Beam vs Instabox
Beam is a serverless GPU platform whose sandboxes are gVisor containers, with a separate line of CPU VMs. Instabox, which launched today as an invite-only beta, gives each agent a Firecracker microVM of one fixed size, free for now.
The companies and products
Beam
Beam is a serverless cloud for GPU inference, sandboxes and background jobs, built on its open-source runtime Beta9.
Beam runs functions, REST endpoints, task queues, pods, sandboxes and VMs on CPUs and GPUs, all from a Python or TypeScript SDK. A sandbox is a container isolated with gVisor that starts in a second or two, lives until you terminate it or its time to live runs out, and can be saved as a filesystem image or a memory snapshot. Beam VMs are a separate CPU product: a microVM with its own kernel, systemd and a root disk that stays when it stops. Much of Beam is a GPU serverless platform for AI teams.
- Bring your own cloud
- Management fee per vCPU and GB of RAM, on top of your own cloud bill
Instabox
Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.
Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.
- Isolation
- Firecracker microVM per machine
- Machines per account
- 5, in any state: paused and stopped ones count
- Company
- InsForge AI, Inc.
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. “8th cheapest of 345” means 7 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 | Beam: price rank | Instabox: 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, systemd, /dev/kvm and a disk that lasts; boat ranks 3rd with all four, while Beam sandboxes end with their time to live and Instabox has one 4 vCPU / 8 GiB size. | 69th of 367, with limits $551 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 115th of 366, with limits $651 a month | No published price | 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 Beam ranks 8th here: its sandboxes bill per second and end on their own when the timer runs out; Instabox has no published price yet, so it is not ranked. | 8th cheapest of 345 $117 a month | No published price | 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 Beam ranks 3rd and boat ranks 1st; Instabox allows 5 machines per account, paused and stopped ones included, so it cannot yet give a sandbox to each of many users. | 3rd cheapest of 361 $290 a month | No published price | 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 | 341st of 360, with limits $939 a month | No published price | 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 Beam ranks 13th and boat ranks 10th; Instabox's 5-machine cap limits how many evals run at the same time. | 13th cheapest of 364 $251 a month | No published price | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build Android apps or VM images need /dev/kvm, which boat exposes and neither Beam nor Instabox documents. | 12th cheapest of 377 $171 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB All three work as a cloud dev box: a Beam VM keeps its root disk while stopped, Instabox adds SSH with mosh, and boat saves the disk every minute. | 13th cheapest of 368 $21 a month | No published price | 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 Beam has no desktop or browser product; Instabox has a Linux desktop with a browser and a click API, and boat streams a desktop at 60fps with Chromium and a computer-use agent. | 111th of 369, with limits $237 a month | No published price | 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 | 195th of 367, with limits $176 a month | No published price | 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 | 200th of 346, with limits $131 a month | No published price | 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 | 42nd of 338, with limits $923 a month | No published price | 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 | 175th of 360, with limits $155 a month | No published price | 2nd cheapest of 360 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month Beam ranks 1st, with GPUs from RTX 4090 to H100 and B200; Instabox lists no GPUs and boat is CPU only. | Cheapest of 98 $458 a month | No published price | 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 | No published price | Can't run it |
Key features
| Feature | Beam | Instabox | boat |
|---|---|---|---|
| Isolation | gVisor container by default for sandboxes; separate Beam VMs are CPU microVMs with their own kernel | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine sizes | You request CPU cores and RAM per sandbox; the maximum size is not published | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused | Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above |
| GPUs | GPU sandboxes and serverless GPUs up to H100, H200 and B200 | None listed | No, CPU only |
| Docker and systemd | Docker inside sandboxes with docker_enabled; systemd only in Beam VMs, not in sandboxes | Docker and Docker Compose run inside; systemd not documented | Docker, systemd and root, like a normal Ubuntu server |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Stopping and pausing | A sandbox ends with its time to live (10 minutes by default) unless you save an image or use a volume; a Beam VM keeps a 50 GiB root disk while stopped | Pause keeps memory and running programs, and resume usually takes about a second; machines pause after 30 idle minutes unless you turn that off | Disk is saved every minute and on stop, and a stopped sandbox keeps it for free |
| Fork and snapshots | Memory snapshot of a running sandbox with its processes, restored into new sandboxes | Fork copies a stopped machine only; up to 10 snapshots, and saving stops a running machine first unless the server allows a live save | Fork a running sandbox with its disk, plus named snapshots of running sandboxes |
| Public port URLs | HTTPS URL per exposed port, public with no built-in auth; no raw TCP or dedicated IP | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS on up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Outbound rules | Block all outbound traffic, or allow up to 10 CIDR ranges, changeable while running | Not documented | Open internet, no provider-side allowlist |
| Desktop and computer use | No desktop or browser product | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model | 60fps Linux desktop with Chromium and a computer-use agent |
| Coding agents | None preinstalled; you install and run them through process exec | Templates and saved agent sign-ins in snapshots; you run the agent yourself | Seven agents preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets are exposed as environment variables inside the sandbox | Vault writes your secrets into each machine as environment variables or files | Credentials proxy: real keys never enter the sandbox, for model providers and any HTTPS API |
| Regions | US only; no other region is listed | Not published | EU only (Germany, Finland, France) |
| Access and price | Open source runtime you can self-host; Developer is pay as you go, Team is $89 a month plus usage | Invite-only beta, free for now with 5 machines per user; no published price | Plans from $20 a month, and the whole fee is usage credit |
Every feature Battleships tracks (43)
| Feature | Beam | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | No | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | Yes | 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 | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Not published | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Not published | Yes |
| Agent harness API | No | Not published | Yes |
| MCP server | Yes | Not published | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | Not published | No |
| Self-hosting | Yes | Not published | No |
| BYOC | Yes | Not published | No |
| Open source | Yes | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | No | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | Yes | Not published | No |
| EU data residency | Not published | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Beam or Instabox: neither has a result on the StarSling hpc-sandbox-benchmarks CPU test, so this page makes no speed claim between them. boat did 26.69 runs per second on that test at 4 vCPU / 8 GB. Beam's guide says its sandboxes cold-boot in 1 to 3 seconds, and Instabox says a new machine's shell is ready in under a second; neither has been measured here.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Beam and Instabox have 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 | Beam, a month | Instabox, 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 | $5 · Developer | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $22 · Developer | No published price | $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 | $410 · Team | No published price | $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 | $191 · Team | No published price | $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 | $259 · Team | No published price | $2,000 · $2000/mo · with limits |
Beam: Beam sandboxes bill per second for each CPU core (one core is two vCPU) and each GiB of RAM until you terminate them or their time to live ends, so an idle tail is billed too. Developer has no fee, Team costs $89 a month plus usage with no usage credit, and there are no egress fees.
Instabox: Instabox is free during the beta ("Free until we figure it out"), with 5 machines per user. It publishes no price or rate, so no bill can be compared yet.
Instabox: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Instabox publishes no rate, so none of the scenarios can be priced for it, and its 5 machines per account (paused and stopped ones count) rule out the 50-agent and user-sandbox scenarios today. Each Instabox machine is 4 vCPU / 8 GiB with 20 GB of storage. Beam's Developer plan allows 30 CPU containers at once, so 50 parallel agents need Team, and Beam publishes no disk price beyond what a VM includes. boat fits every scenario except the burst of 1,000 short jobs, where its $2,000 plan queues starts.
| Scenario | Beam | Instabox | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Beam when
your agents need GPUs, when you want short sandboxes that bill per second and lock down outbound traffic, or when you must self-host.
- GPUs in the same platform. For work that needs a GPU, Beam offers GPU sandboxes and serverless GPUs from RTX 4090 to H100, H200 and B200.
- Locked-down, short-lived sandboxes. For short jobs, sandboxes bill per second, end on their own, and can be limited to 10 outbound CIDR ranges.
- Open source and your own cloud. Its Beta9 runtime is AGPL-3.0 and free to self-host, and it can run in your own cloud for a fee.
Use Instabox when
you want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with memory pause and SSH over mosh.
- A microVM for every machine. Each machine is a Firecracker microVM with its own kernel and root, where Beam sandboxes are gVisor containers by default.
- Pause with memory. A paused machine keeps its memory and running programs and usually resumes in about a second.
- Free during the beta. For trying things out, every account can run 5 machines of 4 vCPU / 8 GiB for free while the beta lasts.
Where boat fits
If your agents do real work over hours, such as installs, builds, Docker, emulators and a browser, look at boat. It gives each agent a full VM with /dev/kvm, private port URLs and keys kept outside the machine, and neither Beam nor Instabox documents any of these today.
A full VM with /dev/kvm and systemd
Beam sandboxes are gVisor containers without systemd, and Instabox does not document systemd. Neither documents /dev/kvm, so an agent that starts an Android emulator or a nested VM has nowhere to run it.
Port URLs that are private by default
On both Beam and Instabox a port URL is open to anyone who has it, so you must put your own login in front of every preview. boat URLs carry a token by default, and boat adds raw TCP.
Keys that never enter the machine
Beam puts secrets in environment variables and Instabox writes them into each machine, where one prompt injection can leak them. boat's credentials proxy keeps real keys outside, for model providers and any HTTPS API.
Use boat when your agents need a full VM with /dev/kvm, private port URLs, keys kept outside the machine, or more than five machines on terms published today. Compare it one to one: boat vs Beam and boat vs Instabox.
Questions people ask
Is Beam cheaper than Instabox?
It can't be compared yet. Instabox is free during its beta and publishes no price, so there is no bill to set against Beam's. Beam's price for each scenario, such as $22 a month for one agent that never stops, is in the table above.
Which is faster, Beam or Instabox?
Neither has been measured on the same CPU test, so we can't say. Beam says its sandboxes cold-boot in 1 to 3 seconds, and Instabox says a new machine's shell is ready in under a second. boat did 26.69 runs per second on the hpc-sandbox-benchmarks test.
Is a Beam sandbox a VM like an Instabox machine?
Not by default. Beam sandboxes are gVisor containers, and Beam sells separate CPU VMs with their own kernel. Each Instabox machine is a Firecracker microVM, and each boat sandbox is a full VM with /dev/kvm.
Can Beam and Instabox run Docker?
Yes. Beam runs Docker inside a sandbox with docker_enabled, and Instabox runs Docker and Docker Compose inside each machine. boat runs Docker too, with systemd and /dev/kvm.
Do Beam or Instabox have GPUs?
Beam does, from RTX 4090 up to H100, H200 and B200. Instabox lists no GPUs, and boat is CPU only, so pick Beam for GPU work.
Can I use Instabox today?
Only with an invite. It launched on 2026-10-14 as an invite-only beta, with sign-in through GitHub or Google, and every machine is 4 vCPU / 8 GiB.
Try boat
Install the CLI, then run boat new.
7-day free trial