Vercel Sandbox vs Google Agent Runtime
Vercel Sandbox gives each run a Firecracker microVM with its own kernel, sudo and Docker, for sessions of up to 24 hours. Google Agent Runtime hosts your agent code on Google Cloud and adds sandboxes that run as an unprivileged user with no Docker, but they can live for days and keep their memory in snapshots.
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.
Google Agent Runtime
Google Agent Runtime is the agent hosting part of Gemini Enterprise Agent Platform on Google Cloud, renamed from Vertex AI Agent Engine in April 2026.
It is a hyperscaler service, not a sandbox company. Agent Runtime deploys agents you build with ADK, LangGraph, LangChain, AG2 or LlamaIndex and bills them only while they work on a turn. Next to it, Agent Sandbox gives those agents a place to run code: a Code Execution sandbox, a shell or custom container sandbox, and a Computer Use browser. All of them run as secure containers inside your Google Cloud project.
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 | Google Agent Runtime: 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 for an agent to check the app it built, and Google has no root or Docker; boat has all of them on every VM. | 244th of 367, with limits $3,351 a month | 295th of 367, with limits $5,801 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB A Google sandbox can live up to 7 days and Agent Runtime skips billing between turns, while Vercel stops each session at 24 hours; boat has no session cap on paid plans. | 257th of 366, with limits $3,657 a month | 28th cheapest of 366 $7,519 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 and bills CPU only while code uses it; Google's Code Execution sandbox is a ready Python interpreter, but its sizes are small and it has no network. | 22nd cheapest of 345 $216 a month | 254th of 345, with limits $275 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 can give your users a public URL for up to 15 ports, while a Google sandbox has no public URL documented; boat ranks first here with HTTPS on up to 50 ports. | 15th cheapest of 361 $1,267 a month | 280th of 361, with limits $1,916 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 fast starts and high concurrency; Google is a compromise here. | 3rd cheapest of 360 $15,761 a month | 128th of 360, with limits $8,240 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 | 79th cheapest of 364 $2,060 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 runs Docker with sudo, so container builds work there, while Google's unprivileged sandboxes have no Docker; boat runs Docker and systemd on every VM. | 107th cheapest of 377 $1,144 a month | 98th cheapest of 377 $989 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 276th of 368, with limits $145 a month | 311th of 368, with limits $241 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 Google offers a browser only and Vercel offers nothing on screen, so desktop apps are out of reach on both; boat streams a 60fps desktop. | 235th of 369, with limits $952 a month | 283rd of 369, with limits $1,648 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 Google gives agents a real Chromium with a VNC view and CDP, while Vercel Sandbox has no browser feature; boat ships Chromium with browser control. | 259th of 367, with limits $486 a month | 102nd of 367, with limits $824 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 | 53rd cheapest of 346 $515 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 | 210th of 338, with limits $8,240 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 | 260th of 360, with limits $412 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 | Google Agent Runtime | boat |
|---|---|---|---|
| Isolation | Firecracker microVM with its own kernel | Secure container sandboxing inside Google Cloud | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root and Docker | Docker inside, with sudo | Runs as appuser with no sudo; images must not need root; no Docker documented | Root, systemd and Docker on every machine |
| Nested virtualization | No | No /dev/kvm documented | Yes, /dev/kvm (Android emulator, VMs) |
| How long a sandbox lives | 24 hours per session on Pro and Enterprise, 45 minutes on Hobby; resume starts a new session | TTL of up to 7 days for a custom container and 14 days for Code Execution, then deleted | No session cap on paid plans |
| Saving state | Filesystem snapshot on stop, billed per GB a month, kept 30 days after last use by default | Snapshots keep memory and files; pause keeps files at a lower rate that is not published | Disk saved every minute and on stop; a stopped sandbox costs nothing; fork a running sandbox |
| Desktop, browser, computer use | None; headless Linux only | A browser in a container with a VNC live view, a click, type and screenshot API, and CDP | 60fps desktop and Chromium, computer-use and browser-control APIs, embeddable stream |
| Shell access | SDK and CLI commands; no SSH | execute_bash() API calls, each in a new shell; no SSH | SSH, plus an API for commands |
| Inbound access | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | Through Google's API or a private endpoint in your VPC; no public URL documented | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| Outbound internet | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running | Off unless the template turns it on; can route through your VPC with Cloud NAT, a static IP or Cloud NGFW | Open internet on every plan; firewall inside the VM, no provider-side allowlist |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Custom containers and templates (in Preview), built to run without root | Named snapshots (templates), shareable by code; no Dockerfile builds |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | Managed Agents API (Preview) runs Google's Antigravity harness | Claude Code, Codex, pi, OpenCode and more, with an API to prompt, steer and stream events |
| Keys kept outside the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | You provision and scope the credentials the agent uses | Credentials proxy for model providers and any HTTPS API you register; switch to another account when credits run out |
| Hosting your agent code | You run your agent loop in the sandbox or elsewhere on Vercel | Agent Runtime deploys ADK, LangGraph, LangChain, AG2 and LlamaIndex agents; idle time between turns is not billed | You run your own agent loop inside a sandbox |
| Regions | 19 regions, default iad1 (US East) | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | EU only: Germany, Finland, France, with EU data residency |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | Google Agent Runtime | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | 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 | No | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | 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 | No | No |
| Windows | No | No | No |
| Arm64 | No | Yes | 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 | Not published | 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 | Not published | Yes |
Performance
On StarSling's Node.js build-and-test loop at 4 vCPU / 8 GB, run on 2026-09-29, 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. Google Agent Runtime and its sandboxes were not part of that run, so there is no comparable number for Google.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Google Agent Runtime 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 | Google Agent Runtime, 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 | $73 · Pay as you go | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $236 · Pro · with limits | $301 · Pay as you go | $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 | $3,626 · 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 | $1,030 · Pay as you go | $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 | $2,060 · Pay as you go | $2,000 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but for memory for 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.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, with the first 50 vCPU-hours and 100 GiB-hours free each month. Runtime skips idle time between turns, but sandboxes are billed while they exist, and disk and egress rates are not published.
Google Agent Runtime: boat plans start at $20 a month, and all of it is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
For one agent that never stops, Vercel ends each session at 24 hours, so it does not fit, while Google fits until the sandbox TTL runs out. For 50 agents in parallel with Docker inside, Google does not fit because its sandboxes have no Docker, while Vercel fits. Every Google row leaves disk and egress unpriced because those rates are not published. For 1,000 short jobs at once both Vercel and Google fit, while boat's start limits queue the jobs.
| Scenario | Vercel Sandbox | Google Agent Runtime | 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 sudo or Docker, want public preview URLs, or already build images from a Dockerfile.
- Sudo and Docker inside. Useful if agents install packages or build containers: each Vercel sandbox is a microVM with sudo and Docker.
- Public preview URLs. Useful if people outside need to open what the code serves: Vercel gives public URLs for up to 15 ports.
- Images from your Dockerfile. Useful if you already have a Dockerfile: build it into an OCI image and boot sandboxes straight into it.
Use Google Agent Runtime when
you build agents with ADK or LangGraph on Google Cloud and want them hosted inside your own project, with locked sandboxes that can live for days and a browser for computer use.
- A managed home for agent code. Useful if you build agents with ADK or LangGraph: Agent Runtime hosts them and skips billing for idle time between turns.
- Sandboxes that last for days. Useful if a task runs longer than a day: a Google sandbox can live up to 7 days, and snapshots keep its memory.
- A browser for computer use. Useful if your agent works in web pages: Google's Computer Use sandbox gives a browser with a live view and CDP.
Where boat fits
Look at boat if your agents work for hours or days on one machine and need a real computer. Vercel stops each session at 24 hours and has no screen, and Google takes away root and Docker. boat gives every agent a full VM with root, Docker, SSH, a desktop and public URLs, with no session cap on paid plans.
No session cap, disk saved every minute
On Vercel a session stops at 24 hours and running processes start over. On Google a sandbox is deleted when its TTL ends, 7 days at most. On boat paid plans have no cap, and a stopped sandbox keeps its disk for free.
Root, Docker and /dev/kvm together
Google's sandboxes run as appuser with no sudo, so docker compose and apt installs fail there. Vercel has Docker but no nested virtualization, so Android emulators and VMs do not run. boat has root, Docker, systemd and /dev/kvm on every VM.
A desktop, and agents you drive from outside
Vercel has no screen at all and Google offers a browser only, so desktop apps are out of reach. boat streams a 60fps desktop and gives you one API to prompt and steer Claude Code, Codex and other agents inside.
Use boat when your agents need a real computer for hours or days: root, Docker, /dev/kvm, SSH, a desktop and public URLs on a full VM that keeps its disk, with coding agents you drive from outside. Compare it one to one: boat vs Vercel Sandbox and boat vs Google Agent Runtime.
Questions people ask
Is Vercel Sandbox cheaper than Google Agent Runtime?
In four of our five scenarios, yes. One workday agent comes to $57 a month on Vercel and $73 on Google, and sandboxes for your users come to $828 vs $1,030. For 1,000 short jobs at once Google is cheaper at $2,060 vs $3,152, and boat comes to $20 for the workday agent and $200 for the user sandboxes.
Which is faster?
Vercel Sandbox did 12.96 runs per second on StarSling's Node.js build-and-test loop at 4 vCPU / 8 GB, and boat did 26.69. Google's sandboxes were not measured in that run, so there is no fair speed comparison with Google.
Can Vercel Sandbox or Google Agent Runtime run Docker?
Vercel Sandbox can: each microVM runs Docker with sudo. Google's sandboxes run as the unprivileged user appuser with no sudo, so Docker is not available. boat runs Docker with root and systemd on every VM.
How long can a sandbox run on each?
A Vercel session lasts up to 24 hours on Pro and Enterprise, then resumes from its filesystem snapshot with processes started over. A Google sandbox lives until its TTL ends, up to 7 days for a custom container and 14 days for Code Execution. boat has no session cap on paid plans.
Is Google Agent Runtime the same as Vertex AI Agent Engine?
Yes. Google renamed Vertex AI Agent Engine to Agent Runtime in April 2026, as part of Gemini Enterprise Agent Platform. Its code, shell and browser sandboxes are a separate part of the same platform called Agent Sandbox.
Where do they run?
Vercel Sandbox runs in 19 regions, with iad1 in the US as the default. Google runs in 23 locations across the US, Europe, Asia, Canada, Australia and Brazil. boat runs only in the EU (Germany, Finland and France) and keeps data there.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Vercel Sandbox
- boat vs Google Agent Runtime
- 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