Vercel Sandbox vs Blaxel

Both run each sandbox in a Firecracker microVM with its own kernel. Vercel Sandbox is built for short runs of code in 19 regions, with sessions that stop after 24 hours, while Blaxel sandboxes sleep a few seconds after the last connection and wake in under 25 ms with their memory intact.

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.

Isolation: Firecracker microVM with a dedicated kernel per sandbox
Default image: Ubuntu with Node.js 24, Python 3.14, and Claude Code, Codex, OpenCode and pi preinstalled
SDKs: JavaScript/TypeScript, Python, and a CLI
Regions: 19 regions, default iad1 (US East)
Longest session: 24 hours on Pro and Enterprise, 45 minutes on Hobby; a stopped sandbox resumes from its last snapshot
Biggest sandbox: 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise
Compliance: SOC 2 Type 2, ISO 27001, PCI DSS; HIPAA for Enterprise

Blaxel

Blaxel is a San Francisco company that runs cloud infrastructure for AI agents, and since September 2026 it is part of Baseten.

You get sandboxes, batch jobs, MCP server hosting and a model gateway. Each sandbox is a Firecracker microVM with its own kernel that drops to standby when nothing is connected and resumes in under 25 ms with its memory and running processes. It is built for agent products that start many sandboxes and want them asleep most of the time.

Isolation: Firecracker microVM per sandbox, own kernel
Regions: Oregon, North Virginia, London, Frankfurt
Ownership: Joined Baseten on September 10, 2026; product unchanged
Headquarters: San Francisco, founded 2024
Compliance: SOC 2 Type II, ISO 27001, HIPAA BAA as an add-on
Billing: Allocated RAM per active second, CPU included

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	Blaxel: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Blaxel ranks 10th and fits with a desktop and a browser, while Vercel Sandbox ranks 244th because it has neither and stops each session at 24 hours; bochka ranks 3rd and adds /dev/kvm for emulators.	244th of 367, with limits $3,351 a month	10th cheapest of 367 $2,373 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Blaxel suits mostly idle assistants that sleep and wake on request, while Vercel's docs say its sandboxes are not designed to run continuously.	257th of 366, with limits $3,657 a month	12th cheapest of 366 $2,832 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: Blaxel ranks 14th and Vercel Sandbox ranks 22nd, and bochka's start limits make it a compromise here.	22nd cheapest of 345 $216 a month	14th cheapest of 345 $144 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 Vercel Sandbox ranks 15th and fits 300 users at once, while Blaxel's self-serve tiers stop at 200 at once; bochka ranks 1st.	15th cheapest of 361 $1,267 a month	101st of 361, with limits $926 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 thanks to high concurrency on Pro, while Blaxel's 200 cap on self-serve tiers makes it a compromise.	3rd cheapest of 360 $15,761 a month	77th of 360, with limits $4,378 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	136th of 364, with limits $704 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	107th cheapest of 377 $1,144 a month	57th cheapest of 377 $431 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither fits a dev box well: Vercel restarts it every 24 hours and Blaxel has no native SSH, while bochka is a plain machine you SSH into and leave on.	276th of 368, with limits $145 a month	265th of 368, with limits $114 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 Blaxel ranks 14th with a desktop and computer use built in, while Vercel Sandbox is headless; bochka ranks 6th with a 60fps desktop you can embed.	235th of 369, with limits $952 a month	14th cheapest of 369 $634 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 Blaxel ships a browser with browser control and Vercel Sandbox has no browser feature, so Vercel is a compromise here.	259th of 367, with limits $486 a month	16th cheapest of 367 $317 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	16th cheapest of 346 $215 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	147th of 338, with limits $4,292 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	3rd cheapest of 360 $217 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	Blaxel	bochka
Isolation	Firecracker microVM with its own kernel	Firecracker microVM 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 session cap; Tier 0 and 1 delete sandboxes after 7 or 30 days	No cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable
Sleep and wake	No idle auto-stop; memory is billed until the session ends	Standby a few seconds after the last connection, wakes in under 25 ms with memory and processes	Stop keeps the disk and costs nothing; resume boots the VM again
Saving files	Filesystem snapshot on stop, kept 30 days after last use by default	Files live in memory (about half the RAM); one block volume can be attached at creation	A real disk, snapshotted every minute while running and on stop
Desktop, browser, computer use	None; headless Linux only	Desktop and browser with computer-use and browser-control support	60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream
Nested virtualization	No	No: Firecracker guests do not get /dev/kvm	Yes, /dev/kvm (Android emulator, VMs)
SSH and systemd	No native SSH; commands through the SDK or CLI	Root, terminal through bl connect, no native SSH	Real SSH, root and systemd
Docker inside	Yes, with sudo	Yes, with a Docker-in-sandbox image	Yes, with root and systemd
Custom images	Your own OCI images from a Dockerfile, via Vercel Container Registry	Custom images built from Docker images	Named snapshots (templates), shareable by code; no Dockerfile builds
Coding agents	Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands	Claude Code image you drive from its terminal or your own harness	Claude Code, Codex, pi, OpenCode and more, with an API to prompt, steer and stream events
Inbound access	Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP	Preview URL per port, public or token-protected; no raw TCP or public IP	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4
Egress rules	Allow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs on Enterprise	Domain allow and deny lists, method and path rules, static egress IPs	Open internet; filter inside the VM with nftables
Keys kept outside the sandbox	Credentials brokering injects headers for any HTTPS domain you allow	Proxy fills secrets into outbound HTTPS requests (public preview)	Credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when one runs out
Regions	19 regions across the US, Europe, Asia, South America, Africa and Australia	Oregon, North Virginia, London, Frankfurt	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

Feature	Vercel Sandbox	Blaxel	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	No	Yes
Desktop GUI	No	Yes	Yes
Browser	No	Yes	Yes
Computer-use API	No	Yes	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	Yes	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	No	No	No
BYOC	No	Yes	No
Open source	No	No	No
Scoped API keys	Not published	Yes	Yes
Spend limits	Yes	No	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Not published	Not published	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	Yes	Yes

Performance

Vercel Sandbox12.96 runs/s

Blaxel19.48 runs/s

bochka26.69 runs/s

All three ran the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU and 8 GB in the same run on September 29, 2026. bochka did 26.69 runs per second, Blaxel 19.48 and Vercel Sandbox 12.96, so Blaxel did about 1.5 times the work of Vercel in the same time. 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. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled).

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	Blaxel, 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	$33 · Pay-as-you-go Tier 1	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$236 · Pro · with limits	$120 · Pay-as-you-go Tier 1	$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	$1,489 · Pay-as-you-go Tier 1	$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	$396 · Pay-as-you-go Tier 2 · 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	$3,152 · Pro	$876 · Pay-as-you-go Tier 2 · with limits	$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, idle time included, 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.

Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, meaning it has an open connection, with CPU included. In standby you pay only snapshot storage, and volumes are billed on their full size.

Blaxel: 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 Blaxel and bochka keep going. For sandboxes for your users and 1,000 short jobs at once, Blaxel's self-serve tiers allow at most 200 sandboxes at once, standby ones included, so you need a sales tier; Vercel fits both on Pro. bochka fits 300 users at once but not the 1,000-job burst, because even its $2,000 plan allows 600 starts an hour and 2,400 a day.

Scenario	Vercel Sandbox	Blaxel	bochka
One coding agent, workdays	None that bite	None that bite	None that bite
One agent that never stops	Pro: sessions capped at 24 h	None that bite	None that bite
50 agents in parallel	None that bite	None that bite	None that bite
Sandboxes for your users	None that bite	Pay-as-you-go Tier 2: max 200 concurrent	None that bite
1,000 short jobs at once	None that bite	Pay-as-you-go Tier 2: max 200 concurrent	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 code in parallel, already build on Vercel, or need to run close to users far from the US and Europe.

Regions all over the world. Useful if your users are spread out: Vercel Sandbox runs in 19 regions, from Virginia to Tokyo and Sydney.
Room for big bursts. Pro allows thousands of sandboxes at once, so large parallel runs fit without a sales call.
Fits a Vercel stack. If you already deploy on Vercel, sandboxes boot from your Dockerfile image and use your project's login tokens.

Use Blaxel when

your sandboxes sit idle most of the time and must wake in milliseconds with their memory, or your agents need a desktop and a browser.

Sleeps in seconds, wakes in milliseconds. Useful if sandboxes sit idle most of the time: one sleeps after the last connection and wakes in under 25 ms.
No 24-hour cut. A Blaxel sandbox has no session cap, so a long agent task is not stopped in the middle.
A desktop and a browser. Computer-use and browser agents get a desktop and a browser built in, with no screen to build yourself.

Where bochka fits

If your agents do real work for hours on one machine, look at bochka. It is a whole Linux VM with a real disk, no session cap on paid plans, a 60fps desktop, and an API to drive the agents inside from outside.

A whole Linux machine

Neither Firecracker guest gets /dev/kvm, so an Android emulator or a VM will not start on Vercel or Blaxel. Neither has native SSH, so editors and scp need a workaround. bochka has /dev/kvm, systemd and real SSH.

Work that runs all day on a disk that stays

Vercel stops each session at 24 hours and processes start over. Blaxel keeps files in memory, about half the RAM, unless you attach a volume at creation. bochka has no session cap and saves its disk every minute.

A faster CPU

On the same benchmark bochka did 26.69 runs per second, Blaxel 19.48 and Vercel Sandbox 12.96. Every install, build and test an agent waits on takes about 1.4 times as long on Blaxel and twice as long on Vercel.

Use bochka when your agents work for hours on one machine: builds, tests, Docker, emulators and a desktop with a browser, on a faster CPU, with an API to drive the agents inside from outside. Compare it one to one: bochka vs Vercel Sandbox and bochka vs Blaxel.

Questions people ask

Is Vercel Sandbox cheaper than Blaxel?

No, Blaxel costs less in all five of our scenarios: one workday agent is $33 a month on Blaxel against $57 on Vercel, and 50 parallel agents are $1,489 against $2,884. But Blaxel's self-serve tiers cap you at 200 sandboxes at once, so the 300-user and 1,000-job scenarios need a sales tier, while Vercel fits them at $828 and $3,152. bochka is $20 and $317 for the first two.

Which is faster, Vercel Sandbox or Blaxel?

On the same Node.js build-and-test benchmark at 4 vCPU and 8 GB, Blaxel did 19.48 runs per second and Vercel Sandbox 12.96, about 1.5 times the work. bochka did 26.69 on the same test.

Can Vercel Sandbox and Blaxel run Docker?

Yes, both. Vercel lets you run Docker with sudo, and Blaxel has a Docker-in-sandbox image. Neither gives you /dev/kvm, so Android emulators and VMs do not run inside, while bochka exposes /dev/kvm.

Can they run 24/7?

Vercel Sandbox cannot as one session: it stops after 24 hours on Pro, and its docs say sandboxes are not designed to run continuously. Blaxel has no session cap, but its lower tiers delete sandboxes after 7 or 30 days. bochka has no session cap on paid plans.

Which one has a desktop for computer use?

Blaxel has a desktop and a browser with computer-use support. Vercel Sandbox is headless Linux only. bochka streams a 60fps desktop with Chromium and computer-use and browser-control APIs.

Where do they run?

Vercel Sandbox runs in 19 regions around the world. Blaxel runs in Oregon, North Virginia, London and Frankfurt. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview