E2B vs Freestyle

Both pause sandboxes with their memory, fork them and wake them on the next request. E2B gives you short-lived Firecracker microVMs in the US, EU and APAC, while Freestyle gives you full KVM VMs with nested virtualization, bigger sizes and no session cap.

The companies and products

E2B

E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.

Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs, and its runtime is open source.

Freestyle

Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.

Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.

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. “16th cheapest of 367” means 15 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 workloadE2B: price rankFreestyle: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Freestyle runs Docker, systemd and nested virtualization with no session cap, while E2B stops at 24 hours on Pro; boat has all of that on CPUs about twice as fast as E2B's.
16th cheapest of 367
$4,143 a month
241st of 367, with limits
$3,311 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month hits E2B's 24-hour cap but runs on Freestyle once you leave the Free plan; boat keeps it running and a stopped boat sandbox costs nothing.
51st of 366, with limits
$5,348 a month
263rd of 366, with limits
$4,195 a month
5th cheapest of 366
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Both are built for this: short code runs that start fast, pause with their memory and wake on the next request.
37th cheapest of 345
$421 a month
40th cheapest of 345
$482 a month
186th of 345, 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
Both wake a paused user sandbox on its next request; boat gives each user a faster machine with a desktop and hosting built in.
23rd cheapest of 361
$2,354 a month
16th cheapest of 361
$1,358 a month
Cheapest of 361
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Both fork with memory, and E2B's high start rate and 1,100 concurrent slots on Pro++ suit many short rollouts that branch from one state.
2nd cheapest of 360
$9,384 a month
107th of 360, with limits
$6,600 a month
34th of 360, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
78th cheapest of 364
$1,975 a month
53rd cheapest of 364
$1,046 a month
10th cheapest of 364
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Freestyle has nested virtualization for Android builds and E2B does not, and boat did about twice E2B's work and 2.8 times Freestyle's on the CPU benchmark.
337th of 377, with limits
$1,429 a month
168th of 377, with limits
$625 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A dev box that runs all month needs no session cap, which Freestyle and boat have and E2B does not.
192nd of 368, with limits
$358 a month
98th cheapest of 368
$151 a month
18th cheapest of 368
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
E2B ships a Linux desktop for computer use, while on Freestyle you install the desktop, VNC and input tools yourself; boat streams its desktop at 60fps.
32nd cheapest of 369
$1,342 a month
234th of 369, with limits
$940 a month
6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
100th of 367, with limits
$746 a month
257th of 367, with limits
$482 a month
7th cheapest of 367
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
57th cheapest of 346
$554 a month
278th of 346, with limits
$482 a month
6th cheapest of 346
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
227th of 338, with limits
$9,223 a month
183rd of 338, with limits
$6,560 a month
71st of 338, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
11th cheapest of 360
$1,043 a month
272nd of 360, with limits
$482 a month
2nd cheapest of 360
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Can't run itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureE2BFreestyleboat
IsolationFirecracker microVM with its own kernelFull KVM VM with its own kernel on bare metal serversFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU benchmark (4 vCPU / 8 GB)12.61 runs/s9.64 runs/s26.69 runs/s
Session lengthUp to 1 hour on Hobby, 24 hours on Pro; pausing resets the clockNo provider cap; a VM runs until you pause, stop or delete itNo cap on paid plans; you set the time to live
Biggest machineUp to 8 vCPU / 8 GiB self-serve, more on requestUp to 32 vCPU / 64 GiB on Pro, 64 / 128 with custom limitsUp to 16 vCPU / 32 GB on the $100 plan and above
Nested virtualizationNot supportedYes, full KVM supportYes, /dev/kvm for Android emulators and VMs
Pause and resumeSaves memory and disk; resume takes about 1 second with processes still runningPause saves memory and disk; the same processes resume where they left offDisk is saved every minute and on stop; resume boots the machine again
ForkFork a running sandbox with its memory, up to 20 copies per call, with a short pauseClone a running VM without pausing it; snapshots capture memory and diskFork a running sandbox with its disk
Wake on requestYes; a paused sandbox can resume on the next HTTP request or SDK callYes; a VM paused by idle timeout resumes on the next traffic that reaches itNo; a stopped sandbox is started by API
Desktop and computer useLinux desktop for computer useGuides to install GNOME or Xvfb, VNC and Chromium yourselfLinux desktop streamed at 60fps, Chromium and computer use built in
Coding agentsTemplates and guides for many agents, run through the command APIclaude, codex, opencode and openclaw preinstalled, driven through exec or a terminalSeven agents preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandboxSecrets injected into outbound HTTPS headers (private beta)Credentials injected at the edge for HTTPS headers, Postgres and S3; the VM must trust the Freestyle CACredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Inbound accessHTTPS URL per port, public by default unless you turn on a tokenHTTPS on free style.dev names or your own domain, forward auth, other public protocolsHTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Outbound rulesAllow and deny lists by IP, CIDR or domainDefault-deny firewall with allow rules by IP, VM, VPC or exact domainOpen internet, no provider-side allowlist
Regions and self-hostingUS, EU and APAC; open-source runtime and bring your own cloud on EnterpriseNot listed; the docs name a San Jose, US data centerEU only (Germany, Finland, France), zero data retention
Every feature Battleships tracks (43)
FeatureE2BFreestyleboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdYesYesYes
Desktop GUIYesNoYes
BrowserYesNoYes
Computer-use APIYesNoYes
SSHYesYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkYesYesNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoYesYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APINoNoYes
MCP serverYesNoNo
GPUNoYesNo
WindowsNoNoNo
Arm64NoNoNo
Self-hostingYesNoNo
BYOCYesNoNo
Open sourceYesNoNo
Scoped API keysNot publishedYesYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)NoNoYes
Audit logsNot publishedYesNo
SSONoYesNo
SOC 2YesNot publishedNo
HIPAAYesNot publishedNo
EU data residencyYesNoYes
Zero data retentionNot publishedNot publishedYes

Performance

E2B12.61 runs/s
Freestyle9.64 runs/s
boat26.69 runs/s

On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, E2B did 12.61 runs per second and Freestyle did 9.64, so E2B finished about 1.3 times as much CPU work. boat did 26.69, about twice E2B and 2.8 times Freestyle. This measures CPU speed only, not start time, where Freestyle advertises about 65 ms.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite.

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.

ScenarioE2B, a monthFreestyle, 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
$202 · Pro$27 · Free$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$368 · Pro · with limits$159 · Free$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
$2,773 · Pro$2,139 · Pro$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
$1,395 · Pro+ (600 concurrent)$581 · Pro$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
$2,797 · Pro++ (1,100 concurrent)$1,305 · Pro · with limits$2,000 · $2000/mo · with limits

E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox. Pro costs $150 a month for higher limits with no usage credit, and more concurrency costs $500 a month per 500 slots.

Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. Hobby and Pro set a $50 or $500 monthly minimum that counts as usage, and a paused VM bills only for storage.

Freestyle: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

E2B caps a session at 24 hours on Pro, so it does not fit an agent that never stops, and its Pro plan includes only 20 GiB of disk. Freestyle has no session cap, but Pro allows 400 concurrent VMs, so it does not fit 1,000 short jobs at once, where E2B Pro++ does. Freestyle also has no idle timeout by default, so a VM bills until you pause it or set one. boat fits every scenario except the 1,000-job burst, where its $2,000 plan caps starts per hour and per day.

ScenarioE2BFreestyleboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
None that biteNone that bite
One agent that never stops
  • Pro: sessions capped at 24 h
  • disk beyond 20 GiB: price unknown
  • egress price not published
None that biteNone that bite
50 agents in parallel
  • egress price not published
None that biteNone that bite
Sandboxes for your users
  • egress price not published
None that biteNone that bite
1,000 short jobs at once
  • egress price not published
  • bursts above 300 starts/min are queued (a burst of 333 takes ~2 min to start)
  • Pro: max 400 concurrent
  • shared vCPUs on this tier”): heavy, sustained CPU use can be slowed by other tenants
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use E2B when

you run many short jobs that pause between requests, need very high concurrency, or must run in the US, EU or APAC or in your own cloud.

  • More regions and your own cloud. E2B runs in the US, EU and APAC, its runtime is open source, and Enterprise can run in your own cloud account.
  • Fast memory pause for short jobs. For short jobs that sleep between requests, a paused sandbox comes back in about a second with its processes running.
  • A desktop out of the box. For computer-use agents, E2B ships a Linux desktop, while on Freestyle you install the display stack yourself.

Use Freestyle when

your VMs need nested virtualization, sessions with no cap, more than 8 vCPU in one machine, or a default-deny firewall per VM.

  • Full VMs with no session cap. For long agent work, Freestyle VMs have nested virtualization and run until you stop them, while E2B stops at 24 hours.
  • Bigger machines. For heavy single jobs, Freestyle Pro allows VMs up to 32 vCPU / 64 GiB, while E2B self-serve stops at 8 / 8.
  • Network controls. Every VM starts behind a default-deny firewall, with private VPCs and credential injection for Postgres and S3 too.

Where boat fits

If your agents do real work for hours, like installs, builds, tests, Docker and a browser, look at boat. It gives each agent a full VM with faster CPUs than either, no session cap, a desktop built in and an API to drive the agents inside from outside.

Faster CPUs for every build

boat did 26.69 runs per second on the CPU benchmark, against 12.61 for E2B and 9.64 for Freestyle. Freestyle says it oversubscribes its hosts, and on both every install and test takes two to three times as long.

A full machine with no cutoff

On E2B a long task hits the 24-hour cap and Android emulators cannot start without nested virtualization. Freestyle has both, but on Free its monthly allowances are hard stops that pause your VM.

Agents and a desktop ready to drive

Neither has an API to prompt and steer the coding agents inside, so you parse CLI output yourself. On Freestyle you also build the desktop, VNC and click layer before a computer-use agent can start.

Use boat when your agents do real work for hours: builds, tests, Docker, emulators, a desktop and a browser, on fast CPUs, with an API to drive the agents inside from outside. Compare it one to one: boat vs E2B and boat vs Freestyle.

Questions people ask

Is E2B cheaper than Freestyle?

In most scenarios on this page, Freestyle costs less: one coding agent on workdays is $27 on Freestyle against $202 on E2B, and 50 agents in parallel are $2,139 against $2,773. For 1,000 short jobs at once, only E2B Pro++ fits, because Freestyle Pro caps at 400 concurrent VMs. boat costs less than both in every scenario.

Which is faster, E2B or Freestyle?

On the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, E2B did 12.61 runs per second and Freestyle did 9.64, so E2B did about 1.3 times the work. boat did 26.69 on the same test. Freestyle advertises VM starts in about 65 ms, which this test does not measure.

Can E2B and Freestyle run Docker and Android emulators?

Both run Docker inside the sandbox. Freestyle also has full KVM support for Android emulators and VMs, while E2B's docs say nested virtualization is not supported. boat exposes /dev/kvm too.

Can a sandbox run for days on E2B or Freestyle?

Not in one E2B session: it stops after 24 hours on Pro and 1 hour on Hobby, though pausing resets the clock. Freestyle has no provider cap, but on Free its monthly allowances are hard stops. boat has no session cap on paid plans.

Do E2B and Freestyle both pause with memory?

Yes. Both save memory and disk, resume the same processes, fork running sandboxes and wake a paused one on the next request. boat saves the disk every minute and on stop, but resuming boots the machine again.

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.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons