Vercel Sandbox vs OpenAI Containers
Vercel Sandbox gives you a Firecracker microVM with root and Docker that you drive with an SDK, for runs of up to 24 hours. OpenAI Containers are a tool inside OpenAI's model API: the model runs Python or shell commands in a box without sudo that expires after 20 minutes without use.
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.
OpenAI Containers
OpenAI Containers are the sandboxes OpenAI runs for its own model tools: Code Interpreter, Hosted Shell and the Agents API's hosted sandbox.
This is a different kind of product from boat: a tool inside OpenAI's model API, not a machine you rent. You create a container through the API or let a Responses call make one, and the model runs Python or shell commands in it on a fixed Debian 12 image without sudo, until it expires after 20 minutes without use. It is built for apps that already call OpenAI models and want them to run code, read files and make charts without running any servers.
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 | OpenAI Containers: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Vercel Sandbox has Docker and root but stops each session at 24 hours; an OpenAI container has no sudo, no Docker and loses its files when it expires. | 244th of 367, with limits $3,351 a month | 356th of 367, with limits $17,371 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An agent that lives on one machine all month does not fit either: Vercel stops at 24 hours and OpenAI expires after 20 idle minutes. | 257th of 366, with limits $3,657 a month | 341st of 366, with limits $13,140 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 OpenAI Containers are built for this, with the model running code inside the API call; Vercel Sandbox ranks 22nd and fits fully since it bills CPU only while code uses it. | 22nd cheapest of 345 $216 a month | 194th of 345, with limits $6,000 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 gives your users public URLs on up to 15 ports; OpenAI containers have no inbound access, and boat ranks 1st here. | 15th cheapest of 361 $1,267 a month | 361st of 361, with limits $3,780 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; OpenAI does not publish how many containers can run at once. | 3rd cheapest of 360 $15,761 a month | 191st of 360, with limits $30,000 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 | 360th of 364, with limits $5,760 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 with Docker inside; OpenAI containers have no documented Docker and Code Interpreter starts with no internet, while boat ranks 4th. | 107th cheapest of 377 $1,144 a month | 345th of 377, with limits $1,728 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither is a dev box you keep: Vercel restarts every 24 hours and OpenAI discards data on expiry; boat keeps its disk with no session cap on paid plans. | 276th of 368, with limits $145 a month | 362nd of 368, with limits $1,051 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 OpenAI's Agents API has a hosted browser for computer use and Vercel Sandbox is headless only; boat streams a 60fps desktop with a computer-use API. | 235th of 369, with limits $952 a month | 351st of 369, with limits $5,280 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 | 328th of 367, with limits $1,440 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 | 328th of 346, with limits $1,755 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 | 311th of 338, with limits $35,100 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 | 308th of 360, with limits $870 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 | OpenAI Containers | boat |
|---|---|---|---|
| What it is | A microVM you create and drive with the JavaScript or Python SDK or a CLI | A sandbox tool the model uses inside OpenAI's API | A cloud VM you create, keep, stop and reach from outside |
| Isolation | Firecracker microVM with its own kernel | A fully sandboxed virtual machine; hypervisor not named | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root and Docker | Docker with sudo; no nested virtualization | Commands do not run with sudo; no Docker or /dev/kvm documented | Root, systemd, Docker and /dev/kvm on every machine |
| Machine size | Up to 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise | 1, 4, 16 or 64 GB of memory; vCPU not published | 4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby | Expires after 20 minutes without use; Agents API sandboxes after an hour without activity | No cap on paid plans; you set the time to live |
| Files after the session | Filesystem snapshot on stop, billed per GB a month, kept 30 days after last use by default | Data is discarded when the container expires | Disk saved every minute and on stop; a stopped sandbox costs nothing |
| Custom image | Your own OCI image from a Dockerfile | Fixed Debian 12 image; you upload files into each container | Named snapshots of a set-up machine, reused as templates |
| Inbound access | Public URLs for up to 15 ports, no built-in auth; no raw TCP | None; you reach the container only through the API | SSH, HTTPS URLs for up to 50 ports, token-protected by default, raw TCP |
| Outbound network | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running | Code Interpreter and Hosted Shell: off until an admin sets an org allowlist | Open internet on every plan; firewall inside the VM |
| Keys kept outside the sandbox | Credentials brokering adds headers for HTTPS domains you allow | domain_secrets: a sidecar adds the real header, the model sees a placeholder | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when one runs out |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Agents API (beta) drives a managed Codex harness with steering, events and webhooks | Claude Code, Codex, OpenCode and more, with one API to prompt, steer and stream events |
| Desktop and computer use | None; headless Linux only | Hosted browser for the Agents API computer_use tool | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Regions | 19 regions across the US, Europe, Asia, South America, Africa and Australia | US or EU processing for Code Interpreter; Agents API data residency in the US only | EU only: Germany, Finland, France |
| CPU speed (4 vCPU / 8 GB) | 12.96 runs per second | Not measured | 26.69 runs per second |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | OpenAI Containers | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | No | Yes |
| Pause/resume | Yes | No | 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 | No | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | Yes | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | No | 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 | No | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | No | No | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | No | No | 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 | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, Vercel Sandbox did 12.96 runs per second and boat did 26.69, about twice as many. OpenAI Containers have no comparable measurement: they are not in the benchmark, and OpenAI does not publish how many vCPU each container size gets.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. OpenAI Containers 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 | OpenAI Containers, 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 | $228 · API pay as you go · 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 | $1,051 · API pay as you go · 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 | $11,405 · API 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 | $1,620 · API pay as you go · 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 | $6,000 · API pay as you go · 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.
OpenAI Containers: OpenAI bills each container session by the minute for the memory size you pick, with a 5-minute minimum, and model tokens are billed on top. There is no plan fee.
OpenAI Containers: boat 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, and all of the fee is usage credit.
Limits in those scenarios
OpenAI Containers do not fit any of the five scenarios as written: no persistent disk, no Docker, no open internet in Code Interpreter and Hosted Shell, and no published vCPU per size. Vercel Sandbox fits four of them, but for one agent that never stops it ends each session at 24 hours and running processes start over. OpenAI does not publish how many containers can run at once, so 300 user sandboxes and a 1,000-job burst are unconfirmed there. Vercel fits that burst at $3,152 a month, while boat's $2,000 plan queues the starts.
| Scenario | Vercel Sandbox | OpenAI Containers | 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 code that need root or Docker, or must run close to users in many regions.
- Root, Docker and your own image. Useful if your code needs system packages or Docker: you get sudo, Docker and sandboxes booted from your own Dockerfile image.
- Regions all over the world. Useful if your users are outside the US and Europe: Vercel Sandbox runs in 19 regions, including Asia, South America, Africa and Australia.
- Ports you can open. Useful if users need to see what was built: a sandbox can serve public URLs on up to 15 ports.
Use OpenAI Containers when
your app already calls OpenAI models and the model only needs to run short pieces of code on files you give it.
- Built into the model call. Useful if your app already calls OpenAI models: one tool line in a request gives the model a place to run code.
- Locked-down network by default. Useful if code must only reach chosen hosts: Code Interpreter and Hosted Shell have no outbound access until an admin allows domains.
- Nothing to manage or clean up. Useful for short jobs: there is no plan fee, billing is by the minute, and an unused container expires on its own.
Where boat fits
Both are built for short runs: Vercel stops each session at 24 hours, and an OpenAI container expires after 20 idle minutes. If your agents work for hours or days on one machine, with Docker, a desktop and ports you can open, look at boat instead.
Agents that work all day and keep their disk
Vercel ends each session at 24 hours and restarts every process, and an OpenAI container discards its files after 20 idle minutes. boat has no session cap on paid plans and saves the disk every minute, and a stopped sandbox costs nothing.
A full VM with /dev/kvm and a desktop
Neither offers nested virtualization, OpenAI gives no sudo or Docker, and Vercel has no screen. boat gives root, systemd, Docker, /dev/kvm for Android emulators and a 60fps desktop with Chromium, so an agent can open the app it built.
Agents driven from outside, reachable on any port
On Vercel you start agents as plain commands and build the control layer yourself; OpenAI's harness runs only Codex and has no inbound access. boat drives Claude Code, Codex and others through one API, with HTTPS on 50 ports and raw TCP.
Use boat when your agents work for hours on one machine: Docker, emulators, a desktop with a browser, a disk that stays, and an API to drive the agents inside from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs OpenAI Containers.
Questions people ask
Is Vercel Sandbox cheaper than OpenAI Containers?
In our scenarios, yes. One workday coding agent comes to $57 a month on Vercel and $228 on OpenAI, and 50 parallel agents come to $2,884 vs $11,405. OpenAI also bills model tokens on top, and its containers do not fully fit these scenarios. boat comes to $20 and $317 for the same two.
Which is faster?
Vercel Sandbox did 12.96 runs per second on a Node.js build-and-test loop at 4 vCPU / 8 GB, and boat did 26.69. OpenAI Containers are not in that benchmark, and OpenAI does not publish the vCPU behind each size, so there is no fair number for them.
Can Vercel Sandbox or OpenAI Containers run Docker?
Vercel Sandbox runs Docker with sudo. OpenAI's docs say hosted shell commands do not run with sudo, and no Docker support is documented. boat gives root, systemd, Docker and /dev/kvm on every sandbox.
How long can a session last?
Vercel Sandbox sessions last up to 24 hours on Pro and Enterprise and 45 minutes on Hobby, then resume from a filesystem snapshot with processes started over. An OpenAI container expires after 20 minutes without use and its data is discarded. boat has no session cap on paid plans.
Can I open a web app running inside the sandbox?
On Vercel Sandbox, yes: it serves public URLs for up to 15 ports, with no built-in auth. OpenAI containers have no ports, URLs or SSH. boat gives HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP and SSH.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs OpenAI Containers
- 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