E2B vs Modal VM Sandboxes

Both give an agent a small Linux VM with its own kernel that runs for at most 24 hours. E2B can pause a sandbox with its memory and wake it on the next request, while Modal VM Sandboxes have no paused state but run a bit faster and sit inside a big serverless AI platform.

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.

Isolation: Firecracker microVM per sandbox
Regions: US by default; EU and APAC on Pro and above, enabled by support
Open source: Runtime published under Apache-2.0, can run on your own Linux host with KVM
Bring your own cloud: Enterprise data plane in your AWS, GCP or Azure account
Compliance: SOC 2 Type II; HIPAA BAA on request
Machine size: 1 to 8 vCPU and 1 to 8 GiB RAM, CPU only

Modal VM Sandboxes

Modal is a serverless cloud for AI work, and VM Sandboxes are the version of its sandboxes that run in a virtual machine with their own Linux kernel.

You create a VM Sandbox from Python, TypeScript or Go code with runtime="vm", run commands in it, and terminate it when the job is done. Modal built the runtime on the Rust-based Cloud Hypervisor, so Docker, FUSE, systemd and nested cgroups work, with the same API, images and prices as its gVisor sandboxes. It became generally available on 1 October 2026 and suits teams that want many short-lived agent machines next to Modal's inference and training.

Founders: Erik Bernhardsson and Akshat Bubna
Offices: New York, Stockholm and San Francisco
Funding: Over $466M raised
Isolation: Virtual machine per sandbox on Cloud Hypervisor, with its own Linux 7.2 kernel
Generally available: 1 October 2026; early customers launched over 20 million VMs before that
Session length: Default 5 minutes, maximum 24 hours
Compliance: SOC 2 on every plan; HIPAA on Enterprise

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 workload	E2B: price rank	Modal VM Sandboxes: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month E2B ranks 16th and fits fully, while Modal VM Sandboxes rank 84th because files outside a Volume reset; bochka ranks 3rd with no session cap and a faster CPU.	16th cheapest of 367 $4,143 a month	84th of 367, with limits $759 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 the 24-hour cap on both, so E2B has to pause and resume and Modal has to start a new sandbox.	51st of 366, with limits $5,348 a month	Can't run it	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 Short code runs that sleep between requests fit E2B well, because a paused sandbox wakes on the next call with its memory intact.	37th cheapest of 345 $421 a month	Can't run it	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 E2B fits and wakes a paused user sandbox on the next request; bochka ranks 1st, with a stopped sandbox that keeps its disk and costs nothing while it waits.	23rd cheapest of 361 $2,354 a month	Can't run it	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 E2B ranks 2nd here: memory forks and fast starts suit many short rollouts, while Modal VM Sandboxes rank 171st on this workload.	2nd cheapest of 360 $9,384 a month	171st of 360, with limits $16,322 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	Can't run it	10th cheapest of 364 $200 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Both are a compromise for CI, and only Modal offers nested virtualization (Team and Enterprise, on request); bochka ranks 4th with /dev/kvm on every plan.	337th of 377, with limits $1,429 a month	188th of 377, with limits $1,064 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	192nd of 368, with limits $358 a month	Can't run it	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 has a Linux desktop for computer use and Modal VM Sandboxes do not; bochka streams its desktop at 60fps with a computer-use API.	32nd cheapest of 369 $1,342 a month	Can't run it	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	Can't run it	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	Can't run it	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	Can't run it	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 E2B ranks 11th and Modal VM Sandboxes rank 294th; bochka ranks 2nd, with fast parallel machines that can fork while running.	11th cheapest of 360 $1,043 a month	294th of 360, with limits $642 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 it	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	Can't run it

Key features

Feature	E2B	Modal VM Sandboxes	bochka
Isolation	Firecracker microVM with its own kernel	VM with its own Linux kernel on Cloud Hypervisor	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU benchmark (4 vCPU / 8 GB)	12.61 runs/s	15.54 runs/s	26.69 runs/s
Longest session	1 hour on Hobby, 24 hours on Pro; pausing resets the clock	24 hours (default 5 minutes); continue from a filesystem snapshot	No cap on paid plans; you set the time to live
Pause and resume	Saves memory and disk; resume takes about 1 second with processes still running	No paused state; a finished sandbox is gone, only Volumes and snapshots keep files	Stop for free, resume later with the whole disk; saved every minute
Wake on request	Yes; a paused sandbox can resume on the next HTTP request or SDK call	No	No; a stopped sandbox is started by API
Fork	Fork a running sandbox with its memory, up to 20 copies per call	Snapshot the filesystem into an image and boot new sandboxes from it; memory snapshots are alpha and end the sandbox	Fork a running sandbox with its disk
Docker, systemd, root	Yes	Yes; start dockerd yourself as the entrypoint	Yes, in every sandbox
Nested virtualization	Not supported	Team and Enterprise plans only, on request	Yes, /dev/kvm on every plan
Desktop and computer use	Linux desktop for computer use	Not offered; an example shows how to set up Xvfb and VNC yourself	60fps desktop, Chromium and computer-use API built in
Inbound access	HTTPS URL per port, public by default unless you turn on a token; no raw TCP, no dedicated IP	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Outbound rules	Allow and deny lists by IP, CIDR or domain	Block all, IP-range allowlist, domain allowlist (beta)	Open internet, no provider-side allowlist
Coding agents and API keys	Templates and guides for many agents, run through the command API; secrets injected into outbound HTTPS headers (private beta)	Examples only; secrets are environment variables, or you run your own proxy in a sidecar	Seven agents preinstalled with a prompt, steer and events API; credentials proxy for model providers and any HTTPS API
Regions	US by default; EU and APAC on Pro and above, enabled by support	US, EU and Asia-Pacific plus narrower regions; pinning costs 1.15x to 1.75x	EU only (Germany, Finland, France)
Self-hosting	Open-source runtime, plus bring your own cloud on Enterprise	No	No

Every feature Battleships tracks (43)

Feature	E2B	Modal VM Sandboxes	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	No	Yes	Yes
Root	Yes	Yes	Yes
Systemd	Yes	Yes	Yes
Desktop GUI	Yes	No	Yes
Browser	Yes	No	Yes
Computer-use API	Yes	No	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	Yes	No	Yes
Fork/clone	Yes	Yes	Yes
Live fork (no pause)	Yes	Yes	Yes
Memory fork	Yes	Yes	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	Yes	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	No	Yes	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	Yes	No	Yes
Secret proxy for any API	Yes	No	Yes
Preinstalled agents	Yes	No	Yes
Agent harness API	No	No	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	Yes	No	No
BYOC	Yes	No	No
Open source	Yes	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	No	Not published	Yes
Audit logs	Not published	Yes	No
SSO	No	Yes	No
SOC 2	Yes	Yes	No
HIPAA	Yes	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

E2B12.61 runs/s

Modal VM Sandboxes15.54 runs/s

bochka26.69 runs/s

All three ran the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB in the same run on 29 September 2026. bochka did 26.69 runs per second, Modal's VM runtime 15.54 and E2B 12.61, so Modal did about 1.2 times E2B's CPU work and bochka about 1.7 times Modal's and twice E2B's. This measures CPU speed only, not start time.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Modal VM Sandboxes measured on: VM Sandbox, request = size.

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	E2B, a month	Modal VM Sandboxes, a month	bochka, 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	$15 · Starter · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$368 · Pro · with limits	$178 · Starter · 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	$2,773 · Pro	$2,229 · Starter · 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	$1,395 · Pro+ (600 concurrent)	$792 · Team	$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)	$3,193 · Team · 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.

Modal VM Sandboxes: Modal bills by the second for the higher of the CPU and memory you request or what you use, until the sandbox ends. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and pinning a region multiplies the price by 1.15x to 1.75x.

Modal VM Sandboxes: bochka charges one hourly rate per machine size, by the second, only while the sandbox runs. Plans start at $20 a month and the whole fee becomes usage credit; a stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Both cap a session at 24 hours, so neither fits the always-on scenario. Modal also misses the workday and 50-agent scenarios, because files outside a Volume reset when the VM ends, while E2B fits them but includes only 20 GiB of disk on Pro and does not publish an egress price. For 1,000 short jobs at once, E2B Pro++ fits and only queues bursts above 300 starts a minute, while Modal's Team tier runs on shared vCPUs; bochka's start limits make that scenario a poor fit too.

Scenario	E2B	Modal VM Sandboxes	bochka
One coding agent, workdays	disk beyond 20 GiB: price unknown egress price not published	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
One agent that never stops	Pro: sessions capped at 24 h disk beyond 20 GiB: price unknown egress price not published	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
50 agents in parallel	egress price not published	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
Sandboxes for your users	egress price not published	None that bite	None 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)	shared vCPUs on this tier (Modal (VM Sandboxes) sells dedicated cores separately as “VM Sandbox, request = size”): 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 sleep between requests and should wake with their memory intact, or want an open-source runtime you can host yourself.

Pause with memory, wake on request. For jobs that sleep between requests: a paused E2B sandbox wakes on the next call in about a second, processes still running.
Memory forks and a desktop. E2B forks a running sandbox with its memory, up to 20 copies per call, and ships a Linux desktop for computer use.
Open source and your own cloud. Its runtime is Apache-2.0, and Enterprise customers can run it in their own AWS, GCP or Azure account.

Use Modal VM Sandboxes when

you need a full kernel with raw TCP and nested virtualization on Team for jobs that finish within a day, or already run your models on Modal.

More kernel and network features. Modal VMs offer nested virtualization on Team by request, plus raw TCP tunnels and an inbound IP allowlist.
A bit more CPU per sandbox. In the same benchmark run at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 runs per second and E2B did 12.61.
One platform with inference and training. Useful if you already serve or train models on Modal: sandboxes and models sit on one account and one bill.

Where bochka fits

E2B and Modal VM Sandboxes are both built around short sessions that end within a day. If your agents work for hours or days on a machine they come back to, with Docker, emulators and a desktop, bochka gives them a faster VM that keeps its disk and has no session cap on paid plans.

No 24-hour cutoff, disk kept

Both stop a session at 24 hours. On E2B your code has to pause and resume it; on Modal the VM's root disk is gone, so you snapshot the filesystem or use a Volume and boot a new sandbox.

Faster CPU and /dev/kvm

bochka did 26.69 runs per second against 12.61 on E2B and 15.54 on Modal, so builds wait less. E2B has no nested virtualization, and Modal offers it only on Team and Enterprise after you ask.

Desktop, agents and keys built in

Modal has no desktop, so you install Xvfb, VNC and a browser yourself. On both, you build the agent harness, and keys sit in environment variables or a beta header injector instead of a credentials proxy for any HTTPS API.

Use bochka when your agents work for hours or days in a machine they come back to: installs, builds, tests, Docker, emulators and a desktop, on a faster VM that keeps its disk and never cuts them off. Compare it one to one: bochka vs E2B and bochka vs Modal VM Sandboxes.

Questions people ask

Is E2B cheaper than Modal VM Sandboxes?

In most of our scenarios Modal costs less: sandboxes for your users cost $1,395 a month on E2B against $792 on Modal. For 1,000 short jobs at once, E2B is cheaper at $2,797 a month against $3,193, and bochka is $200 a month for the user sandboxes.

Which is faster, E2B or Modal VM Sandboxes?

On the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 runs per second and E2B did 12.61. bochka did 26.69 in the same run. This measures CPU speed, not start time.

How long can a sandbox run on E2B and Modal?

Both stop at 24 hours: E2B on Pro (1 hour on Hobby, and pausing resets the clock) and Modal on every plan, with a 5-minute default. bochka has no session cap on paid plans.

Can E2B and Modal run Docker and Android emulators?

Both run Docker inside the sandbox. E2B does not support nested virtualization, and Modal offers it on Team and Enterprise after you ask support. bochka exposes /dev/kvm on every plan.

Can Modal VM Sandboxes pause with memory like E2B?

Not in the same way. E2B pauses with memory and resumes in about a second with processes running. Modal has no paused state; its memory snapshots are alpha, end the sandbox and expire after 7 days.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview