Cloudflare Sandbox vs Sprites

Both run each sandbox in its own Firecracker microVM, and both sleep when idle. Cloudflare Sandbox is a container you build and drive from a Worker. Its disk starts fresh after sleep unless your code saves a snapshot or uses an R2 mount. A Sprite is a fixed 8 vCPU Linux computer from Fly.io that keeps its 100 GB disk and wakes with its processes still in memory.

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. 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. The disk resets when the container stops, and your code keeps files with snapshots, automatic saves, R2 backups or R2 bucket mounts. It suits teams already on Workers who want sandboxes that sleep when idle. For code that only calls known methods, Cloudflare also offers Dynamic Workers, which run JavaScript in V8 isolates.

Sprites

Sprites is Fly.io's product for agents: persistent Linux computers you create by API or CLI, which sleep when idle and wake on the next request.

Each Sprite is a Firecracker microVM with 8 vCPU, memory that scales from 2 GB to 16 GB as needed, and a 100 GB ext4 disk backed by object storage. It runs one managed Ubuntu image with Claude Code, Codex, Gemini CLI and Cursor preinstalled. It gets an HTTPS URL that wakes it, and it bills only for the CPU and memory it uses while awake. It is built for coding agents, dev environments and user code that sit idle most of the time.

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. “43rd cheapest of 361” means 42 of the other 360 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 workloadCloudflare Sandbox: price rankSprites: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Sprites keeps a long session's files on a 100 GB disk with no code. On Cloudflare your code saves snapshots, automatic saves or R2, and the disk is 20 GB at most. boat saves the disk with no code and adds systemd, /dev/kvm and a desktop.
192nd of 365, with limits
$1,543 a month
101st of 365, with limits
$546 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An always-on assistant needs its files and open connections to stay put. On Cloudflare your code keeps files with snapshots or R2. A Sprite drops open connections on each pause, and a Tasks API hold keeps it awake up to an hour at a time. boat keeps the machine running once auto-stop is off (default 1 hour).
43rd cheapest of 361
$2,188 a month
214th of 361, with limits
$1,166 a month
6th cheapest of 361
$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-interpreter calls. Cloudflare bills CPU only while busy, wakes on the next request and runs your own image. Sprites bills used CPU and memory and wakes in under a second.
17th cheapest of 336
$144 a month
99th of 336, with limits
$140 a month
189th of 336, 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
Cloudflare fits sandboxes for your users, with egress rules written as Worker code. Sprites does not publish how many machines can run at once on pay as you go, so 300 at once is not confirmed.
19th cheapest of 349
$731 a month
61st of 349, with limits
$428 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
147th of 349, with limits
$9,428 a month
114th of 349, with limits
$6,540 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
60th cheapest of 359
$818 a month
130th of 359, with limits
$545 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Sprites fits CI with a 100 GB disk, against 20 GB at most on Cloudflare. boat adds Docker with systemd and /dev/kvm for Android and VM builds.
303rd of 374, with limits
$704 a month
63rd cheapest of 374
$476 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A dev box should keep its files. Sprites does and wakes in under a second. Cloudflare starts a fresh disk after sleep unless your code restores a snapshot (beta, 30 days) or mounts an R2 bucket. boat adds SSH and systemd.
123rd cheapest of 371
$93 a month
120th cheapest of 371
$27 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Neither Cloudflare nor Sprites ships a built-in desktop. On Cloudflare you build one into your image, or use the separate Browser Run service; on a Sprite you install a display server, a browser and a stream. boat streams a 60 fps desktop with Chrome.
207th of 367, with limits
$460 a month
132nd of 367, with limits
$136 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
68th of 356, with limits
$233 a month
236th of 356, with limits
$122 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
102nd cheapest of 343
$286 a month
279th of 343, with limits
$206 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
168th of 327, with limits
$5,741 a month
139th of 327, with limits
$4,113 a month
73rd of 327, 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 need raw TCP and full root networking. Cloudflare takes no raw TCP inbound, and Sprites reaches other ports only through the sprite proxy CLI. boat has raw ports over public IPv6 and /dev/kvm.
25th cheapest of 351
$325 a month
243rd of 351, with limits
$223 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureCloudflare SandboxSpritesboat
IsolationFirecracker microVM per container, own kernel and networkFirecracker microVM per Sprite, own kernelFull VM with its own kernel, on a physical host dedicated to boat (AMD Ryzen 7 9700X or Ryzen 9 9950X); vCPUs are shared
Machine sizeInstance types up to 4 vCPU / 12 GiB / 20 GB disk; no 4 vCPU / 8 GB sizeFixed 8 vCPU and 100 GB disk; memory scales from 2 GB to 16 GB as neededYou choose 2 to 16 vCPU and 4 to 32 GB (16 vCPU needs the $100 plan or higher); disk fixed per size, 51 to 251 GB
ImageYour own linux/amd64 container imageOne managed Ubuntu 25.10 image; you install on top and save a checkpointboat's Ubuntu 24.04 image or a saved snapshot; you install what you need
Files between sessionsDisk is fresh after sleep; keep files with snapshots (public beta, 30 days), scheduled automatic saves, R2 directory backups or a mounted R2 bucket100 GB disk kept with no code; checkpoints restore in placeDisk saved every minute and at each stop, with no code; kept at least 14 days after a stop, longer as a saved snapshot
Idle behaviorStops after an inactivity timeout and wakes on the next requestPauses about 30 seconds after activity stops; wakes in 100 to 500 ms with memory, or 1 to 2 s after a cold stopRuns until auto-stop (1 h by default, up to 30 days, or off on paid plans); no idle timer, full rate while running
Fork a running sandboxSnapshot or back up a running sandbox, then start new sandboxes from it; no one-call forkNo fork command in the CLI or API docs; checkpoints restore in placeOne call, without stopping it; the fork uses the last 1-minute snapshot
Docker insidedocker:dind with iptables and IP forwarding turned offDocker runs (a user reports docker exec fails for containers that do not run as root); services run through the Sprites services API, not systemdDocker with BuildKit and Compose, root and systemd
Nested virtualizationNot documentedNot documentedYes, /dev/kvm for Android emulators and VMs
Desktop and browserBuilt-in desktop removed in SDK 0.10.2; build one into your own image, or use the separate Browser Run service for headless browsersNo desktop or browser built in; you install a browser, display server and stream yourself1920x1080, 60 fps desktop and Chrome, computer tools, embeddable stream; no GPU
Inbound trafficHTTP and WebSocket previews routed through your Worker; SSH; no raw TCP inbound or public IPOne HTTPS URL to one HTTP port, private by default; other ports and SSH through the sprite proxy CLIUp to 50 HTTPS URLs, token-gated by default; SSH; raw ports over public IPv6; the IP changes at each resume
Egress controlallowedHosts deny-by-default list plus outbound handlers you write in Worker codeOptional DNS-based domain allowlist set from outside; private IPs always blockedOpen internet, no provider-side allowlist; filter inside the VM with root
Keeping keys out of the sandboxYour outbound handler adds the token for any HTTP or HTTPS host; you write the codeConnectors gateway holds the token for GitHub, OpenRouter, Slack or any HTTP API, with path allow and block listsOptional paid proxy ($1 a day while on, plus $1 per 1,000 requests) for model providers and HTTPS APIs you register
Coding agentsGuides for Claude Code, Codex, OpenCode and Pi in your imageClaude Code, Codex, Gemini CLI and Cursor preinstalled, run through exec or a consoleSeven installed, with a prompt, steer and events API to drive them from outside
RegionsSeveral regions across Cloudflare's network; pin to a region or jurisdictionNo region option when you create a SpriteGermany, Finland and France; no US or Asia region; you cannot pick one
Every feature Battleships tracks (43)
FeatureCloudflare SandboxSpritesboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNo documented wayNo documented wayYes
RootYesYesYes
SystemdNot publishedNo documented wayYes
Desktop GUINo documented wayNo documented wayYes
BrowserWith your own setupNo documented wayYes
Computer-use APINo documented wayNo documented wayYes
SSHYesWith your own setupYes
Persistent diskWith your own setupYesYes
Pause/resumeNo documented wayYesYes
Automatic snapshotsWith your own setupYesYes
Fork/cloneWith your own setupNo documented wayYes
Live fork (no pause)With your own setupNo documented wayYes
Memory forkNo documented wayNo documented wayNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo documented way
Wake on requestYesYesNo documented way
HTTPS preview URLsYesYesYes
Raw TCP inboundNo documented wayNo documented wayYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistYesYesNo documented way
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APIWith your own setupNo documented wayYes
MCP serverNo documented wayYesNo documented way
GPUNo documented wayNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingNo documented wayNo documented wayNo documented way
BYOCNo documented wayNo documented wayNo documented way
Open sourceYesNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsNo documented wayNot publishedYes
Usage per sandbox (API)Not publishedNo documented wayYes
Audit logsYesNot publishedNo documented way
SSOYesYesNo documented way
SOC 2YesYesNo documented way
HIPAAYesYesNo documented way
EU data residencyYesNo documented wayNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

Cloudflare SandboxNot measured
SpritesNot measured
boat28.06 runs/s

Neither Cloudflare Sandbox nor Sprites is in StarSling's run of 3 October 2026 (run 37073680030), so we cannot say which is faster. In that run boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. A Sprite always has 8 vCPU, so a fair test would also need a matching shape.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Cloudflare Sandbox and Sprites are not in the public benchmarks we use, so we cannot say which is faster.

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. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioCloudflare Sandbox, a monthSprites, a monthboat, 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$23 · Pay-as-you-go$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$148 · Workers Paid$92 · Pay-as-you-go$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$1,120 · Pay-as-you-go$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$314 · Pay-as-you-go · 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$1,134 · Pay-as-you-go · with limits$8,800 · $2000/mo · with limits

Cloudflare Sandbox: You need Workers Paid ($5 a month minimum). CPU is billed only while busy, at $0.072 per vCPU-hour. Memory and disk are billed on the instance size in 10 ms steps until the container sleeps. 4 vCPU always comes with 12 GiB. Durable Object and Worker requests are billed on top. Snapshot pricing is not published.

Sprites: Sprites bills CPU time at $0.0385 per CPU-hour and actual memory at $0.021875 per GB-hour, only while the Sprite is awake. Storage costs about $0.50 per GB-month for hot data and about $0.02 per GB-month for cold data. Pay as you go has no plan fee; optional plans buy fixed CPU-hour, memory-hour and storage allowances, not credit.

Sprites: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A default 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. The $20 plan includes 12 starts a minute, 60 an hour and 200 a day; extra starts cost $0.03 to $0.07. A stopped sandbox has no compute charge and keeps its disk at least 14 days. Saved snapshots above the included count ($0.056 a day each) and the AI proxy, if on, still bill while stopped.

Limits in those scenarios

Cloudflare keeps 50 GB of files between days only through snapshot, automatic-save or R2 code, and its local disk tops out at 20 GB. An account runs 1,500 vCPU at once by default, short of the 2,000 the 1,000-job burst needs, raised on request. Sprites does not publish how many Sprites can run at once on pay as you go, so 300 user sandboxes and 1,000 jobs at once are not confirmed, and creation is 10 a minute without a plan. boat does not fit the burst either: the $2,000 plan includes 90 starts a minute and 600 an hour, charges $0.03 to $0.07 for extra starts, and refuses starts above 270 a minute.

ScenarioCloudflare SandboxSpritesboat
One coding agent, workdaysNone for this scenarioNone for this scenarioNone for this scenario
One agent that never stopsNone for this scenarioNone for this scenarioNone for this scenario
50 agents in parallelNone for this scenario
  • how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
None for this scenario
Sandboxes for your usersNone for this scenario
  • not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)
None for this scenario
1,000 short jobs at once
  • Workers Paid: max 1,500 vCPU running at once (needs 2,000)
  • not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use Cloudflare Sandbox when

your app already runs on Workers, you want your own container image, and your sandboxes are short sessions that sleep when idle.

  • Your own image and size. Teams that need a custom toolchain can ship their own container image and pick a smaller or larger instance type per container class.
  • Egress rules you can program. Cloudflare can block every host except the ones you list, and run your own Worker 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 a region you can pick.

Use Sprites when

your agents or apps sit idle most of the day, should keep their files with no code, and should wake on a request in under a second.

  • A disk that stays. Each Sprite keeps a 100 GB disk across sleeps with no code, so an agent finds its repo and packages where it left them.
  • Wakes fast with memory intact. A Sprite pauses when idle and wakes in 100 to 500 ms with its processes still in memory, billing only real CPU and memory use.
  • Agents and platforms ready. Claude Code, Codex, Gemini CLI and Cursor come preinstalled, and Sprites can back Claude Managed Agents and Cursor Cloud Agents.

Where boat fits

Cloudflare Sandbox and Sprites are both built around machines that sleep when nobody uses them. If your agents work for hours on builds, tests, Docker, emulators or a browser, boat gives each one a full VM that keeps running, saves its disk with no code, and can be driven from outside. boat runs only in the EU, has no GPU and limits starts per plan.

Files that stay, and forks

On Cloudflare your code saves snapshots (kept 30 days), automatic saves or R2. Sprites keeps the disk, and its checkpoints restore in place. boat saves the disk every minute and forks a running sandbox in one call, to try two fixes from one state. A boat resume is like a reboot: memory is not saved.

A fuller machine

Cloudflare tops out at 4 vCPU and 20 GB of disk, with iptables off. Sprites is a fixed 8 vCPU machine that runs services through its own API, not systemd. Neither documents /dev/kvm or ships a desktop. boat has systemd, Docker, /dev/kvm and a 60 fps desktop.

Reach it and drive it from outside

Cloudflare routes traffic through your Worker with no raw TCP inbound, and Sprites has one public HTTP port with other ports through its proxy CLI. boat gives up to 50 HTTPS URLs, raw ports over public IPv6, SSH and an API to prompt and steer agents inside.

Use boat when your agents need a full machine for hours: systemd, Docker, emulators, many ports, a desktop and browser, forks, and an API to drive the agents inside from outside. Compare it one to one: boat vs Cloudflare Sandbox and boat vs Sprites.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is Cloudflare Sandbox cheaper than Sprites?

In all five scenarios we priced, Sprites comes out lower. One agent that never stops is $92 a month on Sprites against $148 on Cloudflare, and 50 agents in parallel are $1,120 against $1,660. boat comes to $26 and $317 for those two, but $8,800 for 1,000 short jobs at once, because it bills extra starts. Sprites and Cloudflare bill used CPU, so a mostly idle workload can cost less than these estimates.

Which is faster, Cloudflare Sandbox or Sprites?

We cannot say. Neither is in StarSling's run of 3 October 2026. A Sprite always has 8 vCPU, while Cloudflare's largest instance has 4. boat did 28.06 V8 Web Tooling runs/s in that run at 4 vCPU / 8 GB, on an AMD Ryzen 9 9950X host; boat also places some sandboxes on other hosts.

Do they keep my files?

Yes. Each Sprite keeps a 100 GB disk across sleeps with no code. Cloudflare keeps files with a snapshot (public beta, 30 days), scheduled automatic saves, an R2 backup or a mounted R2 bucket. boat saves the disk every minute and at each stop with no code, and keeps it at least 14 days after a stop.

Can Cloudflare Sandbox or Sprites run Docker?

Both can, with limits. Cloudflare supports docker:dind with iptables and IP forwarding turned off. On Sprites a user reports docker exec fails for containers that do not run as root. boat runs Docker with BuildKit and Compose and systemd.

Can I SSH into them?

On Sprites you install an SSH server and tunnel it through the sprite proxy CLI. Cloudflare documents SSH to containers, and routes other traffic through your Worker with no raw TCP inbound or public IP. boat sandboxes have SSH through a shared IPv4 host and port, and raw ports over public IPv6; the IP changes at each resume.

Where do they run?

Cloudflare places containers in several regions of its network and lets you pin a region or jurisdiction. Sprites has no region option. boat runs on machines in Germany, Finland and France, and you cannot pick a region.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons