Vercel Sandbox vs Morph Cloud

Vercel Sandbox runs short sessions of untrusted code in Firecracker microVMs across 19 regions, and each session stops after 24 hours. Morph Cloud gives each agent a full VM with no session cap that can pause, branch and wake up again with its memory.

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.

Morph Cloud

Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.

You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state, and it also sells managed GitHub Actions runners and a shared filesystem.

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 rankMorph Cloud: price rankbochka: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Neither has a ready desktop and browser for an agent to check the UI it built; bochka ships both, plus coding agents you drive by API.
244th of 367, with limits
$3,351 a month
198th of 367, with limits
$2,288 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
Vercel's docs say sandboxes are not designed to run continuously; Morph has no session cap, and bochka adds coding agents, a desktop and a credentials proxy.
257th of 366, with limits
$3,657 a month
235th of 366, with limits
$3,014 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; Morph ranks 16th and Vercel 22nd, while bochka's start limits make it a compromise here.
22nd cheapest of 345
$216 a month
16th cheapest of 345
$154 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 own users; Morph ranks 12th and Vercel 15th, and bochka ranks first for the same work.
15th cheapest of 361
$1,267 a month
12th cheapest of 361
$905 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 ranks 3rd for many short parallel rollouts thanks to high concurrency and fast starts; Morph's memory branching suits rollouts that start from one running state.
3rd cheapest of 360
$15,761 a month
86th of 360, with limits
$4,847 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
38th cheapest of 364
$675 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
Morph also sells managed GitHub Actions runners and ranks 39th, ahead of Vercel at 107th; bochka ranks 4th with a runner you install inside a sandbox.
107th cheapest of 377
$1,144 a month
39th cheapest of 377
$355 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
Morph fits a dev box that stays up all day, while Vercel restarts it every 24 hours with fresh processes.
276th of 368, with limits
$145 a month
85th cheapest of 368
$116 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
Vercel has no desktop and Morph has a remote desktop you set up yourself; bochka streams a 60fps desktop with a computer use API.
235th of 369, with limits
$952 a month
182nd of 369, with limits
$595 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
214th of 367, with limits
$250 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
239th of 346, with limits
$234 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
154th of 338, with limits
$4,750 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
214th of 360, with limits
$228 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 SandboxMorph Cloudbochka
IsolationFirecracker microVM with its own kernelFull VM with its own kernelFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Longest session24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new sessionNo cap; a machine runs until you stop it or its optional TTL endsNo cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable
Memory on resumeNot kept; a new session boots from the filesystem snapshotKept; a paused VM resumes with all its processes and bills only its snapshotNot kept; the machine reboots with its disk
Fork a running machineYes, from a filesystem snapshotYes, with its memory, as many copies as you ask for, in under 250 msYes, with its disk
Wake on requestNoYes; a paused VM resumes on the next HTTP request, SSH or exec callNo; a stopped sandbox is started by API
Saving work automaticallyFilesystem snapshot on every stop, billed per GB a month and kept 30 days after last useSaved when you pause or snapshot; a plain stop deletes the instanceDisk saved every minute and on every stop; a stopped sandbox costs nothing
Nested virtualizationNoExperimentalYes, /dev/kvm for Android emulators and VMs
Docker insideYes, with sudoYes, including Docker in Docker and local KubernetesYes, with root and systemd
Custom imagesYour own OCI images from a Dockerfile, via Vercel Container RegistrySnapshots of a configured machine; no OCI imagesNamed snapshots (templates), shareable by code; no Dockerfile builds
Desktop, browser, computer useNone; headless Linux onlyBrowser-based remote desktop; you install the browser and any computer use agent yourself60fps desktop with Chromium, computer use and browser-control APIs
Coding agentsClaude Code, Codex, OpenCode and pi preinstalled; you start them as commandsYou install the agent, then drive it through a tmux API that sends keys and reads the screenSeven agents preinstalled, with an API to prompt, steer and stream events
Keys kept outside the sandboxCredentials brokering injects headers for any HTTPS domain you allowResponses Proxy for model APIs only; other secrets are handed to the machineCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Egress rulesAllow-all, deny-all or a domain and CIDR allowlist, changeable while runningNo provider-side allowlist documentedNo provider-side allowlist; firewall inside the VM
Inbound accessPublic URLs for up to 15 ports, no built-in auth; no raw TCPNamed HTTP services with optional API key auth; SSH through Morph's gateway; no raw TCPHTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Regions19 regions across the US, Europe, Asia, South America, Africa and AustraliaNot publishedEU only: Germany, Finland, France, with zero data retention
Every feature Battleships tracks (43)
FeatureVercel SandboxMorph Cloudbochka
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdNot publishedYesYes
Desktop GUINoYesYes
BrowserNoNoYes
Computer-use APINoNoYes
SSHNoYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkNoYesNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopNoYesNo
Wake on requestNoYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNoYes
Public IPv4NoNoNo
Egress allowlistYesNoNo
Secret proxyYesYesYes
Secret proxy for any APIYesNoYes
Preinstalled agentsYesNoYes
Agent harness APINoYesYes
MCP serverYesNoNo
GPUNoNoNo
WindowsNoYesNo
Arm64NoNoNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedYesYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)NoYesYes
Audit logsNot publishedYesNo
SSOYesNot publishedNo
SOC 2YesNot publishedNo
HIPAAYesNot publishedNo
EU data residencyYesNot publishedYes
Zero data retentionNot publishedNot publishedYes

Performance

Vercel Sandbox12.96 runs/s
Morph CloudNot 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. Morph Cloud has no comparable measurement: it is not in that benchmark run. Morph says it restores a snapshot in under 250 ms, which measures start time, not CPU speed.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Morph Cloud 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 monthMorph Cloud, 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$32 · Developer$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$236 · Pro · with limits$121 · Team$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$1,459 · Scale$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$325 · Scale$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$869 · Scale$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 a 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.

Morph Cloud: Morph bills MCUs at $0.05 an hour each, where a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. Team ($40 a month) and Scale ($250 a month) are prepaid MCU bundles at a discount, and a paused VM bills only its snapshot.

Morph Cloud: bochka charges a flat price per size, per second, only while the machine runs, and a stopped sandbox costs nothing and keeps its disk. 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 does not fit: each session ends at 24 hours and running processes start over, while Morph keeps running. Morph prices disk beyond 16 GiB per vCPU at a rate our scenarios cannot pin down, and it does not publish egress prices. Morph's Developer pool of 64 vCPU holds only 16 machines at 4 vCPU, and one Vercel sandbox on Pro is at most 8 vCPU / 16 GB. For 1,000 short jobs at once, both Vercel and Morph fit, while bochka's $2,000 plan queues the starts.

ScenarioVercel SandboxMorph Cloudbochka
One coding agent, workdaysNone that bite
  • disk beyond 16 GiB: price unknown
  • egress price not published
None that bite
One agent that never stops
  • Pro: sessions capped at 24 h
  • disk beyond 16 GiB: price unknown
  • egress price not published
None that bite
50 agents in parallelNone that bite
  • disk beyond 16 GiB: price unknown
  • 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 close to users around the world, want egress rules you can change from outside, or already build images from a Dockerfile.

  • Regions all over the world. Useful if your users are spread out: Vercel Sandbox runs in 19 regions, while Morph does not publish where it runs.
  • Egress rules and keys you control from outside. A running sandbox can switch to deny-all or a domain allowlist, and its brokered credentials work for any HTTPS API.
  • Images from your Dockerfile. Useful if you already have a Dockerfile: build it into an OCI image and boot sandboxes straight into it.

Use Morph Cloud when

your agents branch from one running state with its memory, sleep between requests and wake on demand, or run for days on one machine.

  • Memory snapshots and branching. Useful for agents that fan out from one running state: Morph copies a live VM with its memory in under 250 ms.
  • Machines that sleep and wake. A paused Morph VM bills only its snapshot and wakes on the next request, with every process still running.
  • No session cap. Morph machines run until you stop them, while Vercel ends every session after 24 hours.

Where bochka fits

Both Vercel Sandbox and Morph Cloud hand you a machine and leave the agent layer to you. If your agents work for hours on one machine, need a desktop and a browser to check their work, or call APIs with keys you do not want inside the sandbox, bochka has those built in, runs no session cap on paid plans, and saves the disk every minute.

Coding agents you drive from outside

On Vercel you start agents as plain commands, and on Morph you drive them through tmux by sending keys and reading the screen. Either way you build and maintain the harness that knows when an agent is done or stuck.

A desktop and a browser ready to use

Vercel Sandbox is headless, and Morph's remote desktop needs you to install the browser and wire up the computer use loop. Without that, an agent cannot open the app it built to see if it works.

A full VM with /dev/kvm and work saved every minute

Vercel has no nested virtualization and Morph lists it as experimental, so Android emulators and VMs are off the table or a gamble. On Morph a plain stop deletes the instance, and on Vercel a 24-hour session restarts every process.

Use bochka when your agents work for hours on one machine and need to arrive ready: coding agents you prompt and steer by API, a desktop with Chromium, /dev/kvm, real keys kept outside the machine, and hosting on many ports in the EU. Compare it one to one: bochka vs Vercel Sandbox and bochka vs Morph Cloud.

Questions people ask

Is Vercel Sandbox cheaper than Morph Cloud?

No, Morph costs less in all five of our scenarios. One workday agent costs $32 a month on Morph vs $57 on Vercel, 50 parallel agents cost $1,459 vs $2,884, and 1,000 short jobs at once cost $869 vs $3,152. bochka costs $20 for the workday agent and $317 for the 50 agents.

Which is faster, Vercel Sandbox or Morph Cloud?

We cannot compare their CPU speed: Vercel Sandbox did 12.96 runs per second on our 4 vCPU benchmark, but Morph Cloud is not in that run. bochka did 26.69 on the same test. Morph's under-250 ms snapshot restore is a start time, not a CPU score.

Can Vercel Sandbox or Morph Cloud run 24/7?

Morph can: a machine runs until you stop it or its optional TTL ends. Vercel ends each Pro session after 24 hours, and the resumed sandbox starts its processes fresh. bochka has no session cap on paid plans and saves the disk every minute.

Can both run Docker and nested virtualization?

Both run Docker inside. Vercel's Firecracker microVMs have no nested virtualization, and Morph lists it as experimental. bochka exposes /dev/kvm for Android emulators and VMs.

Can they keep a machine's memory between runs?

Morph can: it pauses, snapshots and branches a running VM with its memory, and a paused VM wakes on the next request. Vercel saves only the filesystem, so a resumed sandbox boots fresh. bochka also keeps the disk but not the memory.

Do they have a desktop for computer use?

Vercel Sandbox is headless only. Morph has a browser-based remote desktop, but you install the browser and any computer use agent yourself. bochka ships a 60fps desktop with Chromium and a computer use API.

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.