Docker Cloud Sandboxes vs Modal VM Sandboxes

Both give a coding agent its own Linux VM with Docker inside, and both end it within 24 hours. Docker's sandbox is the same microVM you run on your laptop and keeps its memory when it stops, while Modal's VM Sandboxes are short-lived machines that scale to thousands at once on a big AI platform.

The companies and products

Docker Cloud Sandboxes

Docker Cloud Sandboxes runs Docker's sbx coding-agent microVMs on Docker-managed compute instead of your laptop.

Each sandbox is a microVM with its own Linux kernel and its own Docker Engine, started from the same sbx CLI you use locally, with Claude Code, Codex and other agents ready to run. You can move a sandbox from your laptop to the cloud and back, publish HTTPS ports and SSH in. It launched on September 24, 2026, is billed pay-as-you-go on a personal Docker account, and is built for developers who want their local agent sandboxes to keep going off their machine.

Isolation: MicroVM per sandbox with its own Linux kernel and its own Docker Engine
Launched: September 24, 2026
Machine sizes: 1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, CPU only, amd64 or arm64 by account
Session length: 1 hour by default, extendable to 24 hours from creation
Default quota: 10 concurrent and 50 stored sandboxes per account
Account: Pay-as-you-go plan on a personal Docker account, even inside an organization
Regions: Not published

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. “280th cheapest of 367” means 279 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	Docker Cloud Sandboxes: price rank	Modal VM Sandboxes: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both end a sandbox within 24 hours; Docker also allows only 10 at a time by default, and Modal loses files outside a Volume, while boat keeps its disk with no session cap.	280th of 367, with limits $4,928 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 agent that lives on its machine all month fits neither: Docker ends a sandbox 24 hours after creation and Modal stops at 24 hours too.	276th of 366, with limits $5,110 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 suit both: Docker bills small sandboxes by the second and keeps memory between runs, and Modal starts fast and runs thousands at once on Team.	119th of 345, with limits $233 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 Serving many users at once needs more than Docker's default 10 concurrent sandboxes; Modal's Team plan runs 5,000 containers, and boat keeps each user's disk while it waits.	136th of 361, with limits $1,628 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 Huge bursts of short rollouts are what Modal is built for, while Docker's default of 10 at once holds a burst back, and boat queues very large bursts.	114th of 360, with limits $7,000 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	167th of 364, with limits $1,400 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 run Docker builds in a VM; Android or VM-image builds need /dev/kvm, which Modal offers on Team and Enterprise on request, Docker does not document, and boat has on every plan.	172nd of 377, with limits $672 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	127th of 368, with limits $204 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 Neither ships a screen: Docker's sandboxes are terminal only and Modal leaves Xvfb and VNC to you, while boat has a 60fps desktop with Chromium.	268th of 369, with limits $1,400 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	277th of 367, with limits $700 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	262nd of 346, with limits $350 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	190th of 338, with limits $7,000 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 Many agents at once hits Docker's 10-sandbox default first; Modal scales wider but each VM ends within 24 hours.	248th of 360, with limits $350 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	Docker Cloud Sandboxes	Modal VM Sandboxes	boat
Isolation and Docker	MicroVM with its own Linux kernel and Docker Engine; hypervisor not named; agent runs as non-root with sudo	VM on Cloud Hypervisor with its own Linux 7.2 kernel; Docker, systemd and FUSE work, you start dockerd yourself	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts, with Docker, root and systemd
Longest session	1 hour by default, at most 24 hours from creation; resuming starts a new timer	5 minutes by default, at most 24 hours; continue from a filesystem snapshot	No cap on paid plans; you set the time to live
Stop and resume	Stop keeps memory and files, and resume picks up where it left off; unused snapshots are deleted after 7 days	No paused state; a finished sandbox is gone, and only Volumes and snapshots keep files	Stop for free and resume with the whole disk, saved every minute; resume boots the machine again
Snapshot and fork	Snapshot a running sandbox with its disk, or disk and memory, and restore it as a new sandbox	Filesystem snapshot boots any number of new sandboxes; memory snapshots are alpha and end the sandbox	Fork a running sandbox with its disk
Sandboxes at once	10 by default; no published way to raise it	100 containers on Starter, 5,000 on Team, more on Enterprise	100 on the $20 plan, up to 2,000 on higher plans, self-serve
CPU benchmark (4 vCPU / 8 GB)	Not measured	15.54 runs/s	26.69 runs/s
Nested virtualization	Not documented	Team and Enterprise plans only, on request	Yes, /dev/kvm on every plan for Android emulators and VMs
Desktop, browser, computer use	Terminal sessions only	Not offered; an example shows how to set up Xvfb and VNC yourself	60fps Linux desktop with Chromium and a computer-use API
Coding agents	Claude Code, Codex, Copilot, OpenCode and more, run and attached to from the sbx CLI	Examples only; you install the agent yourself	Seven agents preinstalled, with a prompt, steer and events API to drive them from outside
Keeping API keys out of the sandbox	Cloud proxy sets the auth header for built-in AI services and custom hosts; the sandbox sees a placeholder	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
Inbound access	Public HTTPS URL per published port, not protected by Docker sign-in; no TCP tunnel; SSH with Docker-issued certificates	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 rules by host, with allow-all, balanced and deny-all presets	Block all, IP-range allowlist, domain allowlist (beta)	Open internet, no provider-side allowlist
Regions	Not published	US, EU and Asia-Pacific; pinning a region costs 1.15x to 1.75x	EU only: Germany, Finland, France
Laptop and cloud	Same microVM and CLI locally or in the cloud; move a sandbox either way	Cloud only	Cloud only

Every feature Battleships tracks (43)

Feature	Docker Cloud Sandboxes	Modal VM Sandboxes	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	No	Yes	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Yes	Yes
Desktop GUI	No	No	Yes
Browser	No	No	Yes
Computer-use API	No	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	No	Yes	No
Wake on request	Not published	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	Not published	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	Yes	No	No
Self-hosting	No	No	No
BYOC	No	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Not published	Not published	Yes
Usage per sandbox (API)	No	Not published	Yes
Audit logs	Not published	Yes	No
SSO	Yes	Yes	No
SOC 2	No	Yes	No
HIPAA	No	Yes	No
EU data residency	No	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

Docker Cloud SandboxesNot measured

Modal VM Sandboxes15.54 runs/s

boat26.69 runs/s

Docker Cloud Sandboxes has no comparable measurement yet: it launched in September 2026, is not in the hpc-sandbox-benchmarks runs, and Docker does not say what hardware it uses. In the same run on 29 September 2026 at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 Node.js build-and-test runs per second and boat did 26.69, about 1.7 times the CPU work in the same 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. Docker Cloud Sandboxes has no published run in this suite yet, so there is no like-for-like number to compare.

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	Docker Cloud Sandboxes, a month	Modal VM Sandboxes, a month	boat, 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	$49 · Docker Agentic Platform (pay-as-you-go)	$15 · Starter · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$204 · Docker Agentic Platform (pay-as-you-go) · 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	$2,464 · Docker Agentic Platform (pay-as-you-go) · with limits	$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	$700 · Docker Agentic Platform (pay-as-you-go) · with limits	$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	$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits	$3,193 · Team · with limits	$2,000 · $2000/mo · with limits

Docker Cloud Sandboxes: Docker bills per second for the size you pick, from $0.07 an hour for 1 vCPU / 2 GiB to $1.12 an hour for 16 vCPU / 32 GiB, with no monthly fee. A stopped sandbox costs nothing, and volumes and egress are free.

Modal VM Sandboxes: Modal bills by the second for whichever is higher, 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, pinning a region costs 1.15x to 1.75x, and egress above the allowance is $0.04 per GiB.

Modal VM Sandboxes: boat 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 one agent that never stops fits neither. Docker's default of 10 concurrent sandboxes is what rules it out for 50 agents in parallel, sandboxes for your users and 1,000 short jobs at once. Modal's root disk is gone when a VM ends, so the workday, always-on and fleet scenarios keep only files in a Volume or snapshot, and its 1,000-job burst relies on shared CPU above the request. On boat the limit that bites is start speed: even the $2,000 plan queues a 1,000-job burst.

Scenario	Docker Cloud Sandboxes	Modal VM Sandboxes	boat
One coding agent, workdays	None that bite	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
One agent that never stops	Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
50 agents in parallel	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
Sandboxes for your users	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	None that bite	None that bite
1,000 short jobs at once	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	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 Docker Cloud Sandboxes when

you already run agents in sbx on your laptop and want a few of them to keep going in the cloud for up to a day, with memory kept across stops and outbound rules by host.

Pause with memory. For agents that wait between steps: a stopped Docker sandbox comes back with its memory and running processes.
The same sandbox on your laptop. If you already run sbx locally, the cloud is the same microVM and CLI, and you can move a sandbox either way.
Agents ready to start. Claude Code, Codex, Copilot and OpenCode start from the sbx CLI, where Modal leaves the agent setup to you.

Use Modal VM Sandboxes when

you run large bursts of short jobs that finish within a day, need regions outside Europe, or already run your models on Modal.

Thousands at once. For huge bursts of short jobs: Modal runs 5,000 containers at once on Team, while Docker defaults to 10.
Regions you can pick. Modal runs in the US, EU and Asia-Pacific and lets you pin a region; Docker does not publish its regions.
One platform with inference and training. Teams that already serve or train models on Modal can keep sandboxes on the same account and bill.

Where boat fits

Both Docker and Modal end each sandbox within 24 hours and give the agent a terminal, not a screen. If your agents work for days, need Android emulators or a browser, or have to be driven from your own app, boat gives each one a full VM that keeps its disk and has no session cap on paid plans.

No 24-hour cutoff

Docker ends a sandbox 24 hours after creation, so your code must stop and resume it in time. Modal ends its VM within 24 hours and drops the root disk, so you snapshot and reboot or keep files in a Volume.

A screen and /dev/kvm

Docker's sandboxes are terminal only and do not document nested virtualization. Modal offers /dev/kvm only on Team and Enterprise on request, and you install Xvfb, VNC and a browser yourself. boat has both on every plan.

Agents driven from outside

On Docker you attach to an agent's terminal from the sbx CLI and parse its text; on Modal you install the agent and its keys sit in environment variables. boat has a prompt, steer and events API and a credentials proxy.

Use boat when your agents work for days or by the dozen in a machine they come back to, need Android emulators, a desktop or a browser, or have to be driven from your own app through an API. Compare it one to one: boat vs Docker Cloud Sandboxes and boat vs Modal VM Sandboxes.

Questions people ask

Is Docker Cloud Sandboxes cheaper than Modal VM Sandboxes?

For one agent on workdays Modal is cheaper, $15 a month against $49 on Docker, but Modal's files reset between days unless you use a Volume. For sandboxes for your users Modal fits at $792 a month on Team, while Docker's default of 10 at once does not fit. boat runs these at $20 and $200 a month.

Which is faster, Docker Cloud Sandboxes or Modal VM Sandboxes?

There is no comparable CPU measurement for Docker yet. Modal's VM runtime did 15.54 runs per second on the hpc-sandbox-benchmarks test at 4 vCPU / 8 GB, and boat did 26.69 in the same run.

Can Docker Cloud Sandboxes and Modal VM Sandboxes run Docker?

Yes. Each Docker sandbox has its own Docker Engine, and Modal's VM runtime runs Docker, systemd and FUSE once you start dockerd. Modal also offers /dev/kvm on Team and Enterprise on request, which Docker does not document and boat has on every plan.

How long can a sandbox run on each?

Docker defaults to 1 hour and allows up to 24 hours from creation; resuming a stopped one starts a new timer. Modal defaults to 5 minutes and stops at 24 hours, after which you continue from a filesystem snapshot. boat has no session cap on paid plans.

How many sandboxes can I run at once?

Docker allows 10 concurrent and 50 stored sandboxes per account by default. Modal runs 100 containers on Starter and 5,000 on Team. boat runs 100 on the $20 plan and up to 2,000 on higher plans.

Does either keep memory when a sandbox stops?

Docker does: a stopped sandbox keeps its memory and files, and you can fork a running one with its memory. Modal has no paused state, and its memory snapshots are alpha and end the sandbox. boat keeps the disk on stop, and resume boots the machine again.

Try boat

Install the CLI, then run boat new.

7-day free trial