Modal VM Sandboxes vs Instabox

Both give an agent a Linux VM with its own kernel, root and Docker. Modal VM Sandboxes are short-lived machines that end within 24 hours on a large serverless AI platform, while Instabox is a new invite-only beta that keeps up to 5 fixed-size machines per account and can pause them with their memory.

The companies and products

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

Instabox

Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.

Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.

Isolation: Firecracker microVM per machine
Machine size: 4 vCPUs and 8 GiB of memory, the same for every machine; 20 GB storage
Machines per account: 5, in any state: paused and stopped ones count
Price: Free during the beta; no published price yet
Access: Invite-only beta; sign in with GitHub or Google
Regions: Not published; more regions are on the roadmap as an idea
Company: InsForge AI, Inc.

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. “84th cheapest of 367” means 83 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	Modal VM Sandboxes: price rank	Instabox: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs machines that keep their work: a Modal VM ends within 24 hours, Instabox keeps its machines but allows only 5, and boat keeps its disk and forks running sandboxes.	84th of 367, with limits $759 a month	No published price	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An agent that lives on one machine all month hits Modal's 24-hour cap; Instabox documents no maximum run time but pauses after 30 idle minutes unless you turn that off.	Can't run it	No published price	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	Can't run it	No published price	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 Modal Team runs thousands of short sandboxes at once, while Instabox's 5 machines per account, stopped ones included, cannot give one to each of many users.	Can't run it	No published price	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; Instabox's 5-machine cap rules them out, and boat's start limits queue the biggest bursts.	171st of 360, with limits $16,322 a month	No published price	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 Instabox's 5-machine cap limits how many evals run at once, while Modal and boat run many in parallel.	Can't run it	No published price	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 emulators need /dev/kvm, which Modal offers on Team and Enterprise on request, Instabox does not document, and boat has on every plan.	188th of 377, with limits $1,064 a month	No published price	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box you come back to fits Instabox better than Modal, since Instabox keeps the machine and adds SSH with mosh, while a Modal VM is gone after 24 hours.	Can't run it	No published price	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 Instabox has a desktop with a browser and a screenshot and click API, Modal has none on its VM runtime, and boat streams a 60fps desktop with a computer-use agent.	Can't run it	No published price	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	Can't run it	No published price	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	Can't run it	No published price	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	Can't run it	No published price	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	294th of 360, with limits $642 a month	No published price	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	No published price	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	No published price	Can't run it

Key features

Feature	Modal VM Sandboxes	Instabox	boat
Isolation	VM with its own Linux kernel on Cloud Hypervisor	Firecracker microVM with its own kernel and root	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine sizes	You set the CPU and memory each sandbox requests	One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused	Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above
CPU benchmark (4 vCPU / 8 GB)	15.54 runs/s	Not measured	26.69 runs/s
Docker, root	Yes; start dockerd yourself as the entrypoint	Docker and Docker Compose run inside, with root	Docker and Compose run inside, with root and systemd
Nested virtualization	Team and Enterprise plans only, on request	Not documented	Yes, /dev/kvm on every plan
Longest session	24 hours (default 5 minutes); continue with a filesystem snapshot	No maximum documented; an optional timeout of up to 24 hours pauses or deletes the machine, and it pauses after 30 idle minutes by default	No cap on paid plans; you set the time to live
Stop, pause and resume	No paused state; a finished sandbox is gone, only Volumes and snapshots keep files	Pause keeps memory and running programs; the docs say resume usually takes about a second	Stop for free, resume later with the whole disk; saved every minute
Fork and snapshots	Snapshot the filesystem and boot many new sandboxes from it; memory snapshots in alpha end the sandbox	Fork copies a stopped machine only; saving a snapshot stops a running machine first, up to 10 snapshots	Fork a running sandbox with its disk; disk saved every minute and on stop
Desktop and computer use	Not offered; an example shows how to set up Xvfb and VNC yourself	Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model	60fps Linux desktop with Chromium and a computer-use agent
Coding agents and API keys	Examples only; secrets are environment variables, or you run your own proxy in a sidecar	Templates and saved agent sign-ins in snapshots; a vault writes your secrets into each machine	Claude Code, Codex and others preinstalled with a prompt, steer and events API; a credentials proxy keeps real keys out
Hosting ports	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused	HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP
SSH	Supported	SSH through a gateway with short-lived certificates, paste-anywhere SSH tokens and mosh	SSH into every sandbox
Regions and outbound rules	US, EU and Asia-Pacific; block all outbound traffic or allow only chosen IP ranges or domains	Regions not published; outbound rules not documented	EU only (Germany, Finland, France); open internet, no provider-side allowlist
Machines at once	100 containers on Starter, 5,000 on Team, more on Enterprise	5 per account, in any state: paused and stopped ones count	Per-plan start limits; the $2,000 plan starts up to 600 an hour and 2,400 a day

Every feature Battleships tracks (43)

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

Performance

Modal VM Sandboxes15.54 runs/s

InstaboxNot measured

boat26.69 runs/s

On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, in the same run on 29 September 2026, boat finished 26.69 runs per second and Modal's VM runtime 15.54, so boat did about 1.7 times the CPU work in the same time. Instabox has no comparable measurement, so this page makes no speed claim for it. Instabox says a new machine's shell is ready in under a second; that has not been measured.

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. Instabox 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	Modal VM Sandboxes, a month	Instabox, 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	$15 · Starter · with limits	No published price	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$178 · Starter · with limits	No published price	$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	$2,229 · Starter · with limits	No published price	$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	$792 · Team	No published price	$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	$3,193 · Team · with limits	No published price	$2,000 · $2000/mo · with limits

Modal VM Sandboxes: Modal bills VM Sandboxes by the second for the higher of the CPU and memory you request or 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 costs 1.15x to 1.75x.

Instabox: Instabox is free during its invite-only beta, with 5 machines per user, and its pricing page says it is free until they figure out pricing. No price, rate or end date is published, so no bill can be compared with Modal's yet.

Instabox: boat 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

A Modal VM Sandbox lives at most 24 hours and its root disk is gone when it ends, so the workday, always-on and 50-agent scenarios only keep files in a Volume or snapshot and do not fit. Instabox publishes no rate, so none of the scenarios can be priced, and its 5-machine cap, counting paused and stopped machines, would rule out the 50-agent, user-sandbox and burst scenarios anyway; an API exec call also runs at most 10 minutes, with 4 at once. On boat the limit that bites is start speed: 1,000 jobs at once exceed even the $2,000 plan's hourly and daily start limits.

Scenario	Modal VM Sandboxes	Instabox	boat
One coding agent, workdays	files survive a stop only in Volumes: packages installed elsewhere reset	no published per-resource rate	None that bite
One agent that never stops	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	no published per-resource rate	None that bite
50 agents in parallel	files survive a stop only in Volumes: packages installed elsewhere reset	no published per-resource rate	None that bite
Sandboxes for your users	None that bite	no published per-resource rate	None that bite
1,000 short jobs at once	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	no published per-resource rate	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 Modal VM Sandboxes when

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

Huge bursts of short jobs. For teams running thousands of short jobs: Modal runs 5,000 containers at once on Team and more on Enterprise.
Regions and outbound rules. For teams that need it, Modal runs in the US, EU and Asia-Pacific and can limit a sandbox to chosen domains.
One platform with inference and training. For teams that already serve or train models on Modal: sandboxes and models share one account and one bill.

Use Instabox when

you want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with memory pause, mosh and a desktop.

Free during the beta. For trying things out: during the beta, each account runs 5 machines of 4 vCPU / 8 GiB for free.
Pause with memory. For agents that come back later: a paused machine keeps its memory and running programs, with no documented run-time cap.
SSH gateway with mosh. For people working in a terminal: mosh and paste-anywhere SSH tokens keep a session alive through sleep and network changes.

Where boat fits

Look at boat if your agents work for hours or days in a machine they keep, and you want to branch that work without stopping it. Modal ends each VM within 24 hours, and Instabox caps you at 5 fixed-size machines with no published terms yet. boat gives a faster full VM with a desktop, private port URLs and keys kept outside.

Work that keeps going and can branch

A Modal VM ends within 24 hours and loses its root disk unless you write snapshot or Volume code. Instabox forks only stopped machines and stops a machine to save it. boat saves the disk every minute and forks running sandboxes.

Real keys stay outside the sandbox

On Modal your keys sit in environment variables unless you build a sidecar proxy, and Instabox's vault writes secrets into each machine. boat's credentials proxy keeps real keys out for model providers and any HTTPS API.

A full machine for apps, emulators and screens

Instabox port URLs are open to anyone and go offline when paused, and Modal has no desktop. boat has token-protected URLs on 50 ports, /dev/kvm on every plan and a 60fps desktop, with agents driven from outside.

Use boat when your agents work for hours or days in a machine they keep, need to fork running work, serve private URLs, run emulators or use a desktop, on a faster VM with published terms. Compare it one to one: boat vs Modal VM Sandboxes and boat vs Instabox.

Questions people ask

Is Modal VM Sandboxes cheaper than Instabox?

It can't be compared yet. Instabox is free during its invite-only beta and publishes no price, so there is no bill to set against Modal's. Modal's Starter plan includes $30 of free credit each month.

Which is faster, Modal VM Sandboxes or Instabox?

Only Modal has been measured: 15.54 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, against boat's 26.69. Instabox says a new machine's shell is ready in under a second, but its speed has not been measured.

Can both run Docker?

Yes. Modal VM Sandboxes run Docker if you start dockerd as the entrypoint, and Instabox runs Docker and Docker Compose inside. For Android emulators, Modal offers nested virtualization on Team and Enterprise on request, and Instabox does not document it.

How long can a machine run on each?

A Modal VM Sandbox runs 5 minutes by default and 24 hours at most. Instabox documents no maximum run time, but a new machine pauses after 30 idle minutes unless you change that. boat has no session cap on paid plans.

How many machines can I run at once?

Modal allows 100 containers at once on Starter and 5,000 on Team. Instabox allows 5 machines per account, and paused and stopped ones count.

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