Steel vs Scrapeless

Both rent you a cloud Chromium that your agent drives over CDP. Steel is an open-source browser API with saved logins, human takeover and hour-long sessions on Scale. Scrapeless is a scraping company whose browser comes with fingerprints, residential proxies and CAPTCHA solving built in.

The companies and products

Steel

Steel is an API that runs fleets of cloud browsers for AI agents: you create a session, connect Puppeteer, Playwright or Selenium, and release it when done.

Each Steel session is a headful Chromium in a VM in Steel's cloud. You drive it over CDP, a Commands API or a computer-use input API, and you can embed a live viewer. Around it Steel sells managed proxies, CAPTCHA solving, saved browser profiles, a credentials vault that signs in for the agent, a files API and readable traces. It is a different kind of product from boat: a managed browser, not a general sandbox. This page compares where the two overlap: agents that use a browser.

Scrapeless

Scrapeless is a web scraping company. It sells Agent Browser, a managed cloud browser, along with AI scrapers, a web unlocker and proxies.

Scrapeless Agent Browser is a different kind of product from boat. You get a Chromium browser in their cloud and reach it over a CDP WebSocket with Puppeteer or Playwright, an MCP server or their agent-browser CLI. Each session gets a random fingerprint, CAPTCHA solving and a residential proxy. You pay per browser-hour plus proxy traffic. It is built for teams that scrape or automate many websites. Your own code runs on a machine you supply.

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. “24th cheapest of 356” means 23 of the other 355 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 workloadSteel: price rankScrapeless: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Neither gives you a shell, Docker or a place to build and test, so both are a compromise here, while boat fits fully.
157th of 365, with limits
$1,115 a month
129th of 365, with limits
$868 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that works all month hits Steel's session caps (15 minutes on Launch, 1 hour on Scale) and Scrapeless's minutes-long sessions, so both keep restarting from a saved profile.
128th of 361, with limits
$3,070 a month
263rd of 361, with limits
$2,628 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
262nd of 336, with limits
$333 a month
243rd of 336, with limits
$249 a month
189th of 336, with limits
$2,000 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
300 sandboxes at once is more than Steel's Scale limit of 100, and Scrapeless sells browser sessions, not a machine your users can run code on.
240th of 349, with limits
$990 a month
222nd of 349, with limits
$741 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
252nd of 349, with limits
$4,150 a month
244th of 349, with limits
$3,580 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
345th of 359, with limits
$400 a month
256th of 359, with limits
$399 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
CI needs a shell, Docker and a known CPU size, which neither browser service offers.
239th of 374, with limits
$120 a month
230th of 374, with limits
$97 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
255th of 371, with limits
$73 a month
248th of 371, with limits
$59 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Both drive only a browser; boat streams a 60fps Linux desktop where the agent can use any app as well as Chromium.
190th of 367, with limits
$367 a month
159th of 367, with limits
$274 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
All three fit browser-use agents: our default ranking puts boat at #6, Scrapeless at #9 and Steel at #18. boat ranks well when the agent also needs a shell and a disk next to Chromium.
24th cheapest of 356
$470 a month
13th cheapest of 356
$274 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
At startup scale all three fit: our default ranking puts boat at #6, Scrapeless at #37 and Steel at #59. boat runs the scraper, its queue and its database on one machine.
61st cheapest of 343
$540 a month
37th cheapest of 343
$370 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
For mass scraping of sites with strong bot checks, our default ranking puts Scrapeless at #4 and Steel at #5, well ahead of boat at #46, which has datacenter IPs and no built-in CAPTCHA solving.
8th of 327, with limits
$7,950 a month
5th of 327, with limits
$7,020 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
250th of 351, with limits
$242 a month
101st of 351, with limits
$199 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureSteelScrapelessboat
Kind of productA managed Chromium browser per session, driven over CDP, REST or a computer-use input APIA managed Chromium browser per session over a CDP WebSocket, sold by a scraping companyA full Linux VM per sandbox with its own kernel, and a desktop and Chromium inside
Machine sizeNot published; billed per browser hourNot published; billed per browser hour4 vCPU / 8 GB by default, 2 to 16 vCPU; 16 vCPU / 32 GB needs the $100 plan or higher
Shell, Docker and nested virtualizationA hosted session gives browser control only; you can self-host the open-source steel-browser in Docker next to your own codeNo shell on the machine that runs the browser; your code runs on your own machine and drives it over CDPSSH, root, systemd, Docker and /dev/kvm on every machine
Session length15 minutes on Launch, 1 hour on Scale, up to 24 hours on Enterprise; longer jobs chain sessions3 minutes by default, 15 minutes recommended at most, longer allowedAuto-stop after 1 hour by default; set up to 30 days, or turn it off on a paid plan
Concurrency10 browsers on Launch, 100 on Scale, 1,000+ on EnterpriseGrows with the prepaid plan; custom concurrency on Enterprise; free tier 1 session100 sandboxes at once on $20, up to 2,000 on $2,000; $20 includes 12 starts a minute and 200 a day, extra starts cost $0.03 to $0.07
State between sessionsProfiles keep cookies and logins; session files become org-wide files that mount into later sessionsBrowser profiles keep cookies, storage, cache and logins, saved when the session closesThe disk is saved every minute and at each stop, and kept at least 14 days after a stop; memory and running programs are not saved
ForkNo fork API; a new session can start from a saved profileNo fork; sessions can share a profile, and the last to close is the one savedFork a running sandbox into a copy, from its last 1-minute snapshot
Stealth and CAPTCHAsCAPTCHA solving on paid plans, billed per solve; a stealth browser on EnterpriseRandom fingerprint per session and CAPTCHA solving included at no extra chargeChromium on datacenter IPs; no built-in CAPTCHA solving; you add a stealth library and a solver service
ProxiesManaged residential proxies billed per GB, dedicated IPs on Scale, your own proxy on every planResidential IPs in 195+ countries down to state and city, billed per GB; your own proxy on paid plansNone managed; you can run your own proxy client inside the VM
Live view and human takeoverEmbeddable live view where a person can take over, mobile mode and tracesLive URL to watch and control the browser, session replay, and Chrome extensionsA full Linux desktop streamed at 1920x1080, 60fps, embeddable, with computer use
Open source and self-hostingsteel-browser is Apache-2.0 open source; Steel Outpost runs inside your networkManaged cloud; the agent-browser CLI is Apache-2.0Managed cloud only
Ready-made scrapersBrowser tools for scrape, screenshot and PDF, billed per callAI Scraper tasks for ChatGPT, Perplexity, Gemini, Copilot, Google AI Mode and more, plus crawl and search over MCPNone; you write or run your own
Reaching the machineNo inbound ports; a CDP websocket and a live view URLNot part of the product: the browser is reached through Scrapeless endpoints, so you host your services elsewhereUp to 50 HTTPS URLs per sandbox, token-gated by default; SSH; a public IPv6 address
Agents and secretsCLI, skills and an MCP server for an agent that runs on a machine you provide; a credentials vault for web loginsCLI skill and an MCP server for an agent that runs on your own machine; a credential store and 1Password linkSeven coding-agent harnesses preinstalled with a prompt, steer and events API; an optional paid AI credentials proxy for supported model providers
ComplianceHIPAA-ready BAA on Scale and Enterprise; SSO on EnterpriseSays it is GDPR and CCPA compliant and ISO certified; SSO on Enterprise plansSOC 2 in progress; no HIPAA BAA or SAML SSO documented
Every feature Battleships tracks (43)
FeatureSteelScrapelessboat
Full VM (own kernel)YesNot publishedYes
Docker insideNo documented wayNo documented wayYes
Nested virtualizationNo documented wayNo documented wayYes
RootNo documented wayNot publishedYes
SystemdNo documented wayNot publishedYes
Desktop GUINo documented wayNo documented wayYes
BrowserYesYesYes
Computer-use APIYesYesYes
SSHNo documented wayNo documented wayYes
Persistent diskYesNo documented wayYes
Pause/resumeNo documented wayNo documented wayYes
Automatic snapshotsYesNo documented wayYes
Fork/cloneNo documented wayNo documented wayYes
Live fork (no pause)No documented wayNo documented wayYes
Memory forkNo documented wayNo documented wayNo documented way
Custom image (Docker or snapshot)No documented wayNot publishedYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo documented way
Wake on requestNo documented wayNo documented wayNo documented way
HTTPS preview URLsNo documented wayNo documented wayYes
Raw TCP inboundNo documented wayNot publishedYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistNo documented wayNo documented wayNo documented way
Secret proxyNo documented wayNo documented wayYes
Secret proxy for any APINo documented wayNo documented wayYes
Preinstalled agentsNo documented wayNo documented wayYes
Agent harness APINo documented wayNo documented wayYes
MCP serverYesYesNo documented way
GPUNo documented wayNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingYesNo documented wayNo documented way
BYOCYesNo documented wayNo documented way
Open sourceYesNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)No documented wayNo documented wayYes
Audit logsNot publishedNot publishedNo documented way
SSOYesYesNo documented way
SOC 2No documented wayNot publishedNo documented way
HIPAAYesNot publishedNo documented way
EU data residencyNo documented wayNo documented wayNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

SteelNot measured
ScrapelessNot measured
boat28.06 runs/s

Steel and Scrapeless are not in the public benchmarks we use, and neither publishes the CPU or memory behind each session, so we cannot say which is faster. For reference, a boat sandbox at 4 vCPU / 8 GB did 28.06 runs/s on the V8 Web Tooling Benchmark in StarSling's run of 3 October 2026 (run 37073680030), second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Steel says a session starts in under a second, and Scrapeless says under 2 seconds.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Steel and Scrapeless are not in the public benchmarks we use, so we cannot say which is faster.

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. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioSteel, a monthScrapeless, a monthboat, 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
$250 · Scale · with limits$399 · Business · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$250 · Scale · with limits$399 · Business · with limits$26 · $20/mo
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$784 · Scale · with limits$570 · Business · with limits$317 · $20/mo × 3 seats
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$510 · Scale · with limits$399 · Business · with limits$200 · $100/mo × 2 seats
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$950 · Scale · with limits$716 · Business · with limits$8,800 · $2000/mo · with limits

Steel: Steel bills browser hours by the minute, rounded up. Launch has no monthly fee, charges $0.10 an hour and gives a one-time $30 credit valid for 90 days; its proxies and CAPTCHA solving need a $10 paid deposit. Scale costs $250 a month, includes $100 of usage and charges $0.08 an hour. Proxy bandwidth, CAPTCHA solves and browser tools are billed on top.

Scrapeless: Scrapeless plans are prepaid into your balance, and unused funds do not roll over. Browser time is $0.09 an hour, discounted on larger prepaid plans. Residential proxy traffic is billed from $1.80 per GB, and CAPTCHA solving is included. A free tier gives 1 session at once and 1 browser-hour a month with no card.

Scrapeless: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A default 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; saved snapshots above the included count and the optional AI credentials proxy still charge. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07 each, up to 1,200 a day. A card is required, also for the 7-day trial.

Limits in those scenarios

None of the five scenarios fits Steel or Scrapeless, because each asks for a 4 vCPU / 8 GB machine with a disk and they sell a browser session with no shell and no published size. On Steel, work that runs for hours must be cut into sessions: 15 minutes on Launch, 1 hour on Scale, 24 hours on Enterprise. Scale allows 100 browsers at once, so 300 user sandboxes or 1,000 short jobs need Enterprise. Scrapeless recommends sessions of 15 minutes at most, and 1,000 sessions at once need a custom plan. On boat, the 1,000-job burst does not fit either: even the $2,000 plan includes 90 starts a minute and 2,400 a day, extra starts cost $0.03 to $0.07, starts above 270 a minute fail with 429, and boat never queues a start.

ScenarioSteelScrapelessboat
One coding agent, workdays
  • Scale: sessions capped at 1 h
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • missing persistent disk
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
None for this scenario
One agent that never stops
  • Scale: sessions capped at 1 h
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • missing persistent disk
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
None for this scenario
50 agents in parallel
  • Scale: sessions capped at 1 h
  • missing Docker inside
  • machine size not published
  • browser-session product, not a general sandbox
  • missing persistent disk, Docker inside
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
None for this scenario
Sandboxes for your users
  • Scale: max 100 concurrent
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • machine size per session not published
None for this scenario
1,000 short jobs at once
  • Scale: max 100 concurrent
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • Business: max 400 concurrent
  • machine size not published
  • browser-session product, not a general sandbox
  • different kind of product: browser session
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use Steel when

you want an open-source browser you can host yourself, sessions up to an hour on Scale, and saved logins, human takeover and traces as ready parts.

  • Open source, and can run in your network. For teams that must host browsers themselves: steel-browser is Apache-2.0, and Steel Outpost runs inside your own network.
  • Longer sessions on a plan you can buy. For agent runs past 15 minutes: Scale sessions last up to 1 hour, and Enterprise up to 24 hours.
  • Ready browser parts for agents. For agents that sign in and need a person nearby: saved profiles, a credentials vault, human takeover and readable traces.

Use Scrapeless when

you run many short sessions on sites with strong bot checks and want fingerprints, residential proxies and CAPTCHA solving included.

  • Stealth included. For sites with strong bot checks: every session gets a random fingerprint, and CAPTCHA solving costs nothing extra.
  • Residential proxies everywhere. For scraping by location: over 70 million residential IPs in 195+ countries, which you can pin to a state or city.
  • Data, not only browsers. For teams that want results: ready-made AI scrapers, crawls and search tools sit behind the same API key, and a free tier needs no card.

Where boat fits

Steel and Scrapeless are both browser services, so boat only overlaps where your agent uses a browser. If what you are really running is agents that browse and then work, writing files, running code, building in Docker or serving an app, look at boat: each agent gets a whole Linux VM with Chromium and a desktop inside.

A whole machine around the browser

Neither hosted service gives you a shell, so installs, builds, Docker and tests run on a second machine you host. You wire the two together, move every file between them and keep both alive.

Long runs and a disk that stays

Steel stops a session after 15 minutes on Launch or 1 hour on Scale, and Scrapeless sessions default to 3 minutes. Both carry a browser profile forward, so files on disk and running work start over each time. boat saves the whole disk every minute and at each stop.

Agents inside, driven from outside

Both offer an MCP server so an agent on your own laptop or server can use their browser, which means you still host that agent. On boat the agent runs inside the VM, and you drive it through one API. boat has no managed proxies or CAPTCHA solving.

Use boat when your agent does more than browse: it needs a shell, files, Docker, a desktop or a server next to Chromium, and it has to keep working for hours. Compare it one to one: boat vs Steel and boat vs Scrapeless.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is Steel cheaper than Scrapeless?

Usually not. In our default rankings, browser-use agents cost $274 a month on Scrapeless and $470 on Steel, and startup-scale scraping $370 against $540. boat comes to $200 and $90. One browser on workdays (about 176 hours) is about $16 of browser time at Scrapeless's $0.09 base rate, and about $18 on Steel's Launch plan with 15-minute restarts from a saved profile, or $250 on Scale for 1-hour sessions. Neither fits that job as a general machine.

Which is better at getting past bot checks?

Scrapeless includes a random fingerprint per session and CAPTCHA solving at no extra charge, with residential IPs in 195+ countries. Steel has residential proxies and CAPTCHA solving billed per use, and keeps its stealth browser for Enterprise. boat uses datacenter IPs and has no built-in CAPTCHA solving.

How long can a session run on Steel and Scrapeless?

Steel allows 15 minutes on Launch, 1 hour on Scale and 24 hours on Enterprise. Scrapeless defaults to 3 minutes and recommends 15 minutes at most, though longer values can be set. A boat sandbox stops after 1 hour by default, and you can turn auto-stop off on a paid plan.

Can Steel or Scrapeless run Docker or a coding agent?

Not in a hosted session. Both give you a cloud Chromium with no shell, so Docker and an agent's code run on a machine you host, which drives the browser through their MCP server or API. You can run Steel's open-source steel-browser in Docker yourself. On boat each sandbox is a full VM with Docker and coding agents preinstalled.

Which is faster?

Neither is in the public benchmarks we use, and neither publishes the CPU behind a session, so we cannot say. Steel says a session starts in under a second, and Scrapeless says under 2 seconds.

Can I self-host Steel or Scrapeless?

Steel, yes: steel-browser is open source under Apache-2.0 and runs in Docker, and Steel Outpost runs inside your own network. Scrapeless is a managed cloud. boat is a managed cloud only.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons