boat vs Zenrows
Zenrows is a web data service: its Browser Sessions are remote Chrome tabs on rotating residential IPs that close after at most 15 minutes. boat gives each agent its own VM with Chromium, a desktop, Docker and files that stay, for as long as the work takes.
Where boat stands out
A whole machine, not one browser tab
A boat sandbox is a full VM with root, systemd, Docker and a disk, with Chromium inside it. Your agent can browse, then save files, run code, start a database or build what it found, all on the same machine. Zenrows gives you a remote Chrome over CDP and nothing around it.
Work that runs past 15 minutes
boat has no session cap on paid plans, and the disk is saved every minute and when the sandbox stops. A Zenrows session closes after at most 15 minutes and keeps nothing. Logins, cookies and downloads stay put on boat until you delete them.
A real desktop you can watch
boat streams a 60fps desktop with Chromium and computer use, and you can embed the stream in your app. Because the browser runs on your own VM, you can change its viewport, user agent, profile and extensions. Coding agents come preinstalled and are driven from outside with a prompt, steer and events API.
The companies and products
boat
boat.dev runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.
You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
Zenrows
Zenrows calls itself web data infrastructure built for agents and applications: APIs that fetch, extract, crawl and browse protected websites.
Browser Sessions (formerly Scraping Browser) is a remote Chrome you connect to over a WebSocket and drive with Puppeteer or Playwright through the Chrome DevTools Protocol. Each session runs on rotating residential IPs and closes after 1 to 15 minutes. It is a different kind of product from boat: a managed browser for scraping and web tasks, not a machine you get a shell on, so this page compares where the two overlap, which is browser and web agents.
Which use cases each one fits
For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “3rd cheapest of 367” means 2 of the other 366 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.
| Use case and its workload | boat: price rank | Zenrows: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Zenrows has no shell, Docker or disk, so a coding agent cannot build or test there; it can only browse. | 3rd cheapest of 367 $634 a month | 59th of 367, with limits $448 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month needs files that stay and no session cap, which boat has and a 15-minute browser session does not. | 5th cheapest of 366 $657 a month | 126th of 366, with limits $833 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 186th of 345, with limits $2,000 a month | 232nd of 345, with limits $166 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month | Cheapest of 361 $209 a month | 203rd of 361, with limits $361 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 34th of 360, with limits $2,000 a month | 229th of 360, with limits $1,111 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month Agent evals that mix code, files and a browser need a whole machine per run, which Zenrows does not offer. | 10th cheapest of 364 $200 a month | 230th of 364, with limits $166 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 4th cheapest of 377 $86 a month | 221st of 377, with limits $83 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 18th cheapest of 368 $26 a month | 232nd of 368, with limits $58 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month A computer-use agent needs a screen and a mouse, and boat streams a 60fps desktop; Zenrows exposes the browser over CDP with no desktop stream. | 6th cheapest of 369 $200 a month | 93rd of 369, with limits $166 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit: Zenrows gives an agent a remote Chrome with residential IPs, and boat gives it Chromium on its own VM that can stay open past 15 minutes. | 7th cheapest of 367 $200 a month | 5th cheapest of 367 $166 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month Both fit; Zenrows brings residential IPs and anti-bot bypass, while boat runs your own scrapers, queues and databases on one machine. | 6th cheapest of 346 $90 a month | 18th cheapest of 346 $227 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Neither fits fully: Zenrows meters bandwidth at 25,000 credits per GB, and boat has no residential proxy network of its own. | 71st of 338, with limits $1,800 a month | 70th of 338, with limits $1,791 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month Red teaming needs a full machine an agent can attack and break, not a remote browser tab. | 2nd cheapest of 360 $200 a month | 149th of 360, with limits $115 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Can't run it | Can't run it |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | Can't run it |
Key features
| Feature | boat | Zenrows |
|---|---|---|
| What you get | A full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | A remote Chrome session reached over CDP; isolation technology not published |
| Session length | No cap on paid plans; you set the time to live | 1 to 15 minutes, 3 by default, then the session closes |
| Files after the session | Disk snapshots every minute and on stop; a stopped sandbox costs nothing and keeps its disk | Session closes and frees its resources; no saved state documented |
| Shell, root and Docker | Root, systemd, Docker and /dev/kvm | No shell; browser control over CDP only |
| Browser control | Chromium on your own VM: install Playwright, Puppeteer, extensions or any tool, and change any setting | Puppeteer or Playwright over CDP; viewport, user agent and some device settings are blocked |
| Desktop and computer use | 60fps desktop stream with Chromium and computer use, embeddable in your app | No desktop stream; screenshots and page actions through CDP or MCP tools |
| Outbound IPs | Traffic leaves from EU data centers; bring your own proxy if you need other IPs | Over 55 million residential IPs in 190+ countries, rotating on every request, with country targeting |
| Anti-bot and CAPTCHA | None built in; you run your own tools | Anti-bot bypass on its tools; Browser Sessions cannot solve CAPTCHAs, the Fetch API has anti-CAPTCHA features |
| MCP server | No MCP server; agents drive the sandbox through the API and CLI | Hosted or local MCP server with scrape, extract, crawl, batch and browser tools |
| Coding agents | Claude Code, Codex and more preinstalled, with a prompt, steer and events API | Tools for your agent to call; no agent runs inside Zenrows |
| Hosting from the sandbox | HTTPS URLs for up to 50 ports, token-protected; raw TCP | None; you connect out to a shared Zenrows endpoint |
| Keeping API keys out of the sandbox | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out | Not documented; auth is your Zenrows API key |
| Where it runs | EU only (Germany, Finland, France), with EU data residency and zero data retention | Primarily hosted on DigitalOcean, no region to choose; proxy exits worldwide |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | SOC 2 |
Every feature Battleships tracks (43)
| Feature | boat | Zenrows |
|---|---|---|
| Full VM (own kernel) | Yes | No |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | Not published |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | No |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | No |
| Live fork (no pause) | Yes | No |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Not published |
| ≥24 h sessions | Yes | No |
| Idle auto-stop | No | Yes |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No | No |
| Egress allowlist | No | No |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | No |
| Self-hosting | No | No |
| BYOC | No | No |
| Open source | No | No |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | No |
| EU data residency | Yes | No |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. Zenrows does not publish the CPU or memory behind a browser session, and it is not in the hpc-sandbox-benchmarks run where boat did 26.69 runs per second at 4 vCPU / 8 GB.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Zenrows has no published run in this suite yet, so there is no like-for-like number to compare.
Pricing in five scenarios
Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.
| Scenario | boat, a month | Zenrows, a month |
|---|---|---|
| One coding agent, workdays 4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days | $20 · $20/mo | $2,499 · Scale S5 (annual) · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $2,499 · Scale S5 (annual) · with limits |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $317 · $20/mo × 3 seats | $2,499 · Scale S5 (annual) · with limits |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $200 · $100/mo × 2 seats | $2,499 · Scale S5 (annual) · with limits |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $2,000 · $2000/mo · with limits | $2,499 · Scale S5 (annual) · with limits |
boat: Plans start at $20 a month, and the whole fee becomes usage credit spent per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Zenrows: Zenrows sells monthly credit plans shared by all its products. A browser session costs 5 credits per minute plus bandwidth at 25,000 credits per GB, plan credits expire at each renewal, and top-ups roll over once.
Limits in those scenarios
The limit that bites on Zenrows is the session length: every session closes after at most 15 minutes, so Zenrows fits no scenario on this page, even on its biggest self-serve plan. There is also no disk, Docker or published machine size, because Browser Sessions is a browser and not a sandbox. On boat, the 1,000-jobs-at-once burst is the one that does not fit: the $2,000 plan starts 90 sandboxes a minute and 2,400 a day, so the burst is queued.
| Scenario | boat | Zenrows |
|---|---|---|
| One coding agent, workdays | None that bite |
|
| One agent that never stops | None that bite |
|
| 50 agents in parallel | None that bite |
|
| Sandboxes for your users | None that bite |
|
| 1,000 short jobs at once |
|
|
Which one should you use?
Use Zenrows when
your agent only needs to open protected web pages for a few minutes at a time from residential IPs in many countries, or when you want scraping APIs and an MCP server rather than a machine.
- Residential IPs in 190+ countries. Useful for scraping protected sites: over 55 million residential IPs rotate on every request, and you can pick the country.
- A full web data toolbox. Fetch, Extract, Crawl and Batch share one credit balance with the browser, and an MCP server hands them to any agent.
- Pay per browser minute. Good for short, spiky page visits: a session costs 5 credits a minute, and a free plan needs no card.
Use boat when
your agent browses as part of real work: logging in once and staying logged in, downloading and processing files, running code and Docker next to the browser, or being watched on a 60fps desktop for hours.
- A whole machine, not one browser tab. With only a remote tab, everything else the agent does needs a second machine somewhere, and you move files and state between the two after every step.
- Work that runs past 15 minutes. A long browser task on Zenrows has to reconnect every 15 minutes or less and restore its login and page state each time, about 32 times in an eight-hour shift.
- A real desktop you can watch. A computer-use agent needs a screen to look at and click. Zenrows blocks viewport and user agent changes and has no desktop stream, so the agent sees screenshots of one page.
Questions people ask
Is boat cheaper than Zenrows?
For the sandbox scenarios on this page, yes: one coding agent on workdays comes to $20 a month on boat, while Zenrows is priced at $2,499 a month on its Scale S5 annual plan and still does not fit because of the 15-minute session cap. For short scraping visits that need residential IPs, Zenrows is built for that and boat is not a like-for-like comparison.
Can a Zenrows browser session run longer than 15 minutes?
No. The session time to live goes from 1 to 15 minutes, with 3 minutes by default, and then the session closes. Longer tasks have to open new sessions and restore their state, while boat has no session cap on paid plans.
Can I use Playwright or Puppeteer on boat?
Yes. A boat sandbox is a full Linux VM with Chromium, so you install Playwright, Puppeteer or any other tool and run it next to the browser. Zenrows also supports both, connected over CDP to its remote browser.
Does boat have residential proxies like Zenrows?
No. boat traffic leaves from EU data centers, and you can run your own proxy client inside the VM. Zenrows routes through over 55 million residential IPs in 190+ countries.
Is Zenrows a sandbox?
No. Zenrows is a web data service with Fetch, Extract, Crawl, Batch and Browser Sessions. You get a remote browser over CDP, not a machine with a shell, disk or Docker.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Browser Use
- boat vs Notte
- boat vs Kernel
- boat vs Anchor Browser
- boat vs Scrapeless
- boat vs Hyperbrowser
- boat vs Steel
- boat vs BrowserCloud
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- Browserbase vs Zenrows
- Browser Use vs Zenrows
- Steel vs Zenrows
- Hyperbrowser vs Zenrows
- Kernel vs Zenrows
- Anchor Browser vs Zenrows
- Browserless vs Zenrows
- Notte vs Zenrows