E2B vs Modal

E2B gives each agent a Firecracker microVM that can pause with its memory and wake on the next request. Modal gives you short-lived gVisor sandboxes inside a bigger AI cloud, with GPUs from T4 to B300.

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

Modal is a serverless cloud for AI work: inference, training, batch jobs and sandboxed code, all driven from Python, TypeScript or Go code.

Modal Sandboxes are containers you create from code, run commands in, and then terminate. By default they run under gVisor, a user-space kernel from Google; since October 2026 you can also pick a VM runtime with its own Linux kernel for Docker and FUSE (Battleships tracks that as a separate card, Modal VM Sandboxes). It suits teams that already run models on Modal and want short-lived, scalable code execution next to their GPUs.

Founders: Erik Bernhardsson and Akshat Bubna
Offices: New York City, Stockholm, San Francisco and London
Funding: Over $466M raised
Isolation: gVisor by default; VM runtime with its own kernel, generally available since 1 October 2026
Compliance: SOC 2 Type II; HIPAA on the Enterprise plan
GPUs: T4 up to B300, on the gVisor runtime only

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: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month	16th cheapest of 367 $4,143 a month	Can't run it	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both cap a session at 24 hours, so an always-on assistant has to be paused or restarted; bochka ranks 5th with no session cap on paid plans.	51st of 366, with limits $5,348 a month	196th of 366, with limits $1,924 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 fit short code runs; Modal ranks 19th against E2B's 37th, while E2B adds memory pause and wake on request.	37th cheapest of 345 $421 a month	19th cheapest of 345 $181 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 fit sandboxes for your users; E2B can wake a paused one on the next request, and bochka ranks 1st with stops that keep the disk.	23rd cheapest of 361 $2,354 a month	11th cheapest of 361 $811 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 E2B ranks 2nd and Modal 5th: both are built for many short rollouts, and E2B can fork a running sandbox with its memory.	2nd cheapest of 360 $9,384 a month	5th cheapest of 360 $19,038 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	59th cheapest of 364 $1,244 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 E2B runs Docker in every sandbox while Modal needs its VM runtime, but neither has nested virtualization for Android or VM builds; bochka ranks 4th.	337th of 377, with limits $1,429 a month	126th cheapest of 377 $1,793 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither keeps a dev box running all month, and Modal also resets the root disk when a sandbox ends; bochka ranks 18th.	192nd of 368, with limits $358 a month	138th of 368, with limits $23 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 has a Linux desktop for computer use and Modal only has a VNC example you set up yourself; bochka ranks 6th with a 60fps desktop.	32nd cheapest of 369 $1,342 a month	98th of 369, with limits $183 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	177th of 367, with limits $136 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	267th of 346, with limits $394 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	223rd of 338, with limits $8,795 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	Can't run it	2nd cheapest of 360 $200 a month
GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month Modal has GPUs from T4 to B300 and neither E2B nor bochka has any, so Modal is the pick here.	Can't run it	19th cheapest of 98 $1,187 a month	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	bochka
Isolation	Firecracker microVM with its own kernel	gVisor user-space kernel by default; VM runtime with its own kernel available	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU benchmark (4 vCPU / 8 GB)	12.61 runs/s	12.79 runs/s (default sandbox)	26.69 runs/s
Docker inside	Yes	Only with the VM runtime	Yes, in every sandbox
Nested virtualization	Not supported	VM runtime only, Team and Enterprise plans, on request	Yes, /dev/kvm for Android emulators and VMs
Longest session	1 hour on Hobby, 24 hours on Pro; pausing resets the clock	24 hours (default 5 minutes)	No cap on paid plans; you set the time to live
Pause and resume	Pauses with memory and disk; resumes in about a second with processes running	No paused state; a finished sandbox is gone, only Volumes keep files	Disk saved every minute and on stop; a stopped sandbox costs nothing and boots again
Wake on request	Yes, a paused sandbox resumes 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	Fork a running sandbox with its disk, without stopping it
GPUs	None	T4 to B300; 10 at once on Starter, 50 on Team	None
Desktop and computer use	Linux desktop for computer use	Not offered; an example shows how to set up 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	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP and a dedicated IP
Keeping API keys out of the sandbox	Secrets injected into outbound HTTPS headers (private beta)	Secrets are environment variables, or you run your own proxy in a sidecar	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
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	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	Yes	No	Yes
Nested virtualization	No	No	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	No	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	Yes	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

Modal12.79 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. E2B did 12.61 runs per second and Modal's default gVisor sandbox 12.79, so the two are close. bochka did 26.69, about twice the CPU work of either.

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

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, 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: Modal bills by the second for whichever is higher, the CPU and memory you request or what you use, until the sandbox is terminated. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and egress above the free allowance costs $0.04 per GiB.

Modal: bochka 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

Both E2B Pro and Modal cap a session at 24 hours, so neither fits the always-on agent. Modal also wipes the root disk when a sandbox ends and needs its VM runtime for Docker, which is why it misses the workday and 50-agent scenarios even though it costs less there. 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 that other tenants can slow down. bochka fits the first four scenarios but not that burst, because its start limits per hour and per day are too low.

Scenario	E2B	Modal	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	missing Docker inside 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 sells dedicated cores separately as “Sandbox (gVisor), request = size, any region”): 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

your agents run short jobs that pause between requests, need Docker in every sandbox, or you want an open-source runtime you can host.

Memory pause and wake on request. For jobs that sleep between requests: a paused E2B sandbox comes back in about a second with its processes still running.
Docker in the default sandbox. Every E2B sandbox is a microVM that runs Docker, while Modal needs its separate VM runtime for that.
Open source and your own cloud. E2B's runtime is Apache-2.0, and Enterprise customers can run it in their own AWS, GCP or Azure account.

Use Modal when

your sandboxes need GPUs, sit next to models you already run on Modal, or come in huge bursts across many regions.

GPUs on the same platform. If your agent trains or runs models, Modal rents GPUs from T4 to B300 next to its sandboxes.
More regions to pick from. Modal runs in the US, EU and Asia-Pacific and lets you pin a sandbox to a region, for a higher rate.
Very large bursts. Modal's Team plan runs up to 5,000 containers at once, which suits huge waves of short jobs.

Where bochka fits

E2B and Modal both shine at short jobs that start fast and end soon. If your agents work for hours or days, with installs, builds, Docker, emulators and a desktop, bochka gives each one a full, faster VM that keeps its disk and is never cut off.

No 24-hour cutoff

E2B Pro and Modal both end a session at 24 hours. On E2B your code has to pause and resume the sandbox; on Modal the root disk is gone, so files survive only if you wrote them to a Volume.

About twice the CPU work

On the same benchmark at 4 vCPU / 8 GB, bochka did 26.69 runs per second, E2B 12.61 and Modal's default sandbox 12.79. Every install, build and test waits about twice as long on either, and you pay for the wait.

A full machine with agents built in

Neither has /dev/kvm for Android emulators, Modal's default sandbox has no Docker, and on both you wire up the agent harness yourself. bochka ships Claude Code, Codex and others, a 60fps desktop, and a proxy that keeps real API keys out.

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

Questions people ask

Is E2B cheaper than Modal?

Usually not. One always-on agent costs $368 a month on E2B against $178 on Modal, and sandboxes for your users cost $1,395 against $792. For 1,000 short jobs at once E2B is cheaper, $2,797 against $3,193, and bochka costs less than E2B in every scenario and less than Modal in all but one agent on workdays.

Which is faster, E2B or Modal?

On the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, E2B did 12.61 runs per second and Modal's default sandbox 12.79, so they are about even. bochka did 26.69 in the same run.

Can E2B and Modal run Docker?

E2B runs Docker inside its sandboxes. Modal's default gVisor sandbox does not document Docker; you need its VM runtime. Every bochka sandbox runs Docker, and also has /dev/kvm for emulators, which neither of the others offers by default.

How long can a sandbox run on E2B and Modal?

E2B allows 1 hour on Hobby and 24 hours on Pro, and pausing resets the clock. Modal's default timeout is 5 minutes and its maximum is 24 hours. bochka has no session cap on paid plans.

Does E2B or Modal have GPUs?

Modal does, from T4 up to B300, on its gVisor runtime. E2B is CPU only, and so is bochka.

Can I pause a sandbox and come back later?

E2B can pause a sandbox with its memory and resume it in about a second. Modal has no paused state, so only files in a Volume survive. bochka saves the disk every minute and on stop, and a stopped sandbox costs nothing.

Try bochka

Install the CLI, then run bochka new.

Product preview