Vercel Sandbox vs smol machines
Both run each sandbox in a microVM with its own kernel. Vercel Sandbox runs short sessions of up to 24 hours in 19 regions, while smol machines has no session cap, branches running machines with their memory, and its open-source engine also runs on your own servers.
The companies and products
Vercel Sandbox
Vercel is a cloud platform for web apps and agents, and Vercel Sandbox is its product for running untrusted or agent-written code in isolated Linux microVMs.
Each sandbox is a Firecracker microVM with its own kernel, started from a Vercel image, your own OCI image, or a saved snapshot. You drive it with the JavaScript or Python SDK or the sandbox CLI: run commands, move files, open ports, and set network rules. It is aimed at code interpreters, app builders, test runs and agent tools, and Vercel's docs say it is not meant to run nonstop.
smol machines
smol machines makes fast, isolated Linux microVMs that run the same way on your laptop, in their hosted cloud, or on your own servers.
The core is smolvm, an open-source microVM engine built on libkrun, where each machine has its own guest kernel. smol cloud is the paid hosted service that runs fleets of those machines behind a REST API and Node, Python and Rust SDKs. It is built for developers who want one VM model from local development to production, with live branching of running machines.
- Uptime SLA
- 99.95% on Pro, Startup and 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. “22nd cheapest of 345” means 21 of the other 344 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 | Vercel Sandbox: price rank | smol machines: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Neither has a desktop, a browser or nested virtualization, and Vercel also stops each session at 24 hours; boat ranks 3rd with a full match. | 244th of 367, with limits $3,351 a month | 73rd of 367, with limits $604 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Vercel's docs say sandboxes are not designed to run nonstop, and smol machines can run nonstop but has no desktop, browser or keys kept outside the guest. | 257th of 366, with limits $3,657 a month | 148th of 366, with limits $1,038 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 well: smol machines ranks 12th with a one-minute minimum and a /code endpoint, and Vercel Sandbox ranks 22nd billing CPU only while code uses it. | 22nd cheapest of 345 $216 a month | 12th cheapest of 345 $140 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 All three fit; boat ranks first, smol machines ranks 7th and Vercel Sandbox ranks 15th on cost for the same work. | 15th cheapest of 361 $1,267 a month | 7th cheapest of 361 $531 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 Vercel Sandbox ranks 3rd with a full match thanks to high concurrency, while smol machines ranks 111th as a compromise even though it can branch a running machine with its memory. | 3rd cheapest of 360 $15,761 a month | 111th of 360, with limits $6,978 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 | 69th cheapest of 364 $1,508 a month | 36th cheapest of 364 $670 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 | 107th cheapest of 377 $1,144 a month | 66th cheapest of 377 $514 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Vercel restarts a dev box every 24 hours and loses its running processes; smol machines has no session cap, but its terminal connections close after an hour. | 276th of 368, with limits $145 a month | 216th of 368, with limits $29 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 Neither streams a desktop, so on both you would build and run your own desktop stack; boat ships a 60fps desktop with computer use. | 235th of 369, with limits $952 a month | 90th of 369, with limits $156 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 Vercel Sandbox has no browser feature and smol machines only documents running your own Chromium; boat ships Chromium with browser control. | 259th of 367, with limits $486 a month | 176th 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 | 277th of 346, with limits $468 a month | 241st of 346, with limits $242 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 | 234th of 338, with limits $9,960 a month | 148th of 338, with limits $4,344 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 | 283rd of 360, with limits $554 a month | 252nd of 360, with limits $377 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 | Vercel Sandbox | smol machines | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | libkrun microVM with its own guest kernel | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new session | No provider cap; an optional lifetime you set yourself | No cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable |
| Biggest machine | 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise | 8 vCPU / 16 GB on Standard, 16 vCPU / 24 GB on Pro, 32 vCPU / 32 GB on Startup | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Stop and keep your files | Filesystem snapshot on every stop, billed per GB a month and kept 30 days after last use | Filesystem survives a stop, /tmp is emptied; stopped disk keeps billing | Disk saved every minute and on stop; a stopped sandbox costs nothing |
| Fork | Boot new sandboxes from a saved filesystem snapshot; memory is not kept | Branch a running machine with its memory and processes; checkpoints capture RAM to a file | Fork a running sandbox with its disk; the fork boots fresh |
| Wake on request | No; sessions run until their timeout or stop | A command or terminal starts a stopped machine; idle apps wake on the next request | No; a stopped sandbox is started by API |
| Docker and nested virtualization | Docker with sudo; no nested virtualization | Docker inside the VM; nested virtualization not exposed in the cloud | Docker with root and systemd, plus /dev/kvm for Android emulators and VMs |
| Shell access | SDK and CLI commands; no SSH | Command API and a WebSocket terminal capped at one hour per connection; no SSH | SSH, plus a command API and terminal |
| Inbound access | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | Up to 16 published ports through a URL or an authenticated connect route; no dedicated IP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Outbound rules | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs on Enterprise | Blocked, open, or an allowlist of hosts and CIDR ranges | Open internet, no provider-side allowlist; firewall inside the VM |
| Keeping API keys out of the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | Cloud secrets are environment variables the guest can read | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Desktop, browser, computer use | None; headless Linux only | No hosted desktop; a guide shows running your own Chromium | 60fps desktop and Chromium, computer-use and browser-control APIs |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Registry images with the Codex CLI and the Harbor eval harness, run through the command API | Seven agents preinstalled, with an API to prompt, steer and stream events |
| Where it runs | 19 regions across the US, Europe, Asia, South America, Africa and Australia | No region choice in the cloud; open-source smolvm runs on your laptop or your own servers | EU only: Germany, Finland, France, with EU data residency |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | smol machines | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | No | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | No | 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 | No | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | 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 | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | Yes | No |
| BYOC | No | Yes | No |
| Open source | No | Yes | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | No | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the StarSling hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, boat did 26.69 runs per second and Vercel Sandbox did 12.96, so boat finished about twice as many runs. smol machines has no comparable measurement: smol cloud has not been run on that test. smol publishes a boot time under 200ms for smolvm, which is a start-time figure, not CPU speed.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. smol machines 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 | Vercel Sandbox, a month | smol machines, 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 | $57 · Pro | $25 · Standard | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $236 · Pro · with limits | $93 · Standard | $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 | $2,884 · Pro | $1,139 · 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 | $828 · Pro | $465 · Startup | $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 | $3,152 · Pro | $1,389 · Startup | $2,000 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but for memory for the whole time the sandbox runs, plus a small fee per sandbox created and a monthly fee per GB of snapshots. The $20 Pro credit is shared with your other Vercel usage.
smol machines: smol cloud charges a base fee for every hour a machine runs, plus the CPU and memory the guest actually uses, with a one-minute minimum and disk billed even while stopped. Pro ($20 a month) and Startup ($150 a month) are fees on top of usage, not credit.
smol machines: boat charges a flat price per size, per second, only while the machine runs, and a stopped sandbox costs nothing. Plans start at $20 a month, and all of the fee is usage credit.
Limits in those scenarios
For one agent that never stops, Vercel ends each session at 24 hours and running processes start over, while smol machines keeps running. smol caps how many machines you hold at once by plan: 20 on Standard, 100 on Pro and 1,000 on Startup, with stopped machines still taking a slot, so 50 agents need Pro and 1,000 short jobs at once need Startup. Vercel fits that burst on Pro, though its vCPU allocation starts at 150 a minute and climbs with steady use. boat does not fit it: even the $2,000 plan allows 600 starts an hour and queues bursts above 90 starts a minute.
| Scenario | Vercel Sandbox | smol machines | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite | None that bite | None that bite |
| One agent that never stops |
| None that bite | None that bite |
| 50 agents in parallel | None that bite | None that bite | None that bite |
| Sandboxes for your users | None that bite | None that bite | None that bite |
| 1,000 short jobs at once | None that bite | None that bite |
|
Which one should you use?
Use Vercel Sandbox when
you run many short bursts of untrusted code close to users around the world, or want to boot sandboxes from your own Dockerfile.
- Regions all over the world. Useful if your users are spread out: Vercel Sandbox runs in 19 regions, from Virginia to Tokyo and Sydney.
- Keys and traffic controlled from outside. Credentials brokering keeps keys out of the guest, and a running sandbox can switch to deny-all or an allowlist.
- Images from your Dockerfile. Useful if you already have a Dockerfile: build it into an image and boot sandboxes straight into it.
Use smol machines when
you want machines with no session cap, live branches of a running machine with its memory, or one open-source VM engine from your laptop to your own servers.
- No session cap. A smol cloud machine can keep running until you stop it, so long jobs are not cut off at 24 hours.
- Live branches with memory. Useful for test fan-out: branch a running machine with its memory and processes, and wake stopped machines on the next command.
- Open source, from laptop to your own servers. Teams that want the same VM locally, in a hosted cloud and on their own servers can use one open-source engine.
Where boat fits
Both Vercel Sandbox and smol machines give you a headless microVM that you drive with commands. If your agents work for hours on one machine, building apps, running Docker or emulators and checking what they built in a browser, boat gives them a whole VM with a desktop and an API to drive the agents inside from outside. On the same CPU test, boat ran about twice as fast as Vercel Sandbox.
A whole machine with /dev/kvm and SSH
Neither Vercel Sandbox nor smol cloud exposes nested virtualization, so an agent cannot start an Android emulator or a VM inside. Neither takes SSH, so tools that expect it must be rewired to an exec API.
A desktop and a browser built in
Without a screen an agent cannot open the web app it built to see if it works. On Vercel there is no desktop at all, and on smol cloud you install, package and maintain your own Chromium and screen stream.
Agents you drive from outside
Vercel preinstalls four agents and smol has a Codex image, but on both you run them as plain commands. You write and maintain the code that prompts each agent, steers it and reads its events.
Use boat when your agents work for hours on one machine: builds, Docker, emulators, SSH and a desktop with a browser, with an API to drive the agents inside from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs smol machines.
Questions people ask
Is Vercel Sandbox cheaper than smol machines?
No, smol machines costs less in all five of our scenarios. One workday agent costs $57 a month on Vercel vs $25 on smol machines, 50 parallel agents cost $2,884 vs $1,139, and 1,000 short jobs at once cost $3,152 vs $1,389. boat costs $20, $317 and, for the burst, $2,000 while still hitting its start limits.
Which is faster, Vercel Sandbox or smol machines?
We cannot say for CPU: Vercel Sandbox did 12.96 runs per second on the StarSling Node.js test, and smol cloud has not been measured on it. boat did 26.69 on the same test. smol publishes boot times under 200ms for smolvm, which is start time, not CPU speed.
Can Vercel Sandbox or smol machines run 24/7?
smol machines can: a cloud machine runs until you stop it, and you can set your own lifetime. Vercel Sandbox sessions stop after 24 hours on Pro and Enterprise and resume from a snapshot with processes started over. boat runs with no session cap on paid plans.
Can both run Docker?
Yes. Vercel Sandbox runs Docker with sudo, and smol machines runs it inside the VM with its data on the machine's ext4 disk. Neither exposes nested virtualization on hosted machines, while boat adds /dev/kvm for Android emulators and VMs.
Can I fork a running sandbox?
smol machines branches a running machine into children that keep its memory and running processes. Vercel Sandbox boots new sandboxes from a saved filesystem snapshot, without memory. boat forks a running sandbox with its disk, and the fork boots fresh.
Can I self-host either one?
smol machines, yes: its smolvm engine is open source and runs on macOS, Linux and Windows hosts, and the same .smolmachine artifact runs locally or on your servers. Vercel Sandbox and boat are hosted services only.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs smol machines
- E2B vs Vercel Sandbox
- Daytona vs Vercel Sandbox
- Modal vs Vercel Sandbox
- Vercel Sandbox vs Cloudflare Sandbox
- Vercel Sandbox vs Blaxel
- Vercel Sandbox vs Runloop
- Vercel Sandbox vs Tensorlake
- Vercel Sandbox vs Morph Cloud
- Vercel Sandbox vs CodeSandbox SDK
- Vercel Sandbox vs Northflank