Freestyle vs Ona
Freestyle is a VM service you drive from code: each agent or user gets a full Linux VM that can pause with its memory, fork and wake on the next request. Ona, formerly Gitpod and now part of OpenAI, is a cloud dev environment platform for engineers and its Codex agent. Since Ona Cloud shut down on October 31, 2026, Ona sells only Enterprise, through sales, on runners in your own cloud 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 a base snapshot. The default Ubuntu image has systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request. Every VM starts behind a default-deny firewall. You drive it from a TypeScript SDK, a CLI or an API.
Ona
Ona, formerly Gitpod, is a platform for cloud dev environments and background coding agents, and is now part of OpenAI.
Ona is a different kind of product from boat: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config. People open it in a browser IDE, VS Code or JetBrains, and Ona's Codex Agent can plan, code, test and open pull requests in it. Ona has a built-in web browser that its AI can drive, prebuilds and Enterprise warm pools. It is built for engineering teams who want the same governed environment for every developer and agent. Since Ona Cloud shut down on October 31, 2026, every customer runs it in their own AWS or GCP account on an Enterprise contract.
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. “31st cheapest of 365” means 30 of the other 364 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 | Ona: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Freestyle fits with Docker, systemd and KVM in a full VM (20th). Ona is a compromise (194th): it sells only Enterprise through sales, documents no nested virtualization, and its built-in browser is not a full desktop. boat ranks 8th. | 31st cheapest of 365 $3,311 a month | 334th of 365, with limits $7,315 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Freestyle fits an always-on assistant (26th) and has no idle timeout unless you set one. On Ona an always-on assistant needs auto-stop set to Never, because background work does not count as activity (93rd, compromise). boat ranks 5th. | 49th cheapest of 361 $4,195 a month | 147th of 361, with limits $8,504 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Freestyle fits short code runs (38th), with VMs that pause with their memory and wake on the next request. Ona starts each environment from a Dev Container config, prebuild or warm pool (204th, compromise). boat's start limits make big bursts a compromise (130th). | 46th cheapest of 336 $482 a month | 326th of 336, with limits $5,320 a month | 189th of 336, 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 is built to give each of your users a VM (21st). Ona is built for your own engineers, and its per-user policy defaults to 10 running environments (193rd, compromise). boat ranks 2nd. | 26th cheapest of 349 $1,358 a month | 325th of 349, with limits $5,988 a month | 3rd cheapest of 349 $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, but Pro allows 400 VMs at once (78th, compromise). Ona cannot copy an environment (169th, compromise). boat's start limits cap the burst (29th, compromise). | 116th of 349, with limits $6,600 a month | 277th of 349, with limits $9,773 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 68th cheapest of 359 $1,046 a month | 332nd of 359, with limits $5,768 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Freestyle's docs send sustained heavy CPU work elsewhere (119th, compromise). Ona has no fork, so each run starts from a prebuild or an Enterprise warm pool (207th, compromise). boat ranks 2nd. | 169th of 374, with limits $625 a month | 366th of 374, with limits $5,461 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Freestyle is a VM you reach over SSH or HTTPS and fits (68th). Ona is a full cloud IDE with Dev Containers and prebuilds, sold only as Enterprise (211th, compromise). boat ranks 13th and adds a desktop. | 102nd cheapest of 371 $151 a month | 371st of 371, with limits $5,140 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Freestyle fits (26th) with guides that install a desktop and noVNC. Ona's AI can drive a built-in browser, but there is no full desktop for other apps (206th, compromise). boat ranks 8th with a 60 fps desktop with Chrome. | 51st cheapest of 367 $940 a month | 355th of 367, with limits $5,691 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 99th of 356, with limits $482 a month | 219th of 356, with limits $5,346 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 110th cheapest of 343 $482 a month | 220th of 343, with limits $5,468 a month | 6th cheapest of 343 $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 327, with limits $6,560 a month | 261st of 327, with limits $14,360 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 28th cheapest of 351 $482 a month | 150th of 351, with limits $5,228 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Freestyle | Ona | boat |
|---|---|---|---|
| What it is | A VM service for AI agents, driven from a TypeScript SDK, a CLI or an API | A cloud dev environment platform for engineers and its Codex agent | A sandbox API: full VMs for agents, with a desktop and coding agents built in |
| Isolation | Full KVM VM with its own kernel on bare metal; Freestyle says it oversubscribes host resources | An isolated VM with dedicated compute per environment, built from a Dev Container config | Full VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared |
| Docker and nested virtualization | Yes; systemd is pid 1, Docker runs from boot, full KVM support | Docker and root inside the Dev Container; nested virtualization is not documented | Docker, root, systemd and /dev/kvm on every sandbox |
| CPU speed (V8 Web Tooling Benchmark, 4 vCPU / 8 GB, StarSling run of 3 October 2026) | 10.22 runs/s, 14th of 15 | Not in the public benchmarks we use | 28.06 runs/s, 2nd of 15 (shared rank), on an AMD Ryzen 9 9950X host |
| Pause and resume | Pause saves memory and disk; a paused VM can wake on the next request | The disk persists across stops and stays on your cloud bill; stops after 30 idle minutes by default; archived after 3 days stopped by default | Disk saved every minute and at each stop; a resume is like a reboot; disk kept at least 14 days |
| Fork | Clone a running VM without pausing it; snapshots capture memory and disk | No environment copy; Enterprise warm pools start a new environment in about 10 seconds | Fork a running sandbox from its last 1-minute disk snapshot |
| Desktop, browser and computer use | You set it up: official guides install GNOME or headed Chromium with TigerVNC and noVNC | Browser IDE plus VS Code and JetBrains; a built-in web browser that Ona's AI can drive; no full graphical desktop for other apps | Linux desktop and Chrome at 1920x1080 and 60 fps, with computer tools for agents, preinstalled |
| Coding agents | claude, codex, opencode and openclaw preinstalled, driven through exec or a terminal | Managed Codex Agent started from chat, Slack, a pull request, a Linear issue or an automation; you install Claude Code yourself | Seven agents preinstalled, with a prompt, steer and events API |
| Driving it from code | SDK, CLI and API on every plan, from Free up | Python, TypeScript and Go SDK and a CLI on Enterprise, Ona's only plan, sold through sales | API, SDK and CLI on every plan, self-serve from $20 a month, including the trial |
| Keeping keys out of the sandbox | Credentials injected at the edge for HTTPS headers, Postgres and S3; the VM must trust the Freestyle CA | Secrets are injected as environment variables or files; OIDC can swap them for short-lived cloud credentials | Optional AI credentials proxy ($1 a day when on, plus $1 per 1,000 requests); other secrets still enter the sandbox |
| Reaching the sandbox | HTTPS on free style.dev names or your own domain, forward auth, firewall ingress rules, a public IPv6 per VM | HTTPS URL per port for you, your organization or everyone; SSH; no raw TCP documented | Up to 50 HTTPS URLs, token-gated by default; SSH; raw ports over IPv6 on sandboxes with no IPv4 of their own |
| Outbound rules | Default-deny firewall with allow rules by IP, VM, VPC or exact domain | Runs in your own cloud account, so your own network rules apply | Open internet; no provider-side allowlist |
| GPUs | Private GPU sandboxes on Enterprise; no type or price published | GPU instance types on Enterprise runners in your own cloud, such as one NVIDIA A10G with 16 vCPU and 64 GB | None |
| Regions and deployment | Regions are not published | Enterprise runners in your own AWS or GCP account, in a region you choose | Germany, Finland and France; no region choice, no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Freestyle | Ona | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | No documented way | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | With your own setup | No documented way | Yes |
| Browser | With your own setup | Yes | Yes |
| Computer-use API | With your own setup | No documented way | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No documented way | Yes |
| Fork/clone | Yes | No documented way | Yes |
| Live fork (no pause) | Yes | No documented way | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | No documented way | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Yes | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | Yes | No documented way | Yes |
| Secret proxy for any API | Yes | No documented way | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | No documented way | No documented way | No documented way |
| GPU | Yes | Yes | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | No documented way | Yes | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No documented way | No documented way | Yes |
| Audit logs | Yes | No documented way | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Not published | Yes | No documented way |
| HIPAA | Not published | No documented way | No documented way |
| EU data residency | Not published | Yes | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's run of 3 October 2026 (run 37073680030), on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, boat did 28.06 runs/s (2nd of 15, shared rank) and Freestyle 10.22 (14th). Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host; boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Providers ran on different hardware in different regions. Ona is not in the public benchmarks we use, so we cannot say how it compares. ComputeSDK measured Freestyle at a 2.0 s median with 100 starts at once (2026-11-06); Freestyle advertises about 65 ms per VM.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Ona is not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | Freestyle, a month | Ona, 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 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $159 · Free | $5,140 · Enterprise (AWS Marketplace 12-month contract) · 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 | $2,139 · Pro | $6,521 · Enterprise (AWS Marketplace 12-month contract) · 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 | $581 · Pro | $5,432 · Enterprise (AWS Marketplace 12-month contract) · 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 | $1,305 · Pro · with limits | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | $8,800 · $2000/mo · with limits |
Freestyle: Freestyle bills per second for the vCPU ($0.04032 an hour), RAM ($0.0129 per GiB-hour) and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. On Free those allowances are hard stops and no card is needed. Hobby and Pro set a $50 or $500 monthly minimum that counts as usage, and a paused VM bills only for storage.
Ona: Ona Cloud and Core shut down on October 31, 2026, so the Ona prices here use its Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract (about $5,000 a month), plus compute on your own cloud bill. Real Enterprise prices are negotiated with sales.
Ona: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge and keeps its disk at least 14 days; saved snapshots above the included count and the AI credentials proxy still charge. The $20 plan includes 200 starts a day; extra starts cost $0.03 to $0.07. A card is required, also for the 7-day trial.
Limits in those scenarios
No Ona scenario fits as published, because Ona sells only Enterprise, through sales. Ona publishes no Enterprise concurrency limit, so the rankings assume 3 environments at once. Freestyle has no idle timeout by default, so a VM bills until you pause it, and Pro allows 400 VMs at once, so 1,000 short jobs at once need Enterprise. Ona stops an environment after 30 idle minutes unless auto-stop is set to Never. boat's auto-stop defaults to 1 hour. Its $2,000 plan includes 90 starts a minute and 2,400 a day, bills extra starts at $0.03 to $0.07, and refuses starts above 270 a minute with 429, so that burst does not fit boat either.
| Scenario | Freestyle | Ona | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario |
| None for this scenario |
| One agent that never stops | None for this scenario |
| None for this scenario |
| 50 agents in parallel | None for this scenario |
| None for this scenario |
| Sandboxes for your users | None for this scenario |
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Freestyle when
your code gives each agent or user its own VM that sleeps between requests and must resume with its memory, or when you need a default-deny firewall per VM.
- Memory pause, live fork and wake on request. Useful for VMs that sleep between requests: they resume the same processes and can wake on the next incoming traffic.
- Self-serve, built for code. Useful if your product starts a VM per agent or per user: there is a free plan with no card and an SDK on every plan.
- Network controls. Every VM starts with no network access, and you allow exactly the IPs, VMs, VPCs or domains it may reach.
Use Ona when
your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account, or with a GPU.
- A full cloud IDE for your team. Useful if your engineers work in the same environments as their agents: browser, VS Code and JetBrains IDEs with Dev Containers, prebuilds and warm pools.
- Runs in your own cloud. Useful if environments must run inside your own AWS or GCP account: Ona's Enterprise runners do that, in many regions.
- GPU environments. Useful if your agents need a GPU: Enterprise runners can use GPU instance types, such as an A10G VM with 16 vCPU and 64 GB.
Where boat fits
If you are comparing Freestyle and Ona because your code starts agents that do real work for hours, look at boat too. It gives each agent a full VM with /dev/kvm, a desktop for computer use, and an API to drive the coding agents inside, on self-serve plans from $20 a month. It runs only in the EU, has no GPU and limits starts per plan.
More CPU work in one public run
In StarSling's run of 3 October 2026 (run 37073680030), the V8 Web Tooling Benchmark at 4 vCPU / 8 GB gave boat 28.06 runs/s and Freestyle 10.22, about 2.7 times the work. That boat sandbox ran on a Ryzen 9 9950X host; boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Ona is not in that benchmark.
A desktop and a browser, ready
On Freestyle you install a desktop, VNC and Chromium from its guides and build the click layer. Ona's AI drives a built-in browser, with no full desktop for other apps. boat streams a 60 fps desktop with Chrome and computer tools.
Agents you drive from outside
On Freestyle you start agent CLIs through exec and parse their output. Ona manages Codex, and its SDK needs an Enterprise contract. boat has a prompt, steer and events API for seven agents, and an optional credentials proxy ($1 a day when on, plus $1 per 1,000 requests).
Use boat when your agents do real work for hours: builds, tests, Docker, emulators, a desktop and a browser, on a VM that saves its disk with no code, with an API to drive the agents inside from outside. Compare it one to one: boat vs Freestyle and boat vs Ona.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is Freestyle cheaper than Ona?
In every scenario we priced, yes, using Ona's Enterprise listing on AWS Marketplace, since Ona sells only Enterprise. One 4 vCPU / 8 GB dev box running all month is $151 on Freestyle and $5,140 on Ona. 50 always-on assistants come to $4,195 against $8,504. On boat those are $26 and $657. Ona's real Enterprise price is a sales quote, so yours may differ.
Which is faster, Freestyle or Ona?
Ona is not in the public benchmarks we use, so we cannot say. In StarSling's run of 3 October 2026 at 4 vCPU / 8 GB, Freestyle did 10.22 V8 Web Tooling runs/s and boat 28.06, on a Ryzen 9 9950X host. boat does not promise a CPU model.
Can Freestyle and Ona run Docker?
Yes. Freestyle VMs run systemd as pid 1 with Docker from boot and full KVM support, so Android emulators work too. Ona runs Docker inside the Dev Container, but nested virtualization is not documented. boat has Docker and /dev/kvm on every sandbox.
Is Ona the same as Gitpod?
Yes. Gitpod renamed itself Ona in 2025 and moved from cloud dev environments to background coding agents, and Ona is now part of OpenAI. Its hosted service, Ona Cloud, shut down on October 31, 2026.
Can I sign up for Ona or Freestyle today?
Freestyle is self-serve, with Free, Hobby and Pro plans plus Enterprise. Ona sells only Enterprise, through sales. boat's plans are self-serve, from a 7-day trial (card required) up.
Can either run a computer-use agent?
Freestyle can, once you install a desktop, VNC and Chromium inside the VM from its guides. Ona's AI can drive a built-in web browser, but there is no full desktop for other apps. boat ships a 60 fps desktop, Chrome and computer tools in every sandbox.
Try boat
Install the CLI, then run boat new.
7-day free trial