Cloudflare Sandbox vs exe.dev
Cloudflare Sandbox gives you a container inside the Workers platform that sleeps when idle, wakes on the next request and starts from a fresh disk. exe.dev gives you a Linux VM that keeps its disk and runs until you stop it, billed mostly as a reserved pool.
The companies and products
Cloudflare Sandbox
Cloudflare Sandbox SDK runs untrusted or AI-generated code in Linux containers on Cloudflare's network, driven from a Cloudflare Worker.
Each sandbox is a Cloudflare Container backed by a Durable Object, and each container runs in its own Firecracker microVM with its own kernel and network. You build a linux/amd64 image, pick an instance type of up to 4 vCPU and 12 GiB, and reach the sandbox through your own Worker. It suits teams already on Workers who want short-lived sandboxes that sleep when idle; for code that only calls known methods, Cloudflare also offers Dynamic Workers, which run JavaScript in V8 isolates.
- Largest instance
- 4 vCPU, 12 GiB memory, 20 GB disk (defaults, can be raised)
- Account limits
- 1,500 vCPU, 6 TiB memory and 30 TB disk running at once
- Compliance
- Cloudflare holds a SOC 2 Type II report
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. “13th cheapest of 345” means 12 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 | Cloudflare 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 A software factory needs big disks, full Docker and a screen for checking UIs; Cloudflare caps disk at 20 GB by default, exe.dev is headless, and boat has both. | 162nd of 367, with limits $1,543 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 Always-on assistants need files that stay put; exe.dev and boat keep the disk, while Cloudflare wipes it when the container sleeps. | 207th of 366, with limits $2,188 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 For many short code-interpreter calls Cloudflare fits best of the three: it wakes on the next request and bills CPU only while busy, while exe.dev pools bill whether used or not. | 13th cheapest of 345 $144 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 For sandboxes you hand to your users, Cloudflare fits and exe.dev's Personal plan stops at 50 VMs at once; boat fits too, with per-sandbox usage and spend limits. | 9th cheapest of 361 $731 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 | 144th of 360, with limits $9,428 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 | 45th cheapest of 364 $818 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 CI that builds Docker images needs room and full Docker; Cloudflare limits both and exe.dev pools bill idle time, while boat bills per second while running. | 301st of 377, with limits $704 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 A dev box should keep its files when you log off; exe.dev and boat both do, and Cloudflare starts from a fresh disk after sleep. | 70th cheapest of 368 $93 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 Computer-use agents need a screen; neither Cloudflare nor exe.dev ships a desktop, while boat streams a 60fps desktop. | 166th of 369, with limits $460 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 | 210th of 367, with limits $233 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 | 250th of 346, with limits $286 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 | 169th of 338, with limits $5,741 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 Red-team runs often want raw networking; Cloudflare containers cannot change iptables, exe.dev has no raw TCP inbound, and boat gives raw TCP and /dev/kvm. | 239th of 360, with limits $325 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 | Cloudflare Sandbox | exe.dev | boat |
|---|---|---|---|
| Isolation | Firecracker microVM per container, own kernel and network | KVM VM with Cloud Hypervisor; you can't choose the kernel | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Files between sessions | Fresh disk after sleep; snapshots (public beta, 30 days) or R2 backups when your code saves them | Disk persists and is streamed to a second server; no snapshots | Disk kept; snapshot every minute and on stop; a stopped sandbox costs nothing |
| Largest machine | 4 vCPU / 12 GiB / 20 GB disk by default (can be raised) | Pools up to 16 vCPU on Personal; larger on Work with approval | Up to 16 vCPU / 32 GB, depending on plan |
| Fork | No fork; restore a saved snapshot or backup into a new sandbox | cp copies a VM's disk and config into a new VM | Fork a running sandbox without stopping it; named snapshots as templates |
| Docker inside | docker:dind with iptables and IP forwarding turned off | Docker with root and systemd | Full Docker, root and systemd |
| Nested virtualization | Not documented | Enterprise only | Yes, /dev/kvm on every plan |
| Desktop and computer use | Built-in desktop removed in SDK 0.10.2; bring your own | Headless; no desktop or screen streaming | 60fps desktop and Chromium, computer-use API, embeddable stream |
| Inbound traffic | HTTP and WebSocket previews routed through your Worker; no raw TCP or public IP | HTTPS proxy for ports 3000 to 9999, one of them public; SSH; no public IP or raw TCP | HTTPS URLs for up to 50 ports, token-protected; raw TCP; own IPv6 or IPv4 |
| Egress control | allowedHosts deny-by-default list plus outbound handlers you write in Worker code | No provider-side allowlist | No provider-side allowlist |
| Keeping keys out of the sandbox | Your outbound handler adds the token for any HTTP or HTTPS host; you write the code | Integrations inject secrets at the network edge for any HTTP host, S3, GitHub and more | Managed proxy for model providers and any HTTPS API you register; switch a credential to another account |
| Coding agents | Run Claude Code, Codex, OpenCode or Pi in your image; OpenCode has an SDK helper | Claude Code, Codex, Pi and Shelley preinstalled; only Shelley takes prompts through the API | Claude Code, Codex, pi, OpenCode and more built in, with a prompt, steer and events API |
| Custom images | Your own linux/amd64 container image | Boot from your own Docker image | Templates from named snapshots; no Dockerfile or OCI images |
| Idle behavior | Stops after inactivity and wakes on the next request | Runs until you stop it; pools bill whether busy or idle | TTL based (1 h default, changeable); a stopped sandbox costs nothing |
| Regions | Several regions across Cloudflare's network | 9 regions in the US, Europe, Asia and Australia | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Cloudflare 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 | Yes | Yes | Yes |
| Persistent disk | No | Yes | Yes |
| Pause/resume | No | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | No | Yes | Yes |
| Live fork (no pause) | No | Yes | Yes |
| Memory fork | No | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | 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 | Yes | Yes | Yes |
| MCP server | No | 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 | Yes | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | No | Not published | Yes |
| Usage per sandbox (API) | Not published | Yes | Yes |
| Audit logs | Yes | 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
boat scores 26.69 runs/s on the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB. Neither Cloudflare Sandbox nor exe.dev has a result on that benchmark, so there is no comparable CPU number for them, and we don't guess.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Cloudflare Sandbox and exe.dev have 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 | Cloudflare 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 | $39 · Workers Paid · with limits | $35 · Personal | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $148 · Workers Paid · 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 | $1,660 · Workers Paid · with limits | $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 | $476 · Workers Paid | $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 | $1,889 · Workers Paid · with limits | $1,050 · Personal · with limits | $2,000 · $2000/mo · with limits |
Cloudflare Sandbox: You need Workers Paid ($5 a month minimum). CPU is billed only while busy; memory and disk are billed on the instance size, in 10 ms steps, until the container sleeps, and 4 vCPU always comes with 12 GiB.
exe.dev: Pools are reserved capacity your VMs share and bill the same whether busy or idle; the Personal 4 vCPU / 8 GiB pool is $35 a month. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour.
exe.dev: Your monthly plan fee, from $20, is all usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Cloudflare's disk resets after sleep and tops out at 20 GB by default, so the scenarios that keep 50 GB of files between days do not fit without your own snapshot or backup code, and an account runs 1,500 vCPU at once by default, short of the 1,000-job burst. exe.dev Personal stops at 50 VMs at once, so the 300-at-once and 1,000-at-once scenarios do not fit there. boat hits start-rate limits on that burst: the top plan allows 600 starts an hour and queues bursts above 90 starts a minute.
| Scenario | Cloudflare Sandbox | exe.dev | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
| None that bite | None that bite |
| Sandboxes for your users | None that bite |
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Cloudflare Sandbox when
your app already runs on Workers and you want short sandboxes that sleep when idle, wake on the next request and follow egress rules you write.
- Sleeps when idle, wakes on request. Useful for many short, spiky sessions: a sandbox sleeps when idle, wakes on the next request, and bills CPU only while busy.
- Egress rules you can program. Cloudflare can block every host except the ones you list, and run your own code on each outbound request.
- Next to the rest of Workers. If your app already runs on Workers, sandboxes sit next to Durable Objects and R2, in several regions.
Use exe.dev when
you want a VM that keeps its disk and runs until you stop it, in a region outside Europe or booted from your own Docker image.
- A VM that keeps running. Useful for a dev box or a long agent: each VM keeps its disk and runs until you stop it.
- Regions around the world. Useful if your users are far from Europe: exe.dev runs in nine regions across the US, Europe, Asia and Australia.
- Team controls and an MCP server. Its Work plan covers a whole team with SSO and roles, and it serves an MCP server for controlling VMs.
Where boat fits
Cloudflare suits short sandboxes that sleep, and exe.dev suits VMs that stay up. If your agents work for hours on builds, Docker, emulators and UIs, boat gives them a full VM that keeps its files like exe.dev, adds a desktop and saved state neither one has, and stops at no cost.
State saved every minute
On Cloudflare a sleeping sandbox wakes with an empty disk unless your code saves a snapshot or backup. exe.dev keeps the disk but has no snapshots, so one bad agent step can cost a session's work. boat snapshots every minute and forks running sandboxes.
A screen and a full machine
Neither ships a desktop, so computer-use agents have nothing to look at until you build one. Cloudflare also runs Docker with iptables off, and exe.dev keeps /dev/kvm for Enterprise. boat has a 60fps desktop, full Docker and /dev/kvm on every plan.
Agents driven from outside
On Cloudflare you bake each agent into your image and write the outbound code that adds every token. On exe.dev only Shelley takes prompts by API. boat lets you prompt, steer and stream built-in agents, with keys kept outside.
Use boat when your agents do real work for hours: builds, tests, full Docker, emulators and a desktop, with state saved every minute and one API to drive agents inside from outside. Compare it one to one: boat vs Cloudflare Sandbox and boat vs exe.dev.
Questions people ask
Is Cloudflare Sandbox cheaper than exe.dev?
It depends on the shape. For one agent that never stops, exe.dev's flat pool is $35 against $148 on Cloudflare, and Cloudflare does not keep the disk. For 30,000 ten-minute user sandboxes Cloudflare is $476 and fits, while exe.dev Personal is $530 and stops at 50 at once. boat is lower than both in four of the five scenarios.
Which is faster?
We can't say: neither Cloudflare Sandbox nor exe.dev has a result on the hpc-sandbox-benchmarks run. boat scores 26.69 runs/s there at 4 vCPU / 8 GB.
Does Cloudflare Sandbox keep my files like exe.dev?
No. A Cloudflare sandbox starts from a fresh disk after it sleeps, unless your code saved a snapshot (public beta, kept 30 days) or a backup to R2. exe.dev keeps each VM's disk until you delete it, and boat keeps the disk and snapshots it every minute.
Can Cloudflare Sandbox and exe.dev run Docker?
Yes, both. Cloudflare supports docker:dind with iptables and IP forwarding turned off, because containers cannot change iptables. exe.dev VMs run Docker with root and systemd, and boat runs full Docker too.
Do either of them have a desktop for computer use?
No. Cloudflare removed its built-in desktop in SDK 0.10.2, and exe.dev VMs are headless. boat gives every sandbox a 60fps desktop with Chromium and a computer-use API.
Where do they run?
Cloudflare places containers in several regions of its network, and 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 Cloudflare Sandbox
- boat vs exe.dev
- E2B vs Cloudflare Sandbox
- Daytona vs Cloudflare Sandbox
- Modal vs Cloudflare Sandbox
- Vercel Sandbox vs Cloudflare Sandbox
- Cloudflare Sandbox vs Blaxel
- Cloudflare Sandbox vs Runloop
- Cloudflare Sandbox vs Tensorlake
- Cloudflare Sandbox vs Morph Cloud
- Cloudflare Sandbox vs CodeSandbox SDK
- Cloudflare Sandbox vs Northflank