Vercel Sandbox vs Azure Container Apps Sandboxes
Both run each sandbox as a microVM with its own kernel, and both are headless. Vercel Sandbox stops every session after 24 hours and bills CPU only while code uses it, while Azure has 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, 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.
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, has its own kernel, and can be suspended with its memory and resumed 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. “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 | Azure Container Apps Sandboxes: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory runs Docker builds, browsers and emulators for hours; both are compromises here, and bochka gives each agent /dev/kvm, a desktop and no session cap. | 244th of 367, with limits $3,351 a month | 288th of 367, with limits $5,276 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Vercel stops each session after 24 hours, and Azure keeps billing a running sandbox every second, so an all-month agent is a compromise on both; bochka runs it with no session cap. | 257th of 366, with limits $3,657 a month | 302nd of 366, with limits $6,544 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 bursts; Vercel Sandbox ranks 22nd and Azure Container Apps Sandboxes ranks 34th, and Azure adds memory suspend and wake on traffic. | 22nd cheapest of 345 $216 a month | 34th cheapest of 345 $354 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 Both fit sandboxes for your users, with Vercel Sandbox ranking 15th and Azure 22nd on cost; bochka ranks first for the same work. | 15th cheapest of 361 $1,267 a month | 22nd cheapest of 361 $2,260 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 many short parallel rollouts thanks to high concurrency and fast starts, while Azure's default quota of 500 active cores makes it a compromise. | 3rd cheapest of 360 $15,761 a month | 153rd of 360, with limits $10,740 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 | 75th cheapest of 364 $1,728 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 The two are close for CI runners, but neither offers nested virtualization, so builds that need an Android emulator or a VM need bochka's /dev/kvm. | 107th cheapest of 377 $1,144 a month | 103rd cheapest of 377 $1,046 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither gives you SSH: Vercel offers an SDK and CLI, Azure a shell through its aca CLI or portal, while bochka gives each dev box SSH and raw TCP. | 276th of 368, with limits $145 a month | 322nd of 368, with limits $262 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 Both are headless, so a computer-use agent has no screen to look at unless you build one; bochka streams a 60fps desktop with computer-use APIs. | 235th of 369, with limits $952 a month | 279th of 369, with limits $1,573 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 | 288th of 367, with limits $795 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 | 284th of 346, with limits $561 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 | 239th of 338, with limits $10,956 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 | 278th of 360, with limits $517 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 | Azure Container Apps Sandboxes | bochka |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | MicroVM per sandbox with its own 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 documented cap; runs until stopped, deleted or suspended for idleness | No cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable |
| Suspend and resume | Filesystem snapshot on stop; processes and memory start fresh | Suspend with memory and disk; resume in under a second with processes running | Disk saved every minute and on stop; resume boots the machine again; a stopped sandbox costs nothing |
| Desktop, browser, computer use | None; headless Linux only | None; headless, no managed browser | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Nested virtualization | No | Not documented | Yes, /dev/kvm for Android emulators and 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 | Interactive shell through the aca CLI, SDK or portal; no SSH | SSH, plus CLI and API exec |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Boots from an OCI image or a snapshot | Named snapshots (templates), shareable by code; no Dockerfile builds |
| 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 | 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 | Egress policy with allow, deny, rewrite and header rules by host, path and method; VNet integration | Open internet, no provider-side allowlist; firewall inside the VM |
| Keeping keys out of the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | Group secrets usable in egress header transforms; Copilot and Anthropic tokens are injected into the sandbox at startup | Credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when one runs out |
| 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 | Seven agents preinstalled, with an API to prompt, steer and stream events |
| Scaling up a fleet | vCPU allocation starts at 150 a minute and climbs toward 5,000 with steady use | 500 concurrent active cores by default; more by Azure support request, which can need review | Concurrency set by plan, up to 2,000 sandboxes, self-serve; start limits per plan |
| Regions | 19 regions, default iad1 (US East) | 40 Azure regions, 9 of them in the EU | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | Azure Container Apps Sandboxes | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Yes | 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 | Yes | 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 | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | No | No | No |
| Open source | No | No | 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 | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Yes | 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, Vercel Sandbox did 12.96 runs per second and bochka did 26.69, so bochka finished about twice as many runs in the same time. Azure Container Apps Sandboxes has no comparable measurement yet, so this page makes no speed claim for it. This measures CPU speed only, not start time.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Azure Container Apps Sandboxes 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 | Azure Container Apps Sandboxes, a month | bochka, 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 | $2,000 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but charges 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.
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, including idle time before auto-suspend, which defaults to 5 minutes. There is no plan fee, and some regions such as West Europe charge more.
Azure Container Apps Sandboxes: bochka charges a flat price per size, per second, only while the machine runs; 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 Azure has no cap but bills every second, and only gets close with a 3-year savings plan commitment. For 50 agents with Docker inside, Azure needs an image that ships Docker and its default 500 active cores cap the fleet until support raises it. For 1,000 short jobs at once, both fit, and bochka does not: even its $2,000 plan allows 600 starts an hour and queues bursts above 90 a minute.
| Scenario | Vercel Sandbox | Azure Container Apps Sandboxes | bochka |
|---|---|---|---|
| One coding agent, workdays | None that bite | 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 | 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, 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: it bills CPU only while code uses it and scales vCPU up with steady use.
- 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 bochka fits
Both Vercel Sandbox and Azure Container Apps Sandboxes are headless microVMs built for running code, not for an agent that works on one machine for hours. If your agents build apps, run Docker and emulators, check their work in a browser and need you to step in over SSH, bochka gives each one a whole computer with a desktop and agents built in.
A whole computer you can SSH into
Neither has 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 for every agent
Both are headless, so an agent cannot open the app it built to see if it works. On either one you would install a browser, a virtual display and a streaming stack yourself, then keep them working.
Agents driven from outside, keys kept outside
On Vercel you start agents as plain commands, and on Azure through raw exec, so you build the prompt and steer layer. Azure also injects Copilot and Anthropic tokens into the sandbox, where a hijacked agent can read them.
Use bochka when your agents work for hours on one machine: SSH, Docker, emulators, a desktop and a browser, with coding agents driven from outside and a credentials proxy built in. Compare it one to one: bochka vs Vercel Sandbox and bochka vs Azure Container Apps Sandboxes.
Questions people ask
Is Vercel Sandbox cheaper than Azure Container Apps Sandboxes?
In most of our scenarios, yes: one workday agent costs $57 on Vercel vs $68 on Azure, 50 parallel agents cost $2,884 vs $3,421, and sandboxes for your users cost $828 vs $989. For 1,000 short jobs at once, Azure is cheaper at $2,148 vs $3,152. bochka costs less than both where it fits, for example $20 a month for the workday agent.
Which is faster?
Vercel Sandbox did 12.96 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, and bochka did 26.69. Azure Container Apps Sandboxes has not been measured on the same test, so we make no claim about it.
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 savings plan. bochka runs one agent all month for $26.
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. bochka runs Docker and systemd on every sandbox and also exposes /dev/kvm, which neither of the other two offers.
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 only a filesystem snapshot, so a resumed sandbox starts its processes over, and bochka also keeps the disk only, saved every minute.
Can I SSH into either one?
No. Vercel gives you commands through its SDK and CLI, and Azure an interactive shell through the aca CLI, SDK or portal. Every bochka sandbox has an SSH endpoint, so editors and tools that connect over SSH just work.
Try bochka
Install the CLI, then run bochka new.
Product preview
More comparisons
- bochka vs Vercel Sandbox
- bochka 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