Vercel Sandbox vs Ona
Vercel Sandbox is a self-serve API for running untrusted or agent-written code in short Firecracker microVM sessions, in 19 regions. Ona, formerly Gitpod and now part of OpenAI, is a cloud dev environment platform for engineers and its Codex agent, sold to new customers through sales and run in their own AWS or GCP 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.
Ona
Ona, formerly Gitpod, is a platform for cloud dev environments and background coding agents, and is now part of OpenAI.
Ona is a different kind of product from boat: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config, which people open in a browser IDE, VS Code or JetBrains, and where Ona's Codex Agent can plan, code, test and open pull requests. It is built for engineering teams who want the same governed environment for every developer and agent; new customers run it in their own AWS or GCP account on an Enterprise contract.
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 | Ona: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Neither has a desktop or browser for an agent to check the UI it built, and neither offers nested virtualization; boat has both and fits fully. | 244th of 367, with limits $3,351 a month | 324th of 367, with limits $7,315 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Neither fits an always-on agent cleanly: Vercel stops each session at 24 hours, and Ona stops after 30 idle minutes unless auto-stop is set to Never, while boat has no session cap on paid plans. | 257th of 366, with limits $3,657 a month | 83rd of 366, with limits $8,504 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 fits short code bursts well because it bills CPU only while code uses it, and Vercel Sandbox ranks 22nd here while Ona ranks 335th. | 22nd cheapest of 345 $216 a month | 335th of 345, with limits $5,320 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 boat ranks first for sandboxes you hand to your users; Ona is built for your own engineers and defaults to 10 running environments per user. | 15th cheapest of 361 $1,267 a month | 330th of 361, with limits $5,988 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; Ona is not built for this, and boat's start limits make it a compromise. | 3rd cheapest of 360 $15,761 a month | 283rd of 360, with limits $9,773 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 | 334th of 364, with limits $5,768 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 starts fast and fits CI runs; Ona starts each run from a prebuild, and boat can fork one warm machine into copies. | 107th cheapest of 377 $1,144 a month | 365th of 377, with limits $5,461 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is a full cloud IDE with Dev Containers and prebuilds, Vercel Sandbox restarts every 24 hours and loses its running processes, and boat is a full VM you reach over SSH, HTTPS or a desktop. | 276th of 368, with limits $145 a month | 368th of 368, with limits $5,140 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 Vercel Sandbox nor Ona has a graphical desktop to drive, while boat streams a 60fps desktop with Chromium for computer use. | 235th of 369, with limits $952 a month | 353rd of 369, with limits $5,691 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 | 150th of 367, with limits $5,346 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 | 146th of 346, with limits $5,468 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 | 234th of 338, with limits $9,960 a month | 261st of 338, with limits $14,360 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 | 93rd of 360, with limits $5,228 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 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 | Ona | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Isolated VM with dedicated compute per environment, built from a Dev Container config | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Getting started | Self-serve Hobby and Pro plans; JavaScript and Python SDKs and a CLI | New customers go through sales for Enterprise; new Core subscriptions are closed, and the SDK is Enterprise only | Self-serve plans from a free trial; API and SDK on every plan |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new session | No hard cap; stops after 30 idle minutes by default, background processes do not count, can be set to Never | No cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable |
| Files after a stop | Filesystem snapshot on stop, billed per GB a month, kept 30 days after last use by default | Disk persists; in your own cloud it is billed while stopped, and Core archives a stopped environment after 3 days | Snapshot every minute and on stop; a stopped sandbox keeps its disk and costs nothing |
| Copies of a machine | New sandboxes can start from a saved snapshot | No environment copy; you can create a project from an environment's config | Fork a running sandbox into copies with its files |
| Docker and nested virtualization | Docker with sudo; no nested virtualization | Docker and root inside the Dev Container; nested virtualization not documented | Docker, root, systemd and /dev/kvm on every machine |
| Desktop and computer use | None; headless Linux only | Browser IDE plus VS Code and JetBrains over SSH; no graphical desktop | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Team IDE | None; you drive it with commands, files and ports | Browser, VS Code and JetBrains IDEs with Dev Containers, prebuilds and organization policies | No team IDE; SSH, HTTPS ports or the desktop |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Codex Agent started from chat, a Linear issue or an automation; Claude Code you run yourself | Claude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code, Mistral Vibe, with an API to prompt, steer and stream events |
| Reaching the sandbox | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | HTTPS URL per port for you, your organization or everyone; SSH; no raw TCP or public IP documented | 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 | No provider-side allowlist documented | No provider-side allowlist; firewall inside the VM |
| Keys kept outside the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | Secrets are injected into the environment as environment variables or files | Credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when one runs out |
| GPUs | None | GPU instance types on Enterprise runners in your own cloud, such as one NVIDIA A10G with 16 vCPU and 64 GB | None |
| Regions | 19 regions across the US, Europe, Asia, South America, Africa and Australia | Enterprise runners in your own AWS or GCP account; Ona Cloud in Frankfurt and North Virginia for existing Core subscribers | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | Ona | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | No | 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 | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | No | Yes | 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 | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Not published | No | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the same hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, boat did 26.69 runs per second and Vercel Sandbox did 12.96, so boat finished about twice as many runs in the same time. There is no comparable measurement for Ona: it was not in the public benchmark runs we use. 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. Ona 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 | Ona, a month | boat, 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 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $236 · Pro · with limits | $5,140 · Enterprise (AWS Marketplace 12-month contract) · 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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | $2,000 · $2000/mo · with limits |
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.
Ona: New Core subscriptions are closed, so Ona prices here use its Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract, plus compute on your own AWS bill. Real Enterprise prices are negotiated with sales.
Ona: boat 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
No Ona scenario fits as published, because a new customer can only buy Enterprise through sales, and Ona does not publish an Enterprise concurrency limit, so the table assumes 3 environments at once. Vercel Sandbox fits four of the five scenarios; the exception is one agent that never stops, because each session ends at 24 hours and running processes start over. Vercel fits the 1,000 short jobs at once, which boat does not: even boat's $2,000 plan allows 600 starts an hour and 2,400 a day. On Pro, one Vercel sandbox can be at most 8 vCPU / 16 GB.
| Scenario | Vercel Sandbox | Ona | boat |
|---|---|---|---|
| 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 Vercel Sandbox when
you run many short bursts of untrusted or agent-written code from your own app, want to sign up and start today, or need to run close to users outside Europe.
- Built for short bursts of code. Useful for code interpreters and many short parallel runs: CPU is billed only while code uses it, and starts are fast.
- Self-serve, from code, today. Useful if you want to start now: sign up for Hobby or Pro and create sandboxes from the JavaScript or Python SDK.
- Regions and a firewall you control. Useful if users are spread out: 19 regions, and a running sandbox can switch to deny-all or a domain allowlist.
Use Ona when
your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account or with a GPU.
- A full cloud IDE for your team. Useful if engineers work in the same environments as their agents: browser, VS Code and JetBrains IDEs with Dev Containers and prebuilds.
- Runs in your own cloud. Useful if environments must run inside your own AWS or GCP account: Ona's Enterprise runners do that.
- GPU environments. Useful if your agents need a GPU: Enterprise runners can use GPU instance types, such as an A10G VM with 16 vCPU and 64 GB.
Where boat fits
If you are choosing between Vercel Sandbox and Ona to run coding agents that work for hours, boat sits between them: a self-serve sandbox API like Vercel, with long-lived full VMs that keep their work like a dev environment. Each boat machine has /dev/kvm, a desktop with a browser, and an API to drive the agents inside from outside.
Agents that work all day
Vercel stops each session at 24 hours and running processes start over. Ona stops after 30 idle minutes because background work does not count, so you set it to Never and pay for the disk on your cloud bill while stopped.
A desktop and /dev/kvm on every machine
Neither Vercel Sandbox nor Ona has a graphical desktop, so an agent cannot open the app it built to check it, and neither offers /dev/kvm for Android emulators or microVMs. boat has both, plus a 60fps stream.
Drive the agents inside from outside
On Vercel the agents are installed but you run them as plain commands and build the control layer yourself. On Ona the SDK needs an Enterprise contract through sales, and its managed agent is Codex only.
Use boat when your agents work for hours on one machine: full VMs with /dev/kvm, Docker and a desktop with a browser, disks saved every minute, forks of a running sandbox, and an API to drive the agents inside from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs Ona.
Questions people ask
Is Vercel Sandbox cheaper than Ona?
In all five of our scenarios, yes. One coding agent on workdays is $57 a month on Vercel Sandbox against $5,030 on Ona, and 50 agents in parallel are $2,884 against $6,521. Ona's numbers use its Enterprise listing on AWS Marketplace, and its real price is a sales quote; boat is $20 and $317 for the same two.
Which is faster?
Only Vercel Sandbox has a comparable CPU score: 12.96 Node.js build-and-test runs per second at 4 vCPU / 8 GB. Ona was not in the public benchmark runs we use. boat did 26.69 runs per second on the same test.
Can Vercel Sandbox and Ona run Docker?
Yes. Vercel Sandbox runs Docker with sudo, and Ona runs Docker with root inside the Dev Container. Neither offers nested virtualization; boat has Docker, systemd and /dev/kvm on every machine.
Can either run an agent 24/7?
Vercel Sandbox sessions stop after 24 hours on Pro, and its docs say sandboxes are not designed to run continuously. Ona has no hard cap, but stops after 30 idle minutes by default and background work does not count, so you set auto-stop to Never. boat has no session cap on paid plans.
Can I sign up for Ona like Vercel Sandbox?
No. Ona's billing docs say new Core subscriptions are no longer available, so new customers go through sales for Enterprise. Vercel Sandbox has self-serve Hobby and Pro plans, and boat's plans are self-serve from a free trial up.
Is Ona the same as Gitpod?
Yes. Gitpod renamed itself Ona in 2025, and Ona is now part of OpenAI. Its managed agent is Codex, and the older Ona Agent is no longer available on Ona Cloud.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs Ona
- 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