Freestyle vs Instabox
Both give each agent its own Linux VM with root and Docker. Freestyle is an established service with published plans, live forks, memory pause and machines up to 32 vCPU, while Instabox launched today as a free invite-only beta with one 4 vCPU / 8 GiB size and 5 machines per account.
The companies and products
Freestyle
Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.
Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.
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. “40th cheapest of 345” means 39 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 | Freestyle: 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 Freestyle offers bigger machines and live forks of a set-up VM, while Instabox has one 4 vCPU size and forks only stopped machines; boat adds faster CPUs and forks running sandboxes. | 241st of 367, with limits $3,311 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both can keep a machine running with no session cap; Instabox pauses after 30 idle minutes unless you turn that off, and Freestyle bills until you pause it. | 263rd of 366, with limits $4,195 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 Freestyle suits short code runs: a VM pauses with its memory and wakes on the next request, which Instabox does not do. | 40th cheapest of 345 $482 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 Freestyle Pro allows 400 VMs at once, while Instabox allows 5 machines per account, paused and stopped ones included. | 16th cheapest of 361 $1,358 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 Freestyle can snapshot a running VM with its memory and boot copies from it; Instabox snapshots and forks are disk-only and need a stopped machine. | 107th of 360, with limits $6,600 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 | 53rd cheapest of 364 $1,046 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 Freestyle offers nested virtualization for builds that need /dev/kvm, Instabox does not document it, and boat exposes /dev/kvm on CPUs that measured 2.8 times faster than Freestyle's. | 168th of 377, with limits $625 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both work as a cloud dev box; Instabox adds an SSH gateway with mosh, and Freestyle has published plans you can plan around. | 98th cheapest of 368 $151 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 Instabox has a desktop template with screenshot and click control; on Freestyle you install the desktop and VNC yourself, and boat streams a desktop at 60fps with computer use built in. | 234th of 369, with limits $940 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 | 257th of 367, with limits $482 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 | 278th of 346, with limits $482 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 | 183rd of 338, with limits $6,560 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 | 272nd of 360, with limits $482 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 | Can't run it | 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 | Freestyle | Instabox | boat |
|---|---|---|---|
| Isolation | Full KVM VM with its 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 | Up to 4 vCPU / 8 GiB on Free, 8 / 16 on Hobby, 32 / 64 on Pro, 64 / 128 with custom limits | 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 |
| CPU benchmark (4 vCPU / 8 GB) | 9.64 runs/s | Not measured | 26.69 runs/s |
| Root and Docker | Yes; systemd is pid 1 and Docker runs from boot | Root, Docker and Docker Compose run inside | Yes, with root, systemd, Docker and Compose |
| Nested virtualization | Yes, full KVM support | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Pause and wake | Pause keeps memory and disk; a paused VM wakes on the next request | Pause keeps memory and running programs; a visit does not wake a paused machine | Disk saved every minute and on stop; start boots the machine again |
| Fork | Clone a running VM without pausing it; snapshots capture memory and disk | Fork copies a stopped machine only; snapshots are disk-only | Fork a running sandbox with its disk |
| Machines at once | 10 on Free, 40 on Hobby, 400 on Pro | 5 per account, paused and stopped ones included | No session cap on paid plans; starts per minute, hour and day are capped by plan |
| Desktop and computer use | Guides to install GNOME or Xvfb, VNC and Chromium yourself | Linux desktop with a browser on one template, screenshot and click API, shareable view or control links; you bring the model | Linux desktop streamed at 60fps, Chromium and computer use built in |
| Coding agents | claude, codex, opencode and openclaw preinstalled, driven through exec or a terminal | 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 | Credentials injected at the edge for HTTPS headers, Postgres and S3; the VM must trust the Freestyle CA | Vault writes your secrets into each machine as environment variables or files | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Inbound access | HTTPS on free style.dev names or your own domain, forward auth, other public protocols | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP |
| Outbound rules | Default-deny firewall with allow rules by IP, VM, VPC or exact domain | Not documented | Open internet, no provider-side allowlist |
| Regions and data | Not listed; the docs name a San Jose, US data center | Not published | EU only (Germany, Finland, France), zero data retention |
Every feature Battleships tracks (43)
| Feature | Freestyle | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | 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 | Yes | Yes | Yes |
| Automatic snapshots | Yes | 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 | Yes | Yes | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Yes | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Not published | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | No | Not published | Yes |
| MCP server | No | Not published | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | No | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Not published | Not published | No |
| HIPAA | Not published | Not published | No |
| EU data residency | No | Not published | 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, Freestyle did 9.64 runs per second and boat did 26.69, about 2.8 times as much CPU work. Instabox has no comparable measurement, so this page makes no speed claim for it. Instabox says a new machine's shell is ready in under a second and Freestyle advertises VM starts in about 65 ms; neither start time was measured here.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Instabox 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 | Freestyle, 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 | $27 · Free | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $159 · Free | 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 | $2,139 · Pro | 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 | $581 · Pro | 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 | $1,305 · Pro · with limits | No published price | $2,000 · $2000/mo · with limits |
Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances. On Free those allowances are hard stops; Hobby and Pro set a $50 or $500 monthly minimum that counts as usage.
Instabox: Instabox is free during the beta, with 5 machines per user, and publishes no price yet ("Free until we figure it out"), so no bill can be compared.
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 allows 5 machines per account, paused and stopped ones included, each 4 vCPU / 8 GiB with 20 GB storage, and an API exec call runs at most 10 minutes with 4 at once. With no published rate, none of the scenarios can be priced on it. Freestyle has no idle timeout by default, its Free allowances are hard stops, and Pro's cap of 400 concurrent VMs is why 1,000 short jobs at once do not fit. boat does not fit that burst either: its start limits per hour and per day are lower than it needs.
| Scenario | Freestyle | Instabox | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| 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 |
|
|
|
Which one should you use?
Use Freestyle when
your VMs sleep between requests and must resume with their memory, when you need live forks, a default-deny firewall or machines above 4 vCPU, or when you need published plans today.
- Memory pause, live fork and wake on request. For VMs that sleep between requests: they resume the same processes, wake on the next request, and can be cloned while running.
- Bigger machines and more of them. For heavy builds or many users: Pro allows VMs up to 32 vCPU / 64 GiB and 400 running at once.
- Network controls. For teams that must limit what an agent can reach: every VM starts behind a default-deny firewall with exact allow rules.
Use Instabox when
you want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with a desktop template, memory pause and mosh.
- Free during the beta. For trying things out: each account can run 5 machines of 4 vCPU / 8 GiB for free while the beta lasts.
- A desktop template ready to use. For computer-use tests: one template has a Linux desktop with a browser, a screenshot and click API, and shareable view links.
- SSH gateway with mosh. For working in a terminal: short-lived SSH certificates, paste-anywhere SSH tokens, and mosh sessions that survive sleep and network changes.
Where boat fits
If your agents spend hours on builds, tests, a desktop and a browser, look at boat. It gives each agent a full VM with /dev/kvm on faster CPUs, a 60fps desktop with computer use, and an API to drive the agents inside from outside, with published plans today.
Almost three times the CPU speed
On the same build-and-test benchmark, boat did 26.69 runs per second and Freestyle 9.64, so every install and test takes about three times as long there. Instabox has no measured score and one 4 vCPU size.
A desktop and agents you drive from outside
On Freestyle you install the desktop, VNC and Chromium yourself; on Instabox the desktop comes on one template and you bring the model. On both you start each agent yourself, while boat has a prompt, steer and events API.
Real keys stay outside the machine
Instabox writes your secrets into each machine as files or environment variables, where an agent can read them. Freestyle injects keys at its edge but the VM must trust its CA, and swapping a key that runs out of credits is your code's job.
Use boat when your agents do real work for hours: builds, tests, Docker, emulators, a desktop and a browser, on fast CPUs, with an API to drive the agents inside from outside. Compare it one to one: boat vs Freestyle and boat vs Instabox.
Questions people ask
Is Freestyle 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 Freestyle's. Freestyle bills per second for allocated resources after monthly allowances.
Which is faster, Freestyle or Instabox?
Freestyle did 9.64 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB; Instabox has not been measured. Instabox says a new shell is ready in under a second, which was not measured either. boat did 26.69 runs per second on the same test.
Can Instabox run Docker and Android emulators?
Instabox runs Docker and Docker Compose inside each machine. Its nested virtualization is not documented, so Android emulators that need /dev/kvm may not work. Freestyle and boat both offer nested virtualization.
Can I fork a running machine?
On Freestyle, yes: it clones a running VM without pausing it, with memory and disk. Instabox forks only a stopped machine, and saving a snapshot stops a running machine first unless the server allows a live save. boat forks a running sandbox with its disk.
Is Instabox free?
Yes, for now. Its pricing page says it is free until they figure out pricing, with 5 machines of 4 vCPU and 8 GB per user. It is an invite-only beta, and no end date or later price is published.
Which one has a desktop for computer use?
Instabox has a desktop template with a browser and a screenshot and click API, and you bring the model. Freestyle has guides to install a desktop, VNC and Chromium yourself. boat streams a Linux desktop at 60fps with computer use built in.
Try boat
Install the CLI, then run boat new.
7-day free trial