E2B vs Vercel Sandbox
Both run each sandbox in a Firecracker microVM and stop a session after 24 hours on their paid plans. E2B can pause a sandbox with its memory and has a Linux desktop, while Vercel Sandbox bills CPU only while code uses it and runs in 19 regions.
The companies and products
E2B
E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.
Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs, and its runtime is open source.
- Isolation
- Firecracker microVM per sandbox
- Bring your own cloud
- Enterprise data plane in your AWS, GCP or Azure account
- Compliance
- SOC 2 Type II; HIPAA BAA on request
- Machine size
- 1 to 8 vCPU and 1 to 8 GiB RAM, CPU only
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.
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. “16th cheapest of 367” means 15 of the other 366 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 | E2B: price rank | Vercel Sandbox: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month E2B fits a software factory fully and Vercel Sandbox only with workarounds, since it has no desktop to check the UI an agent built; bochka ranks 3rd with nested virtualization and no 24-hour cap. | 16th cheapest of 367 $4,143 a month | 244th of 367, with limits $3,351 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both stop a session at 24 hours, so an assistant that lives on its machine all month is a compromise on each; bochka can simply keep running. | 51st of 366, with limits $5,348 a month | 257th of 366, with limits $3,657 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 Vercel Sandbox ranks 22nd and E2B ranks 37th for short code bursts, where fast starts and paying little for idle time matter most. | 37th cheapest of 345 $421 a month | 22nd cheapest of 345 $216 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; Vercel Sandbox ranks 15th, E2B ranks 23rd and bochka ranks 1st for the same work. | 23rd cheapest of 361 $2,354 a month | 15th cheapest of 361 $1,267 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 E2B ranks 2nd and Vercel Sandbox ranks 3rd for many short rollouts in parallel, where bochka's start limits make it a compromise. | 2nd cheapest of 360 $9,384 a month | 3rd cheapest of 360 $15,761 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 | 78th cheapest of 364 $1,975 a month | 69th cheapest of 364 $1,508 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 Vercel Sandbox fits CI runners fully and E2B only as a compromise; bochka ranks 4th and adds nested virtualization for Android and VM builds. | 337th of 377, with limits $1,429 a month | 107th cheapest of 377 $1,144 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 192nd of 368, with limits $358 a month | 276th of 368, with limits $145 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 E2B has a Linux desktop for computer use and Vercel Sandbox has none; bochka streams its desktop at 60fps. | 32nd cheapest of 369 $1,342 a month | 235th of 369, with limits $952 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 Neither E2B nor Vercel Sandbox fully fits browser agents, while bochka ranks 7th with Chromium and a browser-control API built in. | 100th of 367, with limits $746 a month | 259th of 367, with limits $486 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 | 57th cheapest of 346 $554 a month | 277th of 346, with limits $468 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 | 227th of 338, with limits $9,223 a month | 234th of 338, with limits $9,960 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 | 11th cheapest of 360 $1,043 a month | 283rd of 360, with limits $554 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 | E2B | Vercel Sandbox | 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 |
| CPU benchmark (4 vCPU / 8 GB) | 12.61 runs/s | 12.96 runs/s | 26.69 runs/s |
| Biggest self-serve machine | Up to 8 vCPU / 8 GiB, more on request | Up to 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Session length | Up to 1 hour on Hobby, 24 hours on Pro; pausing resets the clock | 45 minutes on Hobby, 24 hours on Pro and Enterprise; resume starts a new session | No cap on paid plans; you set the time to live |
| Pause and resume | Saves memory and disk; resumes in about 1 second with processes running, and can wake on the next request | Filesystem snapshot on stop; memory is not kept and a new session boots from the snapshot | Disk saved every minute and on stop; a stopped sandbox costs nothing and boots again on resume |
| Desktop and computer use | Linux desktop for computer use | None; headless Linux only | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Nested virtualization | Not supported | No | Yes, /dev/kvm for Android emulators and VMs |
| Docker inside | Yes | Yes, with sudo | Yes, with root and systemd |
| Coding agents | Templates and guides for many agents, run through the command API | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Seven agents preinstalled, with an API to prompt, steer and stream events |
| Inbound access | HTTPS URL per port, public by default unless you turn on a token; no dedicated IP | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Outbound rules | Allow and deny lists by IP, CIDR or domain | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs on Enterprise | Open internet, no provider-side allowlist; firewall inside the VM |
| Keeping API keys out of the sandbox | Secrets injected into outbound HTTPS headers (private beta) | Credentials brokering injects headers for any HTTPS domain you allow | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Regions | US by default; EU and APAC on Pro and above, enabled by support | 19 regions across the US, Europe, Asia, South America, Africa and Australia | EU only (Germany, Finland, France) |
| Self-hosting | Open-source runtime, plus bring your own cloud on Enterprise | No | No |
Every feature Battleships tracks (43)
| Feature | E2B | Vercel Sandbox | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | Yes | 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 | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | Yes | No | 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 | Yes | No | No |
| BYOC | Yes | No | No |
| Open source | Yes | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Not published | Not published | No |
| SSO | No | 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
All three were measured in the same hpc-sandbox-benchmarks run, a Node.js build-and-test loop at 4 vCPU / 8 GB. E2B did 12.61 runs per second and Vercel Sandbox did 12.96, so they are close to even, while bochka did 26.69, about twice either one. 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.
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 | E2B, a month | Vercel Sandbox, 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 | $202 · Pro | $57 · Pro | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $368 · Pro · with limits | $236 · Pro · 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 | $2,773 · Pro | $2,884 · Pro | $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 | $1,395 · Pro+ (600 concurrent) | $828 · Pro | $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 | $2,797 · Pro++ (1,100 concurrent) | $3,152 · Pro | $2,000 · $2000/mo · with limits |
E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox. Pro costs $150 a month for higher limits with no usage credit, and more concurrency costs $500 a month per 500 slots.
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but for memory 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.
Vercel Sandbox: 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
Neither E2B nor Vercel Sandbox fits one agent that never stops, because both end a session at 24 hours on Pro. E2B's Pro plan includes 20 GiB of disk, so a 50 GB workday agent goes past what it publishes a price for. For 1,000 short jobs at once, both fit: E2B Pro++ queues bursts above 300 starts a minute, and Vercel fits on Pro. bochka does not fit that burst, since even its $2,000 plan allows 600 starts an hour and 2,400 a day.
| Scenario | E2B | Vercel Sandbox | bochka |
|---|---|---|---|
| One coding agent, workdays |
| None that bite | None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
| None that bite | None that bite |
| Sandboxes for your users |
| None that bite | None that bite |
| 1,000 short jobs at once |
| None that bite |
|
Which one should you use?
Use E2B when
your jobs pause between requests and must come back with their memory, when an agent needs a desktop, or when you want to self-host the runtime.
- Pause with memory, wake on request. Useful for jobs that sleep between requests: a paused sandbox comes back in about a second with its processes still running.
- A desktop for computer use. E2B has a Linux desktop an agent can see and click, which Vercel Sandbox does not offer.
- Open source and your own cloud. Its runtime is Apache-2.0, and Enterprise customers can run it in their own AWS, GCP or Azure account.
Use Vercel Sandbox when
you run short bursts of untrusted code, want to pay for CPU only while it works, or need regions close to users around the world.
- Pay for CPU only while it works. Useful for bursty code runs: CPU is billed only while code uses it, though memory is billed the whole session.
- Regions all over the world. Vercel Sandbox runs in 19 regions, from Virginia to Tokyo and Sydney, so it can sit close to your users.
- A firewall you change while it runs. A running sandbox can switch to deny-all or a list of allowed domains without a restart.
Where bochka fits
E2B and Vercel Sandbox are both built around short sessions that stop at 24 hours. If your agents work for hours on one machine, building, testing, running Docker or emulators and checking their work on a screen, bochka gives them a faster full VM that keeps going.
No 24-hour cutoff
Both stop a session at 24 hours on their paid plans. On E2B your code has to pause and resume the sandbox to reset the clock; on Vercel the sandbox resumes from a snapshot but every process starts over.
Twice the CPU and nested virtualization
E2B did 12.61 and Vercel Sandbox 12.96 runs per second, against 26.69 on bochka, so every build and test waits about twice as long. Neither exposes /dev/kvm, so Android emulators and VMs cannot start.
Drive agents inside from outside, with a screen
On both, agents run as plain commands, so you build the code that prompts, steers and reads them. Vercel has no desktop at all, while bochka streams a 60fps desktop with computer-use and browser-control APIs.
Use bochka when your agents work for hours on one machine: builds, tests, Docker, emulators and a desktop with a browser, on a CPU about twice as fast, with an API to drive the agents inside from outside. Compare it one to one: bochka vs E2B and bochka vs Vercel Sandbox.
Questions people ask
Is E2B cheaper than Vercel Sandbox?
It depends on the workload. Vercel Sandbox costs less for one workday agent ($57 vs $202 a month on E2B) and for sandboxes for your users ($828 vs $1,395 on E2B). E2B costs a little less for 50 parallel agents ($2,773 vs $2,884 on Vercel) and for 1,000 short jobs at once ($2,797 vs $3,152 on Vercel).
Which is faster, E2B or Vercel Sandbox?
On the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, E2B did 12.61 runs per second and Vercel Sandbox did 12.96, so they are about even. bochka did 26.69 in the same run, about twice either one.
Can E2B or Vercel Sandbox run for days?
Not in one session. E2B stops a sandbox after 24 hours on Pro, though pausing and resuming resets the clock. Vercel stops a session after 24 hours and resumes from a filesystem snapshot with processes starting over; bochka has no session cap on paid plans.
Can E2B and Vercel Sandbox run Docker?
Yes, both run Docker inside the sandbox. Neither offers nested virtualization, so Android emulators and VMs will not start; bochka exposes /dev/kvm for those.
Does either have a desktop for computer use?
E2B has a Linux desktop for computer use. Vercel Sandbox is headless only. bochka streams a 60fps desktop with Chromium and computer-use and browser-control APIs.
Where do E2B and Vercel Sandbox run?
E2B runs in the US by default, with EU and APAC on Pro and above, enabled by support. Vercel Sandbox runs in 19 regions around the world. bochka runs only in the EU, in Germany, Finland and France.
Try bochka
Install the CLI, then run bochka new.
Product preview