boat vs Northflank

Both give each agent a Linux machine with its own kernel. boat keeps the disk between runs with no setup and ships the agents, desktop and browser inside the machine. Northflank is a broad cloud platform with GPUs, 17 regions, your own cloud, and filesystem snapshots that you turn on.

Where boat stands out

The disk comes back with no setup

boat saves a sandbox's disk every minute and once more at each stop. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days, or longer as a saved snapshot. Start it again and the packages, files and config the agent left are there. Memory and running programs are not saved, so a resume is like a reboot. You can also fork a running sandbox from its last 1-minute snapshot.

Agents you drive from outside

Seven coding agents come installed in every boat sandbox, Claude Code and Codex among them. You send a prompt, steer the agent mid-task and follow its events through one API. With the optional AI credentials proxy on ($1 a day plus $1 per 1,000 requests), real model keys stay outside the machine.

A desktop and a browser inside

Every boat sandbox can show a 1920x1080, 60 fps Linux desktop with Chrome and computer tools for agents, and you can embed the stream in your app. It also has /dev/kvm, so Android emulators and VMs run inside.

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.

Northflank

Northflank is a London developer platform for running services, jobs and databases on Kubernetes, and Sandboxes is its product for running untrusted code.

A Northflank sandbox is a container image deployed as a service. CPU sandboxes run in Kata microVMs with their own kernel, and GPU sandboxes run under gVisor. You create and drive them from the JavaScript or Python SDK, the CLI or the dashboard, on Northflank's cloud or inside your own. It suits teams that want one platform for apps, databases, GPUs and sandboxes.

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. “5th cheapest of 365” means 4 of the other 364 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 workloadboat: price rankNorthflank: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
A coding agent installs packages all over the machine. boat keeps the disk across stops with no setup, for at least 14 days. On Northflank you set it up: attach volumes, or snapshot the filesystem before each pause and restore from it.
5th cheapest of 365
$634 a month
186th of 365, with limits
$1,413 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine for weeks needs its tools and files to stay. boat keeps the disk across stops, and with auto-stop off (default 1 hour) there is no session cap. Northflank has no session cap either, and keeps files outside volumes when you snapshot before a pause.
6th cheapest of 361
$657 a month
44th cheapest of 361
$2,551 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Short code runs on small machines fit Northflank's per-second plans from 0.1 vCPU, with no start fees. boat's smallest size is 2 vCPU / 4 GB, and starts above the plan's included number cost extra.
189th of 336, with limits
$2,000 a month
91st of 336, with limits
$114 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Both can give each user a machine. boat publishes how many run at once (100 on the $20 plan, up to 2,000 on $2,000) and adds HTTPS on up to 50 ports. Northflank adds 17 regions but does not publish a concurrency limit.
3rd cheapest of 349
$209 a month
94th of 349, with limits
$810 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
39th of 349, with limits
$2,000 a month
333rd of 349, with limits
$1,742 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
10th cheapest of 359
$200 a month
139th of 359, with limits
$685 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Both fit and both bill per second. boat adds /dev/kvm for Android emulators and VM builds. Northflank lets you boot your own container image and offers arm64; boat starts from its own image or a saved snapshot.
2nd cheapest of 374
$86 a month
36th cheapest of 374
$347 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
19th cheapest of 371
$26 a month
124th cheapest of 371
$106 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
boat ships a 1920x1080, 60 fps Linux desktop and Chrome with computer tools for agents. On Northflank you set it up: install a desktop, a browser and a screen stream in your own image. No desktop example is documented.
7th cheapest of 367
$200 a month
189th of 367, with limits
$367 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
boat has Chrome ready inside every sandbox. On Northflank you set it up: Northflank's guide runs Playwright and its browser from your own image.
7th cheapest of 356
$200 a month
83rd of 356, with limits
$359 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
6th cheapest of 343
$90 a month
94th cheapest of 343
$200 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
73rd of 327, with limits
$1,800 a month
83rd of 327, with limits
$2,031 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
3rd cheapest of 351
$200 a month
43rd of 351, with limits
$180 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Northflank has GPU sandboxes from L4 to H100, H200 and B200. boat has no GPU on any size.
Not ranked: misses a requirement5th cheapest of 102
$692 a month
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 requirement

Key features

FeatureboatNorthflank
IsolationFull VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are sharedKata microVM with its own kernel for CPU sandboxes; gVisor for GPU sandboxes
List price, 4 vCPU / 8 GB$0.036 an hour, billed per second, 51 GB disk included, from a $20 monthly plan$0.1333 an hour (nf-compute-400), billed per second, no plan fee; 1 GB ephemeral disk, volumes $0.11657 per GiB a month
What survives a stopThe disk, saved every minute and at each stop; no compute charge while stopped; disk kept at least 14 days, longer as a saved snapshot; memory and processes are not saved; a machine failure loses writes after the last good snapshotAttached volumes survive (billed while paused); the rest of the disk resets unless you snapshot it before pausing and restore from it (microVM sandboxes only); processes reset
Snapshots and forkAutomatic disk snapshots; fork a running sandbox from its last 1-minute snapshot; saved snapshots with no scheduled expiryFilesystem snapshots of a running or terminating sandbox, on demand or on termination (opt-in, microVM only); restore into a new sandbox; no memory
Custom imagesStart from boat's image or a saved snapshot; you cannot boot your own Docker or OCI imageAny container image
Nested virtualization/dev/kvm on every sandbox for Android emulators, QEMU/KVM and FirecrackerNot documented inside a sandbox
Desktop and browser1920x1080, 60 fps Linux desktop and Chrome, computer tools for agents, embeddable streamNo built-in desktop. You set it up: Northflank's guide runs Playwright browser agents from your own image; a desktop and stream you install yourself
Coding agentsSeven agents installed (Claude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code, Mistral Vibe), with a prompt, steer and events APIHarnesses with Claude Code, Codex, Cursor, OpenCode, Pi, OMP or Devin CLI and a lifecycle API; you talk to the agent through a terminal or SSH
Keeping API keys out of the sandboxOptional AI credentials proxy, off by default, $1 a day plus $1 per 1,000 requests; model providers and HTTPS APIs you register; switch a credential to another account when credits run outHeader injection for listed hosts in the network policy API (documented for your own cluster); otherwise secrets are env vars or files in the container
Inbound accessUp to 50 HTTPS URLs, token-gated by default; SSH; public IPv6 address; raw ports over IPv6, and over IPv4 only on sandboxes with their own IPv4; the IP changes at each resumeHTTP and HTTP/2 ports on a code.run domain or your own domain, private by default; SSH; public TCP and UDP through a separate Layer 4 load balancer with a stable IP (price not published)
Outbound rulesOpen internet, no provider-side allowlist; you set it up: firewall rules inside the VM with rootNetwork policies with allow lists by IP, CIDR or domain, documented for your own cluster; static egress IPs
Sizes and disk2 vCPU / 4 GB to 16 vCPU / 32 GB (16 vCPU needs the $100 plan or higher); disk fixed per size, 51 to 251 GB includedPlans from 0.1 vCPU / 0.25 GB to 20 vCPU / 40 GB, custom sizes on request; disk through billed volumes; a resize restarts the sandbox
GPUsNo GPU on any sizeL4, A100, H100, H200, B200, RTX PRO 6000 and more
RegionsGermany, Finland and France; you cannot pick a region; no US or Asia region; snapshot copies can be stored outside the EU17 regions in North America, South America, Europe, Asia, Australia and Africa; one region per project
ComplianceSOC 2 in progress; no HIPAA BAA documentedSOC 2 Type 2, HIPAA and ISO 27001
Self-hostingNoBring your own cloud, or the control plane in your VPC on Enterprise
Compliance and transparencySOC 2 is in progress. We're open about where we stand: live status and data retention policy.SOC 2
Every feature Battleships tracks (43)
FeatureboatNorthflank
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesNo documented way
RootYesNot published
SystemdYesNot published
Desktop GUIYesNo documented way
BrowserYesWith your own setup
Computer-use APIYesNo documented way
SSHYesYes
Persistent diskYesWith your own setup
Pause/resumeYesYes
Automatic snapshotsYesYes
Fork/cloneYesYes
Live fork (no pause)YesYes
Memory forkNo documented wayNo documented way
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNo documented wayNo documented way
Wake on requestNo documented wayNo documented way
HTTPS preview URLsYesYes
Raw TCP inboundYesYes
Public IPv4No documented wayNo documented way
Egress allowlistNo documented wayYes
Secret proxyYesYes
Secret proxy for any APIYesYes
Preinstalled agentsYesYes
Agent harness APIYesNo documented way
MCP serverNo documented wayNo documented way
GPUNo documented wayYes
WindowsNo documented wayNo documented way
Arm64No documented wayYes
Self-hostingNo documented wayYes
BYOCNo documented wayYes
Open sourceNo documented wayNo documented way
Scoped API keysYesNot published
Spend limitsYesNot published
Usage per sandbox (API)YesYes
Audit logsNo documented wayYes
SSONo documented wayYes
SOC 2No documented wayYes
HIPAANo documented wayYes
EU data residencyNo documented wayYes
Zero data retentionYesNot published

Performance

boat28.06 runs/s
NorthflankNot measured

Northflank Sandboxes is not in the public CPU benchmark we use, so we cannot say which is faster. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 V8 Web Tooling Benchmark runs per second at 4 vCPU / 8 GB, 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. For start time, ComputeSDK's latest one-at-a-time run measured a Northflank median of 83 ms at its default size. boat is not in the ComputeSDK benchmark.

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. Northflank is 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.

Scenarioboat, a monthNorthflank, 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$30 · Developer Sandbox (free tier)
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$106 · Developer Sandbox (free tier)
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$1,290 · Developer Sandbox (free tier)
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$359 · Developer Sandbox (free tier) · with limits
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$8,800 · $2000/mo · with limits$684 · Developer Sandbox (free tier) · with limits

boat: Plans cost $20, $100, $500 or $2,000 a month. The whole plan price comes back as VM time for that month, and unused time does not carry over. A default sandbox (4 vCPU / 8 GB) costs $0.036 an hour, billed per second while it runs. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Saved snapshots above the included count ($0.056 a day each) and the optional AI credentials proxy still charge while sandboxes are stopped. The $20 plan includes 12 starts a minute and 200 a day; each extra start costs $0.03 to $0.07. boat does not bill egress.

Northflank: Northflank bills per second for the plan size you pick, from $0.0038 an hour for 0.1 vCPU; 4 vCPU / 8 GB is $0.1333 an hour. There is no monthly fee and no start fee. There is no idle auto-pause, so a sandbox bills until you pause it. Volumes cost $0.11657 per GiB a month, also while paused, and outbound traffic costs $0.06 per GB.

Limits in those scenarios

In the first four scenarios, Northflank keeps files outside attached volumes only if you snapshot the filesystem before each pause and restore from it. Northflank also does not publish how many sandboxes can run at once, so 300 or 1,000 at a time is not confirmed. boat's limits: a stopped disk is kept for at least 14 days, and a machine failure loses the writes after the last good snapshot. In the burst scenario, even the $2,000 plan includes only 90 starts a minute and 2,400 a day. Extra starts cost $0.03 to $0.07, and starts above 270 a minute fail with 429, so 1,000 short jobs at once do not all start together.

ScenarioboatNorthflank
One coding agent, workdaysNone for this scenarioNone for this scenario
One agent that never stopsNone for this scenarioNone for this scenario
50 agents in parallelNone for this scenario
  • how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
Sandboxes for your usersNone for this scenario
  • not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)
1,000 short jobs at once
  • 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
  • not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)
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

Which one should you use?

Use Northflank when

you need GPUs next to the agent, regions outside Europe, your own container image, SOC 2, HIPAA or ISO 27001 reports, or sandboxes inside your own cloud account next to the rest of your apps.

  • GPU sandboxes. For agents that train, fine-tune or run models: Northflank has GPU sandboxes from L4 to H100, H200 and B200.
  • Regions around the world. For users far from Europe: Northflank runs in 17 regions, in the US, Asia, Australia, South America and Africa too.
  • Your own image, your own cloud, one platform. For teams that boot their own container image, must run in their own AWS, GCP or Azure account, or need compliance reports.

Use boat when

your agents work on one machine for hours or days and should find their files as they left them with no snapshot setup: installs, Docker, emulators, a desktop and a browser, with the agent driven from your code. boat runs only in Germany, Finland and France and has no GPU.

  • The disk comes back with no setup. On Northflank a pause wipes files outside attached volumes unless you snapshot the filesystem first and restore from it. That works on microVM sandboxes, but you set it up for each sandbox.
  • Agents you drive from outside. Northflank Harnesses start Claude Code, Codex, Cursor, OpenCode, Pi, OMP or Devin CLI for you, and the API manages their lifecycle. You talk to the agent through a terminal or SSH, so to drive many agents from your code you build that layer yourself.
  • A desktop and a browser inside. On Northflank you set it up: build an image with a desktop, a browser and a stream. Northflank's browser-agent guide covers Playwright without a desktop, and nested virtualization inside a sandbox is not documented.

Questions people ask

Is boat cheaper than Northflank?

In four of the five scenarios on this page, yes, at list prices. One agent that never stops (4 vCPU / 8 GB with 50 GB of disk) is $26 a month on boat against $106 on Northflank. For 1,000 short jobs at once, Northflank costs about $684 a month against $8,800 on boat, because boat charges $0.03 to $0.07 for each start above the plan's included number and refuses starts above 270 a minute. Below about $20 of use a month, Northflank's plan with no monthly fee costs less.

Does a Northflank sandbox keep its files when paused?

Files on attached volumes survive a pause. The rest of the disk is wiped unless you take a filesystem snapshot first and restore from it (microVM sandboxes only). Running processes end either way. boat keeps the disk on every stop for at least 14 days with no extra steps; memory and running programs are not saved on boat either.

Can I run Claude Code or Codex in each?

Yes. Northflank Harnesses start Claude Code, Codex, Cursor, OpenCode, Pi, OMP or Devin CLI, and you connect through a browser terminal or SSH. boat installs seven agents and adds an API to prompt, steer and follow them from your code.

Does Northflank have GPUs?

Yes. GPU sandboxes run under gVisor with cards from L4 to H100, H200, B200 and more. boat has no GPU on any size.

Can I run Docker and Android emulators in each?

Both give each sandbox its own kernel, so Docker can run inside. boat also exposes /dev/kvm for Android emulators and VMs. Northflank does not document that inside a sandbox.

Is boat SOC 2 compliant?

SOC 2 is in progress, and boat documents no HIPAA BAA. Northflank lists SOC 2 Type 2, HIPAA and ISO 27001. boat's live status is at status.ascii.dev and its data retention policy is at docs.boat.dev/data-retention.

Start a sandbox

Install the CLI, then run boat new.

7-day free trial

More comparisons