REST API, or over the Chrome DevTools Protocol, so existing Playwright, Puppeteer and Selenium scripts connect without modification. The open-source library, installed with pip install browser-use, is for teams who would rather build and run the agent themselves, with their own tools, prompts, hooks and output schemas. The performance claims are unusually specific and published with their methodology: 98% on Online-Mind2Web across 300 tasks on 136 live sites with none removed, against 86% for the next result; 81% of protected sites reached on an in-house stealth benchmark of 71 sites, against 77%; and 84.8% on the 296-task BrowserBench suite. Stock headless Chrome reaches 2% of those protected sites. Models are interchangeable per run — Claude Opus 5, Grok 4.5, GPT-5.6, Gemini 3.6 Flash and MiniMax M3 are hosted, or you connect your own provider key. Browser Use also trains its own BU 2.0 models for browser work, claiming 68 seconds per task against 225 to 330 for general-purpose computer-use models, and 53 tasks per dollar against 2. Around this sit residential proxies in more than 195 countries, CAPTCHA solving inside the session, persistent profiles, cookie sync, live preview, session recordings, deterministic replay scripts that cost no tokens, and human takeover for logins, approvals and payments. Sub-second cold starts and per-minute billing from USD 0.02 an hour make wide fan-out practical: concurrency runs from three sessions on the free tier to five hundred on Scaleup. The company is SOC 2 Type II certified and publishes a machine-readable llms.txt alongside its documentation.

What it does

  • Run a web task described in a single sentence inside a real browser and return the result
  • Return schema-validated JSON, with a webhook callback when a run finishes
  • Fan out thousands of agents in parallel, each with its own browser, proxy and model context
  • Provide remote stealth Chromium browsers driven over CDP, an SDK or REST
  • Solve CAPTCHAs inside the session and route traffic through residential proxies in 195+ countries
  • Keep persistent browser profiles and hand control back to a human for logins, approvals or payments
  • Watch a page continuously and report when it changes, with no scraper to maintain
Audience

When to use Browser Use / When not to

A quick filter to help you decide if Browser Use is the right fit.

When to use Browser Use

  • Developers building web agents who want an open-source Python library they can run themselves
  • Data and platform engineers pulling structured data out of websites with no selectors to maintain
  • QA and test automation engineers reusing existing Playwright, Puppeteer or Selenium scripts over CDP
  • Teams whose agents must reach anti-bot protected sites at scale, up to 500 concurrent sessions
  • Startups, indie builders and researchers who need a permanent free tier and pay-as-you-go usage with no subscription

When not to use Browser Use

  • Non-technical users looking for a no-code interface: everything goes through code or an API
  • Anyone who needs a mobile app, since no iOS or Android application is offered
  • Buyers who require a fixed monthly cost, as billing meters browser minutes, proxy gigabytes, tokens and credits separately
  • Organisations that cannot accept model training on submitted inputs, for which no opt-out is documented
  • Teams needing a written retention period or a named hosting country outside an Enterprise contract
Get started

How to use Browser Use

A typical end-to-end flow, from setup to results.

  1. Pick the product family according to who should control the browser: hosted agent, managed browsers alone, or the local library
  2. Create an account on cloud.browser-use.com; the free tier asks for no card
  3. Generate an API key from the dashboard settings
  4. Hosted agents: POST to /api/v4/runs with the X-Browser-Use-API-Key header, a plain-language task and a model name
  5. Declare an output schema so results arrive as valid JSON rather than prose
  6. Collect the result from the event stream or from the webhook fired when the run ends
  7. Browser infrastructure: POST to /api/v3/browsers, optionally with a proxy country code, then connect to the returned CDP URL from Playwright or Puppeteer
  8. Stop sessions explicitly, because browser time is billed by the minute
  9. Open-source route: pip install browser-use, then build the agent with your own model and browser
  10. Follow runs through live preview and session recordings, taking over by hand for a login or a payment
Quick read

Pros & Cons

Pros

  • Benchmark results published with open methodology and task lists, not just headline percentages
  • The core Python library is open source with 108,500 GitHub stars, so the whole loop can be self-hosted
  • Very low entry cost: USD 0.02 per browser-hour, a permanent free tier and no mandatory subscription
  • Existing Playwright and Puppeteer scripts connect over CDP without a rewrite
  • Best measured stealth of the panel tested: 81% of protected sites reached, against 2% for stock headless Chrome
  • Per-run model choice and bring-your-own-key avoid lock-in to a single LLM provider
  • SOC 2 Type II with a named auditor and observation window, plus a published DPA with SCCs and a sub-processor list

Cons

  • The privacy policy states that inputs are used to train the models, and no opt-out is documented
  • No retention period is quantified outside an Enterprise contract
  • No hosting country or region is named: the DPA allows processing wherever the company or its sub-processors keep facilities
  • No postal address, legal notice page or contact page is published, only email addresses
  • Multi-meter billing across browser hours, proxy gigabytes, tokens and credits makes the cost of a real task hard to forecast
  • Strictly for a technical audience: no no-code interface and no mobile application
  • The terms impose individual arbitration under Californian law and waive class actions
Pricing

Pricing & Plans

Browser Use offers a permanent free plan covering ten agent tasks per month, free browsers and three concurrent sessions. The cheapest paid tier is Dev at USD 29 per month, which grants USD 29 of monthly credits and twenty-five concurrent sessions. Usage may also be purchased without any subscription, through non-expiring credits, with browser time billed at USD 0.02 per hour.

Free — USD 0
  • 10 agent tasks per month
  • free browsers
  • 3 concurrent sessions
Dev — USD 29/month
  • USD 29 of credits per month
  • 25 concurrent sessions
  • advanced stealth
  • top-ups and bring your own key
Business — USD 299/month
  • USD 299 of credits per month
  • 200 concurrent sessions
Scaleup — USD 999/month
  • USD 999 of credits per month
  • 500 concurrent sessions
  • managed proxy at USD 4/GB
Enterprise — custom quote
  • annual credit pool
  • SLAs
  • data retention terms
  • dedicated support
  • via sales@browser-use.com
Usage rates
  • browser session USD 0.02/hour billed by the minute
  • managed proxy USD 5/GB (USD 4/GB on Scaleup)
  • proxyless or bring-your-own-proxy egress USD 0.20/GB
Hosted agents (API V4), tokens at 1.2x provider rates per 1M input/cached/output
  • MiniMax M3 0.36/0.072/1.44
  • Gemini 3.6 Flash 1.80/0.18/9.00
  • Grok 4.5 2.40/0.36/7.20
  • Claude Opus 5 6.00/0.60/30.00
  • GPT-5.6 6.00/0.60/36.00 (USD)
Bring your own key
  • provider cost plus a 0.2x orchestration fee
In-house BU 2.0 model
  • USD 0.60/1M input
  • USD 0.06/1M cached input
  • USD 3.50/1M output
API V2, step-priced
  • from USD 0.006 per LLM step plus USD 0.01 per task initialisation
Annual billing
  • two months free
  • with credits granted up front
Special offers — Annual plans include two months free, with credits granted up front · Permanent free tier: ten agent tasks per month, free browsers and three concurrent sessions · CAPTCHA solving is included in the browser session at no extra cost, with no separate solver service · Managed proxy drops to USD 4 per gigabyte on the Scaleup plan, against USD 5 elsewhere · No student, jobseeker, non-profit or open-source discount is advertised
Prices and plans listed above may evolve. Always check the official pricing page before subscribing.
Trust & Privacy

Data, GDPR & hosting

A consolidated view of how Browser Use handles your data.

GDPR overview

Browser Use never claims GDPR compliance in so many words, but it publishes a full data processing agreement, last updated 30 July 2026. That DPA names the GDPR and the UK GDPR among the privacy laws it covers, incorporates the European Commission's 2021/914 Standard Contractual Clauses by reference, and handles the UK Addendum and the Swiss FADP explicitly. Sub-processing runs under Clause 9 Option 2, with ten days' notice before any new sub-processor and a five-day right of objection; the current list is published on a Vanta trust page. Data subject rights cover access, correction, deletion, portability, objection, withdrawal of consent, appeal and complaint to a supervisory authority. The company states it neither sells personal information nor shares it for interest-based advertising. No Article 27 EU representative is named, and Do Not Track signals are not honoured. Privacy contact: privacy@browser-use.com.

Who owns the data?

You decide entirely what you submit: the agent filters nothing, much as a browser or a search engine would not. Browser Use acts as controller for its own site and account data, and as processor — or sub-processor — for the customer data it handles under contract, which the privacy policy expressly does not cover. Inputs and outputs may be passed to the third-party LLM providers that power the service, and to hosting, analytics, payment and support vendors. Professional advisers, authorities and a future acquirer may also receive personal information. Browser profiles retain cookies and session state, though the vendor states it does not store browser passwords.

Reuse rights

Outputs come back as structured JSON you can pass straight to the next step, and nothing in the terms requires permission to reuse them. Two limits matter. The terms forbid using the service to harvest email addresses or contact details of other users for unsolicited messaging, and forbid circumventing any block Browser Use applies, including through a proxy or a VPN. You remain solely responsible for the legality, quality and accuracy of what you submit, and Browser Use may refuse or remove content at its sole discretion. Separately, it reserves the right to build aggregated, de-identified, anonymous or sanitised datasets from inputs, outputs, usage telemetry and workflow patterns, and to use, share and license them.

Data retention & training

Retention summary
The privacy policy sets no figure: personal information is kept as long as needed to run the service or for legitimate purposes such as disputes, security and legal obligations, weighed against the volume, nature and sensitivity of the data. The data processing agreement is firmer. Section 10 forbids keeping customer personal data longer than the purpose requires, and commits to securely destroying all of it, copies included, within ninety days of the service ending, except where law requires retention or for isolated backups later deleted or anonymised. Annex I ties the processing period to the contract term plus the time until deletion, and Schedule C allows archival retention on customer request. Enterprise plans negotiate their own retention terms. Deletion can also be requested through data subject rights at privacy@browser-use.com. Aggregated, de-identified datasets derived from inputs and outputs fall outside this scheme.
Trains on customer data
Yes
Subprocessors disclosed
Yes
DPA available
Yes

Hosting summary

No hosting country or region is named anywhere on the site. Section 11(a) of the data processing agreement states that customer personal data may be processed in any country where Browser Use, its affiliates and its authorised sub-processors maintain facilities; for data covered by European privacy law, it undertakes not to transfer outside the country of collection without first putting the necessary measures in place. The European Commission's Standard Contractual Clauses are incorporated by reference, with the UK Addendum and the Swiss FADP handled separately. The current sub-processor list is published on a Vanta trust page cited in section 7(a). Stripe processes payments, and inputs and outputs may be passed to third-party LLM providers. The responsible entity is a US company whose team sits in San Francisco, with Californian law governing the terms. SOC 2 Type II attests to the controls without specifying a storage jurisdiction. The domain resolves to an anycast address in the United States, which identifies a delivery node rather than a place of storage.

Watch-outs

Things to keep in mind

Risks and trade-offs to weigh before adopting Browser Use.

  • Inputs feed model training according to the privacy policy, with no documented opt-out: anything the agent reads or types can end up improving the product
  • The agent filters nothing, so it is easy to hand it personal or sensitive data, including other people's, without meaning to
  • Persistent profiles and cookie sync mean a logged-in session left in place exposes a real account to an unintended automated action
  • Agents can fill forms and place orders, so a poorly bounded run can trigger something irreversible before a human notices
  • Stealth, anti-detection and CAPTCHA solving carry legal and contractual risk against the target sites' own terms, and invite retaliatory blocking
  • Usage billing across several meters means an agent stuck in a loop can spend with no obvious ceiling
  • A 98% benchmark score invites over-trust: the remaining 2% pass unnoticed without human verification
Setup

Setup & Integrations

Technical difficulty

Straightforward for a developer, and impossible without one. The open-source route is a single command, pip install browser-use. On the cloud side, an account, an API key and one HTTP POST are enough to launch an agent or a browser. Existing Playwright, Puppeteer and Selenium scripts connect over CDP without a rewrite. There is no no-code interface. Expect to manage session lifecycle, model choice, output schemas, credits and concurrency yourself, and to keep the Cloud SDK and the open-source package apart, since the documentation warns that their APIs differ.

Deployment

Web appAPI

Integrations

Playwright Puppeteer Selenium MCP N8n OpenClaw Hermes Agent Anthropic OpenAI Google XAI MiniMax GitHub Stripe

Supported languages

English
Company

Behind Browser Use

Company name
Browser Use Inc.
Founded
17/11/2024
Country of origin
🇺🇸 United States
UBO
INFORMATION_NOT_FOUND
UBO country
INFORMATION_NOT_FOUND
Domain registrar country
🇺🇸 United States
Legal contact
Support contact

Fundraising

USD 17M round, announced 23 March 2025, led by Felicis Ventures
Reported participants: A Capital, Liquid2, Nexus Ventures, Paul Graham, Pioneer Fund, SV Angel, Y Combinator
The careers page confirms the raise first-hand, describing a recent USD 17M round and a very long runway
Company reported as founded in 2024 by Gregor Zunic and Magnus Muller, based in San Francisco
No later round or cumulative total was found

Social

Official links

Resources

All the official URLs gathered for verification and reference.

Compare

Alternatives

Tools that compete with or complement Browser Use.

B BrowserbaseS SteelH HyperbrowserA AnchorO OnkernelS StagehandO OpenAI OperatorT TinyFish
FAQ

Frequently asked questions

What exactly is a web agent?
It is an LLM that drives a real browser: it reads the page, decides what to click or type, and works through the task the way a person would. That is what separates it from a scraper, which follows selectors written by hand and breaks the moment the page changes.
Is there a free plan, and what does the cheapest paid tier cost?
Yes, the free plan is permanent: ten agent tasks per month, free browsers and three concurrent sessions. The first paid tier is Dev at USD 29 per month, which includes USD 29 of credits and twenty-five concurrent sessions. Annual billing adds two months free.
How is browser time priced?
A browser session costs USD 0.02 per hour, metered by the minute, with no subscription required. Managed residential proxy traffic is USD 5 per gigabyte, dropping to USD 4 on Scaleup, and egress without a managed proxy is USD 0.20 per gigabyte.
Which models can the agent use?
Hosted options are Claude Opus 5, Grok 4.5, GPT-5.6, Gemini 3.6 Flash and MiniMax M3, alongside the in-house BU 2.0 model. On eligible plans you can connect your own Anthropic, OpenAI or Google key and pay the provider directly plus a 0.2x orchestration fee.
Do my existing Playwright or Puppeteer scripts still work?
Yes. Every session is a real remote Chromium reachable over the Chrome DevTools Protocol, so Playwright, Puppeteer and Selenium clients connect without changes, no SDK required. Python and TypeScript SDKs and a REST API are also available.
Is Browser Use open source?
The Python library is, installed with pip install browser-use and carrying 108,500 GitHub stars. The managed stealth browsers and the hosted agents are commercial cloud products. The two have different APIs, and the documentation warns against mixing their examples.
Is my data used to train the models?
The privacy policy states that inputs are used to train the models in order to improve the services, and no opt-out option is documented. Under the data processing agreement, customer personal data is restricted to the purpose of the contract, so the two regimes differ.
How long is data retained?
The privacy policy gives no figure, keeping data as long as needed to run the service or for legitimate purposes. Under the DPA, all customer personal data is securely destroyed within ninety days of termination, apart from legal obligations and isolated backups. Enterprise plans negotiate their own terms.
What security assurances exist?
Browser Use is SOC 2 Type II compliant, audited by Accorp Partners over an observation window from 17 July to 17 October 2025. The trust report is available on request from support@browser-use.com, and a data processing agreement with Standard Contractual Clauses and a public sub-processor list is published.
Is there a minimum age, or a mobile app?
The service is not for anyone under 13, and users between 13 and 18 need the express consent of a parent or guardian. There is no iOS or Android application: access is through the web dashboard, the API and the open-source library.
Conclusion

Should you pick Browser Use?

Browser Use has moved well beyond the open-source library that made its name. It now sells three things at once — hosted agents, managed stealth browsers and its own purpose-built models — and it is the rare vendor in this space that publishes benchmark methodology alongside the numbers. For a technical team that needs an agent to act on real, defended websites at scale, the combination is hard to fault: CDP compatibility means existing Playwright and Puppeteer code keeps working, USD 0.02 per browser-hour keeps fan-out affordable, per-run model choice avoids provider lock-in, and the open-source path remains open to anyone who would rather run the whole loop in-house. SOC 2 Type II certification with a named auditor, a published data processing agreement carrying Standard Contractual Clauses, and a public sub-processor list are more than most tools of this age offer. The reservations concern data and predictability rather than capability. The privacy policy says plainly that inputs are used to train the models, and no opt-out is documented; retention is quantified only inside a contract; and no hosting country is ever named. The company publishes no postal address, no legal notice page and no contact page, which is thin for a vendor asking to drive authenticated browser sessions. Billing spans browser minutes, proxy gigabytes, tokens and credits, so forecasting the cost of a real workload takes a pilot rather than a spreadsheet. Recommended for developers, data and QA engineers, and AI teams comfortable with an API-first product. Less suitable for non-technical buyers, anyone needing mobile access, or organisations with firm contractual requirements on retention or data residency who are not ready to negotiate an Enterprise agreement. Watch the pricing page and the changelog: this product moves fast.