Vercel Sandbox vs Upstash Box

Vercel Sandbox runs each sandbox in a Firecracker microVM with its own kernel, in 19 regions, for sessions of up to 24 hours. Upstash Box gives each agent a Docker container in AWS us-east-1 that pauses when idle, wakes on the next request, and can stay on all 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.

Upstash Box

Upstash Box is a cloud computer for AI agents from Upstash, the company known for serverless Redis, Vector and QStash.

Each box is a Docker container with its own filesystem, shell, git and an optional coding agent such as Claude Code, Codex or OpenCode, which you drive from TypeScript or Python SDKs. A box pauses when it sits idle, keeps its files, and you pay for the CPU it actually uses. Upstash built it to run its own Context7 service and opened it to everyone in March 2026.

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 workloadVercel Sandbox: price rankUpstash Box: price rankbochka: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Neither fits fully: Vercel stops each session after 24 hours and Upstash has no Docker inside, while bochka ranks 3rd with Docker, a desktop and no session cap.
244th of 367, with limits
$3,351 a month
61st of 367, with limits
$464 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An always-on agent fits Upstash's keep-alive box better than Vercel, whose sessions stop at 24 hours; bochka gives it a full VM that runs with no session cap.
257th of 366, with limits
$3,657 a month
103rd of 366, with limits
$475 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 well, since both bill CPU only while code uses it; Upstash Box ranks 10th and Vercel Sandbox ranks 22nd.
22nd cheapest of 345
$216 a month
10th cheapest of 345
$119 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
All three fit sandboxes for your users; bochka ranks 1st, Upstash Box ranks 2nd and Vercel Sandbox ranks 15th on cost for the same work.
15th cheapest of 361
$1,267 a month
2nd cheapest of 361
$222 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, while Upstash Box only fits as a compromise.
3rd cheapest of 360
$15,761 a month
352nd of 360, with limits
$8,068 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
52nd cheapest of 364
$1,011 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
Both fit CI runners and land close together, while bochka ranks 4th and adds /dev/kvm for Android builds.
107th cheapest of 377
$1,144 a month
120th cheapest of 377
$1,520 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A 24/7 dev box fits Upstash's flat-price keep-alive box; on Vercel it restarts every 24 hours and loses its running processes.
276th of 368, with limits
$145 a month
10th cheapest of 368
$20 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 for a computer-use agent to look at; bochka streams a full Linux desktop at 60fps.
235th of 369, with limits
$952 a month
73rd of 369, with limits
$76 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
49th of 367, with limits
$38 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
37th cheapest of 346
$400 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
200th of 338, with limits
$8,000 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
225th of 360, with limits
$259 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 itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureVercel SandboxUpstash Boxbochka
IsolationFirecracker microVM with its own kernelDocker container per box on AWSFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker insideYes, with sudoNot documented; the box is itself a Docker containerYes, Docker and systemd run as on any Linux server
Nested virtualizationNoNoYes, /dev/kvm for Android emulators and VMs
Longest session24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new sessionNo cap documented; a box pauses when idle, and a keep-alive box stays on all monthNo cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable
Stop and resumeFilesystem snapshot on stop, stored per GB-month and kept 30 days after last use by defaultPauses itself when idle and keeps its files; storage keeps billing while pausedDisk saved every minute and on stop; a stopped sandbox costs nothing
Wake on requestNoYes; a request to a public URL resumes a paused boxNo; a stopped sandbox is started by API
Custom imagesYour own OCI images from a Dockerfile, via Vercel Container RegistryComing soon; environments are reused through filesystem snapshotsNamed snapshots (templates), shareable by code; no Dockerfile builds
Biggest machine8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on EnterpriseLarge: 8 vCPU / 16 GB, with a 20 GB diskUp to 16 vCPU / 32 GB on the $100 plan and above
Desktop, browser, computer useNone; headless Linux onlyManaged headless Chromium with AI page actions and CDP; no desktop60fps desktop and Chromium, computer-use and browser-control APIs
Coding agentsClaude Code, Codex, OpenCode and pi preinstalled; you start them as commandsClaude Code, Codex and OpenCode built in, with run and stream APIs, webhooks and scheduled promptsClaude Code, Codex, pi, OpenCode and more, with an API to prompt, steer and stream events
Inbound accessPublic URLs for up to 15 ports, no built-in auth; no raw TCPHTTPS URL per port, public unless you add a token or basic auth; SSH through a gateway; no raw TCPHTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Outbound rulesAllow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs on EnterpriseAllow all, deny all, or allow and deny by domain and CIDR, changeable on a running boxOpen internet, no provider-side allowlist; firewall inside the VM
Keys kept outside the sandboxCredentials brokering injects headers for any HTTPS domain you allowHost proxy injects headers into outbound HTTPS; set when the box is createdCredentials proxy for model providers and any HTTPS API; switch a credential to another account when one runs out
Regions19 regions across the US, Europe, Asia, South America, Africa and AustraliaUS only (AWS us-east-1)EU only (Germany, Finland, France)
Every feature Battleships tracks (43)
FeatureVercel SandboxUpstash Boxbochka
Full VM (own kernel)YesNoYes
Docker insideYesNoYes
Nested virtualizationNoNoYes
RootYesNot publishedYes
SystemdNot publishedNot publishedYes
Desktop GUINoNoYes
BrowserNoYesYes
Computer-use APINoNoYes
SSHNoYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesNoYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkNoNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopNoYesNo
Wake on requestNoYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistYesYesNo
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APINoYesYes
MCP serverYesYesNo
GPUNoNoNo
WindowsNoNoNo
Arm64NoYesNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)NoYesYes
Audit logsNot publishedNot publishedNo
SSOYesNoNo
SOC 2YesYesNo
HIPAAYesNoNo
EU data residencyYesNoYes
Zero data retentionNot publishedNot publishedYes

Performance

Vercel Sandbox12.96 runs/s
Upstash BoxNot measured
bochka26.69 runs/s

On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, bochka did 26.69 runs per second and Vercel Sandbox did 12.96, so bochka finished about twice as many runs in the same time. Upstash Box has no result in that test, so there is no comparable measurement 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. Upstash Box 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.

ScenarioVercel Sandbox, a monthUpstash Box, a monthbochka, 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$21 · 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$21 · 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
$2,884 · Pro$900 · Pay as You Go · with limits$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$306 · 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$1,822 · 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 fee per sandbox created and per GB of snapshots. The $20 Pro credit is shared with your other Vercel usage.

Upstash Box: A standard box is billed per active CPU hour by size, plus storage per GB-month, and RAM is free. A keep-alive box costs a flat $8, $16 or $32 a month whether it is busy or not.

Upstash Box: bochka 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, all of it usage credit.

Limits in those scenarios

For one agent that never stops, Vercel does not fit: each session ends at 24 hours and running processes start over. For 50 agents in parallel, Upstash does not fit because there is no Docker inside a box, and its egress price is not published. For 1,000 short jobs at once both fit, while bochka's $2,000 plan starts at most 600 an hour and 2,400 a day, so the burst is queued.

ScenarioVercel SandboxUpstash Boxbochka
One coding agent, workdaysNone that bite
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
One agent that never stops
  • Pro: sessions capped at 24 h
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
50 agents in parallelNone that bite
  • missing Docker inside
  • flat pool: the tier is billed whether used or not
  • egress price not published
None that bite
Sandboxes for your usersNone that bite
  • egress price not published
None that bite
1,000 short jobs at onceNone that bite
  • egress price not published
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use Vercel Sandbox when

you run many short bursts of untrusted code, need Docker or your own image, or need to run close to users around the world.

  • A real microVM with Docker. Each sandbox has its own kernel and can run Docker with sudo, which an Upstash container does not offer.
  • Regions all over the world. Useful if your users are spread out: Vercel Sandbox runs in 19 regions, while Upstash Box runs only in us-east-1.
  • Images from your Dockerfile. Useful if you already have a Dockerfile: build it into an image and boot sandboxes straight into it.

Use Upstash Box when

your agents mostly wait, need to wake on an incoming request or stay on all month cheaply, and can live without Docker in the US.

  • Idle costs no CPU, and a request wakes the box. Good for agents that wait a lot: RAM is not billed, idle costs no CPU, and a request wakes a paused box.
  • Boxes that stay on. A keep-alive box stays on all month for a flat price, with no 24-hour session cap to work around.
  • Agent APIs built in. Claude Code, Codex and OpenCode come with run and stream APIs, webhooks and scheduled prompts.

Where bochka fits

Look at bochka when your agents need a whole machine for hours: Docker, emulators, a desktop and services that keep running. Vercel stops sessions at 24 hours and Upstash runs containers without Docker inside, and neither gives an agent a screen.

A full VM with Docker and /dev/kvm

Upstash boxes are containers with no Docker inside, so the 50-agent scenario does not fit there. Vercel runs Docker, but Firecracker has no nested virtualization, so Android emulators and VMs are out on both.

No session cap, disk saved every minute

On Vercel each session stops at 24 hours and every process starts over. Upstash keeps a box on only with a flat-price keep-alive box. bochka runs with no session cap on paid plans and stops cost nothing.

A desktop the agent can see

Vercel Sandbox is headless, and Upstash offers only a headless Chromium over CDP. bochka streams a 60fps desktop with Chromium and computer-use APIs, so an agent can open the app it built and check it.

Use bochka when your agents work for hours on one machine: Docker, emulators, a desktop with a browser and services that keep running, with an API to drive the agents inside from outside. Compare it one to one: bochka vs Vercel Sandbox and bochka vs Upstash Box.

Questions people ask

Is Vercel Sandbox cheaper than Upstash Box?

No, Upstash costs less in all five of our scenarios. One workday agent costs $21 a month on Upstash against $57 on Vercel, and sandboxes for your users cost $306 against $828. For 50 agents in parallel Upstash is $900 a month, but it does not fit because there is no Docker inside.

Which is faster, Vercel Sandbox or Upstash Box?

Only Vercel Sandbox has a CPU result in the hpc-sandbox-benchmarks test: 12.96 runs per second at 4 vCPU / 8 GB. Upstash Box has no comparable measurement. bochka did 26.69 on the same test.

Can Upstash Box run Docker?

Its docs do not offer it: each box is itself a Docker container, and custom images are listed as coming soon. Vercel Sandbox runs Docker inside its microVM with sudo, and bochka runs Docker and systemd as on any Linux server.

Can Vercel Sandbox or Upstash Box run 24/7?

Upstash can: a keep-alive box stays on all month for a flat price. Vercel sessions last up to 24 hours on Pro, then stop, and the resumed sandbox starts its processes fresh. bochka has no session cap on paid plans.

Do they have a desktop for computer use?

No. Vercel Sandbox is headless Linux, and Upstash offers a headless Chromium with AI page actions and CDP but no desktop. bochka streams a 60fps Linux desktop with computer-use tools.

Where do they run?

Vercel Sandbox runs in 19 regions, with iad1 in the US as the default. Upstash Box runs only in AWS us-east-1, with more regions planned. bochka runs in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview

More comparisons

Bochka product preview · Pricing, benchmarks and commands are illustrative. Sandbox provisioning is not connected.