Vercel Sandbox vs Azure Container Apps Sandboxes
Both run each sandbox as a microVM with its own kernel, and neither has a built-in desktop. Vercel Sandbox stops each session after 24 hours, resumes from a snapshot, and bills CPU only while code uses it. Azure documents no session cap and can suspend a sandbox with its memory, then wake it on traffic, inside your Azure account.
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, fork sandboxes, mount Drives and set network rules. Sandboxes are persistent by default: each stop saves the filesystem, and the next session resumes from it. Vercel aims it at code interpreters, app builders, test runs, developer environments and agent workspaces. Its docs suggest a VM for 24/7 hosting.
- Default image
- Ubuntu; the universal image adds Node.js 24, Python 3.14, Bun, and Claude Code, Codex, OpenCode and pi preinstalled
- Longest session
- 24 hours on Pro and Enterprise, 45 minutes on Hobby; a persistent sandbox resumes from its last snapshot with no cap on total lifetime
- Biggest sandbox
- 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise
Azure Container Apps Sandboxes
Azure Container Apps Sandboxes is a service inside Microsoft Azure that gives each agent or user an isolated microVM you create, suspend and resume through an SDK.
It is part of Azure Container Apps, the hyperscaler's serverless container platform, and lives in your Azure subscription as a sandbox group resource. Each sandbox boots from an OCI image or a snapshot and has its own kernel. A stop keeps the disk, or the disk and the memory, and a memory-mode sandbox resumes in under a second. It is built for teams already on Azure that want stateful code execution with Azure networking, identity and billing.
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. “27th cheapest of 336” means 26 of the other 335 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 | Azure Container Apps Sandboxes: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Azure fits at $5,276 a month with the azure-dev image for Docker and your own desktop image. Vercel is listed with limits ($3,351): no built-in desktop and no /dev/kvm. boat fits at $634. | 259th of 365, with limits $3,351 a month | 33rd cheapest of 365 $5,276 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Azure is a full match at $6,780 a month with no session cap. Vercel is listed with limits ($3,657) because each session stops at 24 hours. boat fits at $657 with auto-stop off. | 75th of 361, with limits $3,657 a month | 52nd cheapest of 361 $6,780 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 bursts: Vercel Sandbox at $216 a month, Azure at $354. Azure adds memory suspend and wake on traffic. boat's start limits make it a compromise here. | 27th cheapest of 336 $216 a month | 39th cheapest of 336 $354 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 Both fit sandboxes for your users: Vercel at $1,267 a month and Azure at $2,260. boat fits at $209, with start limits per plan. | 25th cheapest of 349 $1,267 a month | 32nd cheapest of 349 $2,260 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 Vercel Sandbox is a full match for many short parallel rollouts at $15,761 a month, with high concurrency and fast starts. Azure ($10,740) is listed with limits: its default quota is 300 active cores per region and subscription, raised by support request. | 7th cheapest of 349 $15,761 a month | 158th of 349, with limits $10,740 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 | 81st cheapest of 359 $1,508 a month | 85th cheapest of 359 $1,728 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 All three fit CI runners: boat at $86 a month, Azure at $1,046 and Vercel at $1,144. Builds that need an Android emulator or a VM need /dev/kvm, which only boat documents. | 112th cheapest of 374 $1,144 a month | 108th cheapest of 374 $1,046 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither documents SSH: Vercel offers an SDK and CLI, Azure a shell through its aca CLI, SDK or portal, so both are listed with limits. boat gives each dev box SSH for $26 a month. | 283rd of 371, with limits $145 a month | 327th of 371, with limits $262 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 Azure fits at $1,573 a month if you build a desktop into your own OCI image. On Vercel you set up a browser yourself, so it is listed with limits ($952). boat streams a 60 fps desktop built in at $200. | 263rd of 367, with limits $952 a month | 58th cheapest of 367 $1,573 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 | 100th of 356, with limits $486 a month | 129th of 356, with limits $795 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 | 109th cheapest of 343 $468 a month | 112th cheapest of 343 $561 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 | 234th of 327, with limits $9,960 a month | 240th of 327, with limits $10,956 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 | 31st cheapest of 351 $554 a month | 30th cheapest of 351 $517 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 requirement | Not ranked: misses a requirement | Not 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 requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Vercel Sandbox | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | MicroVM per sandbox with its own kernel | Full VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby; a persistent sandbox resumes from its snapshot in a new session | No documented cap; runs until stopped, deleted or suspended for idleness | No session cap once you turn auto-stop off on a paid plan; auto-stop defaults to 1 hour |
| Suspend and resume | Filesystem snapshot at every stop; processes and memory start fresh | Stop keeps disk only, or disk and memory; a memory-mode resume takes under a second with processes running | Disk saved every minute and at each stop, kept at least 14 days after a stop; memory is not kept, and a resume is like a reboot |
| Desktop, browser, computer use | No built-in desktop or computer-use API; you install Chromium and agent-browser yourself (Vercel guide) or connect an external browser | No desktop or browser in the public images; you can build one into your own OCI image and publish it on an HTTPS port | Built in: 1920x1080, 60 fps desktop and Chrome, computer tools and a browser-control API, embeddable stream |
| Nested virtualization | No; Firecracker does not expose /dev/kvm to guests | Not documented | Yes, /dev/kvm (Android emulator, VMs) |
| Docker inside | Yes, with sudo | Depends on the image: azure-dev ships Docker on systemd; the default ubuntu image has only Buildah | Docker, systemd and root on every sandbox |
| Getting a shell | Commands through the SDK or sandbox CLI; no SSH server | Interactive shell through the aca CLI, SDK or portal; SSH is not documented | SSH, plus CLI and API exec |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Any OCI image from a public or private registry, imported as a disk image | Start from boat's image or a saved snapshot; you cannot boot your own Docker or OCI image |
| Inbound access | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | Public HTTPS routes per published port; private endpoint from your VNet at extra cost; no public IP | Up to 50 HTTPS URLs, token-gated by default; SSH; raw ports over IPv6 (some sandboxes have no IPv4 of their own); no static IP |
| Outbound rules | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs on Enterprise | Egress policy with allow, deny, rewrite and header rules by host, path and method; VNet integration | No provider-side allowlist; firewall inside the VM |
| Keeping keys out of the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | You set it up: an egress Transform rule adds a group secret or managed-identity token as a header, one rule per API host; the built-in Copilot and Claude connections put tokens inside | Optional AI credentials proxy ($1 per day on, plus $1 per 1,000 requests) for model providers and any HTTPS API you add |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Copilot CLI and Claude Code images, run through the exec API | Claude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code and Mistral Vibe, with an API to prompt, steer and stream events |
| Scaling up a fleet | Up to 10,000 sandboxes at once on Pro; vCPU allocation starts at 150 a minute and climbs toward 5,000 with steady use | 300 concurrent active cores per region and subscription by default; more by Azure support request, which can need review | 100 at once on $20 up to 2,000 on $2,000, self-serve; 12 to 90 starts a minute included; extra starts are paid |
| Regions | 19 regions, default iad1 (US East) | 40 Azure regions across the Americas, Europe, Asia, Africa and Oceania | Germany, Finland and France; you cannot pick a region; no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No documented way | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Yes | Yes |
| Desktop GUI | No documented way | With your own setup | Yes |
| Browser | With your own setup | With your own setup | Yes |
| Computer-use API | No documented way | No documented way | Yes |
| SSH | No documented way | No documented way | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | No documented way | Yes | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No documented way | Yes | No documented way |
| Wake on request | No documented way | Yes | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | Yes | No documented way |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No documented way | No documented way | Yes |
| MCP server | Yes | No documented way | No documented way |
| GPU | No documented way | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | No documented way | No documented way | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | No documented way | Yes | Yes |
| Audit logs | Not published | Yes | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Yes | Yes | No documented way |
| EU data residency | Yes | Yes | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
On the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, boat did 28.06 runs per second and Vercel Sandbox did 12.66 (about 2.2x), in StarSling's run of 3 October 2026 (run 37073680030). boat was second of 15; Vercel shared rank 7. 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. Providers ran on different hardware in different regions. Azure Container Apps Sandboxes is not in that run, so we cannot say how fast it is. This measures CPU speed only, not start time.
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. Azure Container Apps Sandboxes is 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.
| Scenario | Vercel Sandbox, a month | Azure Container Apps Sandboxes, 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 | $68 · Pay-as-you-go | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $236 · Pro · with limits | $262 · Pay-as-you-go · with limits | $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 | $3,421 · 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 | $828 · Pro | $989 · Pay-as-you-go | $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 | $2,148 · Pay-as-you-go | $8,800 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it ($0.128 per vCPU-hour in iad1), and for memory for the whole time the sandbox runs ($0.0212 per GB-hour). It adds $0.60 per million sandboxes created, $0.08 per GB-month of snapshots, and $0.05 per GB-month for Drives plus reads and writes. Rates are up to 1.73x higher outside the US. The $20 Pro credit is shared with your other Vercel usage.
Azure Container Apps Sandboxes: Azure bills per second on the Container Apps Consumption meters for the vCPU and memory of the sandbox's tier while it runs, idle time before auto-suspend included. The XL tier (4 cores / 8 GiB) is $0.432 an hour at the East US rates. Stopped sandboxes pay no CPU or memory, and there is no plan fee. Storage for images, snapshots and volumes is announced as billed per GiB soon.
Azure Container Apps Sandboxes: boat charges a flat price per size, per second, while the sandbox runs, busy or idle: $0.036 an hour for 4 vCPU / 8 GB. Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A card is required, also for the 7-day trial. A stopped sandbox has no compute charge, but saved snapshots above the plan's count and the optional AI credentials proxy still charge. Starts above the plan's included number cost $0.03 to $0.07 each.
Limits in those scenarios
For one agent that never stops, Vercel ends each session at 24 hours; it resumes from its snapshot, but running processes start again. Azure has no cap but bills every second, and its lowest price there ($262 a month) needs a 3-year savings plan that Azure does not say covers Sandboxes. For 50 agents with Docker, Azure needs the azure-dev image or your own; 50 XL sandboxes use 200 of its default 300 active cores per region and subscription. Sandboxes for your users (300 L sandboxes, 600 cores) and 1,000 short jobs at once (2,000 cores) need a support request first, which can need review. Vercel fits the burst at $3,152. boat does not: the $2,000 plan includes 90 starts a minute and 2,400 a day, extra starts cost $0.03 to $0.07, and starts above 270 a minute fail with 429. boat also keeps a stopped disk at least 14 days unless you save a snapshot, and a machine failure loses what was written after the last 1-minute snapshot.
| Scenario | Vercel Sandbox | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario | None for this scenario | None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel | None for this scenario | None for this scenario | None for this scenario |
| Sandboxes for your users | None for this scenario | None for this scenario | None for this scenario |
| 1,000 short jobs at once | None for this scenario | None for this scenario |
|
Which one should you use?
Use Vercel Sandbox when
you run many short bursts of untrusted code, build sandboxes from your own Dockerfile, or already deploy on Vercel.
- Images from your Dockerfile. Useful if you already have a Dockerfile: build it into an image and boot sandboxes straight into it.
- Big bursts of short runs. Good for many short parallel jobs: up to 10,000 sandboxes at once on Pro, with CPU billed only while code uses it.
- Fits a Vercel team. If you already deploy on Vercel, sandboxes use your project's login tokens with no extra setup.
Use Azure Container Apps Sandboxes when
your team already runs on Azure and wants stateful sandboxes with no session cap that suspend with their memory, wake on traffic and sit behind strict egress rules.
- Memory suspend and wake on traffic. Good for stateful jobs that sleep between requests: a sandbox suspends with its memory and resumes in under a second.
- No session cap. A running sandbox has no documented time limit, so a long task is not cut off at 24 hours.
- Inside Azure, in 40 regions. Teams already on Azure get Entra ID, Azure billing, VNets and fine-grained egress rules, in 40 regions.
Where boat fits
Vercel Sandbox and Azure Container Apps Sandboxes are microVMs built for running code from an SDK. If your agents work for hours on one machine, build apps, run Docker and emulators, check their work in a browser and need you to step in over SSH, look at boat. Each sandbox has a built-in desktop and installed agents. Check its start limits first: each create, fork and resume counts as a start.
A whole computer you can SSH into
Neither documents SSH or nested virtualization, so an agent cannot start an Android emulator or a VM, and remote editors need a workaround. On Azure, Docker also depends on picking an image like azure-dev.
A screen and a browser built in
Neither has a built-in desktop. On Vercel you install a browser yourself, and on Azure you build a desktop into your own OCI image and keep it working. boat streams a 1920x1080, 60 fps desktop with Chrome.
Agents driven from outside
On Vercel you start agents as plain commands, and on Azure through the exec API, so you build the prompt and steer layer. boat has one API to prompt, steer and stream events from seven installed agents.
Use boat when your agents work for hours on one machine: SSH, Docker, emulators, a built-in desktop and a browser, with coding agents driven from outside. Check the start limits of your plan first. Compare it one to one: boat vs Vercel Sandbox and boat vs Azure Container Apps Sandboxes.
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 Vercel Sandbox cheaper than Azure Container Apps Sandboxes?
In three of our five scenarios, yes: one workday agent costs $57 on Vercel against $68 on Azure, 50 parallel agents cost $2,884 against $3,421, and sandboxes for your users cost $828 against $989. For 1,000 short jobs at once, Azure is cheaper at $2,148 against $3,152, after a quota raise. For one agent that never stops, neither fits as listed. boat costs $20, $317 and $200 in the first three, and does not fit the 1,000-job burst.
Which is faster?
Vercel Sandbox did 12.66 runs per second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB in StarSling's run of 3 October 2026, and boat did 28.06 on an AMD Ryzen 9 9950X host. Azure Container Apps Sandboxes is not in that run, so we cannot say.
Can they run 24/7?
Vercel Sandbox cannot as one session: it stops after 24 hours, then resumes from its filesystem snapshot with processes starting fresh. Azure documents no session cap, but bills a running sandbox every second, so all month costs $262 even with a 3-year savings plan. boat runs one agent all month for $26 once auto-stop is off (default 1 hour).
Can they run Docker?
Vercel Sandbox runs Docker with sudo. On Azure it depends on the image: azure-dev ships Docker on systemd, while the default ubuntu image has only Buildah. boat runs Docker and systemd on every sandbox and also exposes /dev/kvm, which neither of the other two documents.
Can they keep a sandbox's memory when it pauses?
Azure can: it suspends a sandbox with its memory and disk and resumes it in under a second with processes running. Vercel keeps a filesystem snapshot, so a resumed sandbox starts its processes again. boat also keeps the disk only, saved every minute and at each stop.
Can I SSH into either one?
Neither documents SSH. Vercel gives you commands through its SDK and CLI, and Azure an interactive shell through the aca CLI, SDK or portal. Every boat sandbox has SSH, so editors and tools that connect over SSH work.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs Azure Container Apps Sandboxes
- 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