Vercel Sandbox vs Together Code Sandbox
Vercel Sandbox is a self-serve microVM for short runs of untrusted code, with a firewall you control and 19 regions. Together Code Sandbox starts VMs from Docker-image snapshots and can save their memory, but Together has to turn it on for your organization.
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.
Together Code Sandbox
Together AI is a cloud for running and training AI models, and Code Sandbox is its product for running code in isolated VMs.
You build a snapshot from a Docker image or Dockerfile on Together's builder, then start sandboxes from it and run commands and file operations through the together-sandbox SDK or CLI. When a sandbox ends you can save its disk, and its memory too, as a new snapshot to start more sandboxes from. It is aimed at model-generated code, agent tool calls and reinforcement learning rollouts, and it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.
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 | Together Code Sandbox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs Docker, root and often /dev/kvm; Vercel has no nested virtualization, Together documents neither, and boat has all three. | 244th of 367, with limits $3,351 a month | 65th of 367, with limits $528 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Neither fits an agent that lives on its machine all month: Vercel stops each session at 24 hours, and Together has no idle detection or wake on request. | 257th of 366, with limits $3,657 a month | 152nd of 366, with limits $1,095 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 fits short code bursts well, billing CPU only while code runs; Together's Code Interpreter runs only Python in 60-minute sessions. | 22nd cheapest of 345 $216 a month | 326th of 345, with limits $2,190 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 boat ranks first and Vercel Sandbox ranks 15th for sandboxes you hand to users; on Together every port is public and preview URLs are listed as coming soon. | 15th cheapest of 361 $1,267 a month | 234th of 361, with limits $900 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 and fast starts; Together can branch rollouts from a memory snapshot, but that VM product needs Together to enable it. | 3rd cheapest of 360 $15,761 a month | 315th of 360, with limits $21,900 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 | 258th of 364, with limits $450 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 | 251st of 377, with limits $180 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that stays up all day restarts every 24 hours on Vercel and has no wake on request on Together; on boat it keeps running with its disk saved. | 276th of 368, with limits $145 a month | 210th of 368, with limits $22 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 Computer-use agents need a desktop and a browser; neither Vercel nor Together offers one, while boat streams a 60fps desktop with Chromium. | 235th of 369, with limits $952 a month | 184th of 369, with limits $600 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 | 301st of 367, with limits $900 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 | 219th of 346, with limits $180 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 | 124th of 338, with limits $3,600 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 | 167th of 360, with limits $150 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 | Together Code Sandbox | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | A VM per sandbox on Together's infrastructure | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Getting started | Self-serve on Hobby and Pro; Enterprise by contract | The SDK and CLI must be enabled for your organization by Together; only Code Interpreter is self-serve | Sign up and start a sandbox from the API, CLI or dashboard |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new session | Runs until you end it or its time to live, counted from creation, runs out | No cap on paid plans (--no-auto-stop); default TTL 1 hour, changeable |
| Machine size | Up to 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise | 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed | 2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above |
| Saving state | Filesystem snapshot on stop, kept 30 days after last use by default; processes start over | End a sandbox with a snapshot of its disk, or disk and memory; new sandboxes resume with processes running | Disk saved every minute and on stop; a stopped sandbox costs nothing; resume boots the machine again |
| Docker inside | Yes, with sudo | Not documented; commands run as user 1000 by default, root on request | Yes, with root and systemd |
| Nested virtualization | No | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Snapshots built from a Docker image or Dockerfile on Together's builder | Named snapshots (templates), shareable by code; no Dockerfile builds |
| Reaching the sandbox | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | All ports public; preview URLs coming soon; an experimental inbound allowlist by IP or token | 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 egress 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 | No credentials proxy documented | Credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when one runs out |
| Desktop, browser, computer use | None; headless Linux only | None; headless command and file access only | 60fps desktop and Chromium, computer-use and browser-control APIs |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Run your own agent through execs; a Harbor guide for agent evals | Claude Code, Codex, OpenCode and more preinstalled, with an API to prompt, steer and stream events |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | Together Code Sandbox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | No | Yes |
| Computer-use API | No | No | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | Yes | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | No | 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 | No | 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 | No | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | 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 | No | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the StarSling hpc-sandbox-benchmarks Node.js test 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. There is no comparable CPU measurement for Together Code Sandbox; it was not part of that run.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Together Code Sandbox 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 | Together Code Sandbox, 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 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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.
Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, but the VMs must be enabled for your organization, so the table prices Together with Code Interpreter: $0.03 per 60-minute session from prepaid credits. Code Interpreter runs only Python and keeps no disk.
Together Code Sandbox: 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
The Together column is Code Interpreter, so it does not fit any scenario: sessions last 60 minutes, nothing is kept, it runs only Python and the machine size is not published. Vercel fits most rows but ends each session at 24 hours, so one agent that never stops restarts every day. For 1,000 short jobs at once, Vercel fits, while boat's start limits queue the burst even on the $2,000 plan.
| Scenario | Vercel Sandbox | Together Code Sandbox | 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 want self-serve sandboxes today for many short bursts of untrusted code, a firewall you control from outside, or regions close to users outside Europe.
- Self-serve, with regions worldwide. Anyone can sign up and start sandboxes today, in 19 regions from Virginia to Tokyo and Sydney.
- A firewall you control from outside. A running sandbox can switch to deny-all or a list of allowed domains without a restart.
- Built for big bursts of short runs. Good for code interpreters and many parallel rollouts: CPU is billed only while code uses it, and concurrency is high.
Use Together Code Sandbox when
you already run models on Together and want light sandboxes you can save with their memory and branch from, or a simple Python runner billed per session.
- Memory snapshots to branch from. Useful for rollouts and test variants: save a sandbox with its memory and start many copies with processes still running.
- Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account and API key.
- Very small machines and a Python runner. Good for many light jobs: sandboxes start at a tenth of a core, and a Python interpreter API bills per session.
Where boat fits
Both Vercel Sandbox and Together Code Sandbox are headless machines for running code you hand them. If what you are really running is agents that work for hours, build and test apps, run Docker or emulators, and need a screen to check their work, boat gives each one a whole machine you can start today.
Agents can work all day
Vercel stops each session after 24 hours and restarts every process, and Together has no idle detection or wake on request. boat has no session cap on paid plans and saves the disk every minute.
A whole machine with a screen
boat gives root, systemd, Docker, /dev/kvm and a 60fps desktop with Chromium. Vercel has no nested virtualization or desktop, and Together documents neither Docker inside nor a desktop, so you build those into your own image.
Private hosting and agents driven from outside
On Together every port is public, and Vercel's URLs have no built-in auth. boat serves token-protected HTTPS on 50 ports and gives one API to prompt and steer the agents inside, which you would otherwise write yourself.
Use boat when your agents work for hours on one machine: builds, tests, Docker, emulators and a desktop with a browser, with private hosting and an API to drive the agents inside from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs Together Code Sandbox.
Questions people ask
Is Vercel Sandbox cheaper than Together Code Sandbox?
Together's only self-serve price is Code Interpreter, which does not fit our scenarios because sessions end after 60 minutes and keep no disk. For sandboxes for your users, Vercel costs $828 a month against $900 for Together, and for 1,000 short jobs at once $3,152 against $6,000. boat costs $200 for the first and does not fit the second.
Which is faster?
Vercel Sandbox did 12.96 runs per second on the StarSling Node.js test at 4 vCPU / 8 GB, and boat did 26.69. Together Code Sandbox has no comparable measurement.
Can Vercel Sandbox and Together Code Sandbox run Docker?
Vercel Sandbox runs Docker inside with sudo. Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox. boat runs Docker, systemd and root on every machine.
Can I sign up for Together Code Sandbox today?
The together-sandbox SDK and CLI must be enabled for your organization, so you ask Together for access. Code Interpreter is self-serve with prepaid credits. Vercel Sandbox and boat are both self-serve.
Which one can save memory and branch from it?
Together can end a sandbox with a snapshot of its disk and memory, and new sandboxes start from it with processes running. Vercel snapshots the filesystem on stop, so processes start over, and boat saves the disk every minute and can fork a running sandbox.
Do they have a desktop for computer use?
No. Both are headless and controlled through commands and files. boat streams a 60fps desktop with Chromium and has computer-use and browser-control APIs.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs Together Code Sandbox
- 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