Vercel Sandbox vs exe.dev
Vercel Sandbox starts short-lived Firecracker microVMs, bills CPU only while code uses it and stops each session after 24 hours. exe.dev rents KVM VMs you reach over SSH that run until you stop them, mostly from a pool you pay for each month.
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.
exe.dev
exe.dev, made by Bold Software, Inc., rents Linux VMs for developers and AI agents that you reach over SSH and HTTPS.
You reserve a pool of vCPUs and memory, and your VMs share it; you can also start standalone VMs billed by the second. Each VM is KVM-isolated (they use Cloud Hypervisor), boots from a container image in about two seconds, and has root, systemd and Docker. It comes with Claude Code, Codex, Pi and exe.dev's own Shelley agent, and is aimed at developers who want a persistent dev box or a sandbox for their agents.
- Company
- Bold Software, Inc.
- Preinstalled agents
- claude, codex, pi and the Shelley web agent
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 | exe.dev: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both are a compromise for a software factory: no desktop to check the UI on either, plus a 24-hour cap on Vercel and no snapshots on exe.dev. | 244th of 367, with limits $3,351 a month | 253rd of 367, with limits $3,701 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB exe.dev ranks 15th for always-on assistants because its VMs never time out; Vercel Sandbox ranks 257th since each session stops after 24 hours. | 257th of 366, with limits $3,657 a month | 15th cheapest of 366 $3,833 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 Vercel Sandbox ranks 22nd for code interpreter bursts because it bills CPU only while code runs; exe.dev ranks 235th, since its pools bill whether busy or idle. | 22nd cheapest of 345 $216 a month | 235th of 345, with limits $175 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 Vercel Sandbox ranks 15th for sandboxes you hand to your users, exe.dev ranks 257th because of its 50-VM cap, and boat ranks 1st. | 15th cheapest of 361 $1,267 a month | 257th of 361, with limits $1,226 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 for RL rollouts thanks to high concurrency and fast starts; exe.dev's Personal plan stops at 50 VMs at once. | 3rd cheapest of 360 $15,761 a month | 265th of 360, with limits $5,250 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 | 283rd of 364, with limits $1,050 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 Vercel Sandbox fits CI runners at rank 107 and exe.dev is a compromise at 288; boat ranks 4th with per-second billing and Docker. | 107th cheapest of 377 $1,144 a month | 288th of 377, with limits $504 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB exe.dev ranks 25th as a 24/7 dev box with SSH and a lasting disk; Vercel Sandbox ranks 276th because it restarts every day. | 276th of 368, with limits $145 a month | 25th cheapest of 368 $35 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 has a desktop, so computer-use agents are a compromise on both; boat ranks 6th with a 60fps desktop and a computer-use API. | 235th of 369, with limits $952 a month | 240th of 369, with limits $1,055 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 | 259th of 367, with limits $486 a month | 130th of 367, with limits $530 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 | 124th of 346, with limits $278 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 | 166th of 338, with limits $5,490 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 | 60th of 360, with limits $263 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 | exe.dev | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | KVM VM with Cloud Hypervisor; you can't choose the 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 cap; VMs run until you stop them | No cap on paid plans; you set the TTL |
| Saved state | Filesystem snapshot on stop, kept 30 days after last use and billed per GB a month | Disk persists and is streamed to a second server; no snapshots | Snapshot every minute while running and on stop; a stopped sandbox costs nothing |
| How you get in | JavaScript and Python SDKs and a CLI; no SSH | SSH, an HTTPS proxy and a CLI | SSH, SDKs for TypeScript and Python, and an API |
| Billing | CPU only while code uses it, memory for the whole session, plus a fee per sandbox created | Reserved pool billed flat whether busy or idle; standalone VMs per second | Flat price per size, per second, only while the machine runs |
| Machines at once | Up to 10,000 on Pro, 10 on Hobby | 50 VMs in the Personal pool, plus up to 50 standalone VMs | 100 to 2,000 by plan, with limits on starts per hour and per day |
| Desktop and computer use | None; headless Linux only | None; headless VMs | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Docker inside | Yes, with sudo | Yes, with root and systemd | Yes, with root and systemd |
| Nested virtualization | No | Enterprise only | Yes, /dev/kvm on every plan |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Boot from your own Docker image | Named snapshots as templates, shareable by code; no Dockerfile builds |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Claude Code, Codex, Pi and Shelley; only Shelley takes prompts through the API | Seven agents, with one API to prompt, steer and stream events from outside |
| Inbound traffic | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | HTTPS proxy for ports 3000 to 9999, one of them public; no public IP or raw TCP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| Egress rules | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running | No provider-side allowlist | No provider-side allowlist; firewall inside the VM |
| Regions | 19 regions across the US, Europe, Asia, South America, Africa and Australia | 9 regions in the US, Europe, Asia and Australia | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | exe.dev | 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 | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | Yes | 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 | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | No | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Yes | Not published | 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 | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the 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. exe.dev is not in that benchmark, so there is no comparable CPU score for it, and we don't guess one.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. exe.dev 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 | exe.dev, 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 | $35 · Personal | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $236 · Pro · with limits | $35 · Personal | $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 | $1,848 · Personal | $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 | $530 · Personal · with limits | $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 | $1,050 · Personal · with limits | $2,000 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but for memory the whole time a 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.
exe.dev: exe.dev's Personal plan is a flat monthly pool your VMs share, from $15 for 2 vCPU / 4 GB, billed the same whether VMs are busy or idle. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour.
exe.dev: 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 Sandbox ends each session at 24 hours and running processes start over, while exe.dev and boat keep going. For 300 sandboxes at once for your users, or 1,000 short jobs at once, exe.dev's Personal plan does not fit because it stops at 50 VMs at once; Vercel fits both. boat fits the 300 user sandboxes, but even its top plan queues a burst of 1,000 starts.
| Scenario | Vercel Sandbox | exe.dev | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops |
|
| 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 |
| 1,000 short jobs at once | None that bite |
|
|
Which one should you use?
Use Vercel Sandbox when
you run many short bursts of untrusted code, need thousands of sandboxes at once, or want egress rules you set from outside.
- Pay only for busy CPU. Useful for short bursts of code: Vercel bills CPU only while your code uses it, so idle waits cost less.
- Huge bursts of sandboxes. Pro allows up to 10,000 sandboxes at once, so many short jobs or rollouts can run side by side.
- A firewall you control from outside. A running sandbox can be switched to deny-all, or to a list of allowed domains, without a restart.
Use exe.dev when
you want a few long-lived Linux VMs over SSH for dev boxes or always-on assistants, on one flat monthly bill.
- VMs that never time out. Useful for dev boxes and always-on assistants: an exe.dev VM runs until you stop it, with no session cap.
- A plain SSH box. You reach each VM over SSH with root, systemd and Docker, like a normal Linux server.
- One flat bill for a small team. A Personal pool is one fixed monthly fee that several VMs share, so the bill never surprises you.
Where boat fits
Vercel Sandbox is built for short runs and exe.dev for long-lived SSH boxes. If your agents work for hours on one machine and need a screen, saved state and an API to drive them, boat gives you all of that on one full VM.
A screen your agents can use
Neither Vercel Sandbox nor exe.dev has a desktop, so an agent cannot open the app it built to check it. On both you would set up and stream a desktop yourself; boat ships a 60fps desktop with Chromium.
Long runs with state saved every minute
Vercel stops each session at 24 hours and running processes start over. exe.dev runs forever but has no snapshots, so one bad agent step can wreck the disk. boat has no cap on paid plans and snapshots every minute.
Drive agents inside from outside
On Vercel you start Claude Code or Codex as plain commands, and on exe.dev only Shelley takes prompts through the API. boat gives you one API to prompt, steer and stream events from seven agents.
Use boat when your agents work for hours on one machine: builds, tests, Docker, emulators and a desktop with a browser, with state saved every minute and one API to drive agents inside from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs exe.dev.
Questions people ask
Is Vercel Sandbox cheaper than exe.dev?
For long runs exe.dev costs less: one workday agent is $35 a month on exe.dev vs $57 on Vercel, and 50 parallel agents are $1,848 vs $2,884. For 300 user sandboxes or 1,000 jobs at once, exe.dev's bill is lower but its Personal plan does not fit, while Vercel does. boat costs $20 and $317 for those first two.
Which is faster, Vercel Sandbox or exe.dev?
We can't say, because exe.dev is not in the hpc-sandbox-benchmarks run. Vercel Sandbox scored 12.96 runs per second at 4 vCPU / 8 GB, and boat scored 26.69 on the same test.
Can Vercel Sandbox run 24/7 like exe.dev?
Not as one session. Vercel sessions last up to 24 hours on Pro, then stop; the sandbox can resume from its snapshot, but processes and memory start fresh. exe.dev VMs run until you stop them, and so do boat machines on paid plans.
Can both run Docker?
Yes. Vercel Sandbox runs Docker with sudo, and exe.dev runs it with root and systemd. Both can also boot from your own container image; boat runs Docker with root and systemd too, and adds /dev/kvm for emulators and VMs.
Do Vercel Sandbox or exe.dev have a desktop for computer use?
No. Both are headless Linux that you drive with commands, files and ports. boat gives every sandbox a 60fps desktop with Chromium and APIs for computer use and browser control.
Where do they run?
Vercel Sandbox runs in 19 regions, with iad1 in the US as the default. exe.dev has nine regions in the US, Europe, Asia and Australia. boat runs only in the EU, in Germany, Finland and France.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs exe.dev
- 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