Ona vs Instabox
Ona, formerly Gitpod and now part of OpenAI, gives engineering teams cloud dev environments shared with its Codex agent, and new customers buy it through sales. Instabox launched on 2026-10-14 as a free, invite-only beta that gives each AI agent its own small Linux VM.
The companies and products
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, which people open in a browser IDE, VS Code or JetBrains, and where Ona's Codex Agent can plan, code, test and open pull requests. It is built for engineering teams who want the same governed environment for every developer and agent; new customers run it in their own AWS or GCP account on an Enterprise contract.
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. “324th cheapest of 367” means 323 of the other 366 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 | Ona: 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 Neither Ona nor Instabox can copy a running machine: Ona has no environment copy and Instabox forks only stopped machines, while boat forks a running sandbox. | 324th of 367, with limits $7,315 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 stop idle machines after 30 minutes by default: Ona stops the VM and Instabox pauses it with its memory; both let you turn that off. | 83rd of 366, with limits $8,504 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 | 335th of 345, with limits $5,320 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 Ona is built for your own engineers, and Instabox allows 5 machines per account counting paused and stopped ones, so neither hands a sandbox to each of many users today. | 330th of 361, with limits $5,988 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 | 283rd of 360, with limits $9,773 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 Instabox's 5-machine cap limits how many evals run at once, and Ona's SDK for starting environments from code is on the Enterprise plan only. | 334th of 364, with limits $5,768 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 Ona nor Instabox documents. | 365th of 377, with limits $5,461 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is the fuller dev box, with a browser IDE, VS Code, JetBrains and Dev Containers; Instabox adds mosh and paste-anywhere SSH tokens; boat is a full VM over SSH, HTTPS or a desktop. | 368th of 368, with limits $5,140 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 Ona environments have no graphical desktop; Instabox has a Linux desktop with screenshot and click control, and boat streams a 60fps desktop with a computer-use agent. | 353rd of 369, with limits $5,691 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 | 150th of 367, with limits $5,346 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 | 146th of 346, with limits $5,468 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 | 261st of 338, with limits $14,360 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 boat can fork one prepared machine into many while it runs; Ona starts each environment from a config or prebuild, and Instabox has 5 machines per account. | 93rd of 360, with limits $5,228 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 | Ona | Instabox | boat |
|---|---|---|---|
| Isolation | An isolated VM per environment, built from a Dev Container config | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Buying it | New Core subscriptions are closed; new customers buy Enterprise through sales | Invite-only beta, free during the beta, sign in with GitHub or Google | Self-serve plans from a free trial up, starting at $20 a month |
| Machine sizes | Many VM classes in your own cloud, including GPU instance types | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage | Several sizes, up to 16 vCPU / 32 GB on $100 plans and above |
| Docker | Docker and root inside the Dev Container | Docker and Docker Compose run inside | Docker and Compose, with root and systemd |
| Nested virtualization | Not documented | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Fork and snapshots | No environment copy; prebuilds snapshot the filesystem on a schedule | Fork copies a stopped machine only; up to 10 snapshots, saved by hand | Fork a running sandbox; disk saved every minute and on stop |
| Stop and resume | The disk persists across stops; in your own cloud it stays on your bill | Pause keeps memory and running programs; resume usually takes about a second | Stop keeps the disk and costs nothing; start boots the machine again |
| Driving it from code | Python, TypeScript and Go SDK on the Enterprise plan only | CLI, TypeScript SDK and HTTP API | API and SDK on every plan, including the trial |
| Desktop and computer use | Browser IDE, VS Code and JetBrains; no graphical desktop | Linux desktop with a browser on one template, screenshot and click API | 60fps Linux desktop with Chromium and a computer-use agent |
| Coding agents | Codex Agent managed for you; Claude Code you run yourself | Templates and saved agent sign-ins in snapshots; you run the agent | Seven agents preinstalled, with a prompt, steer and events API |
| Port URLs | HTTPS URL per port for you, your organization or everyone; no raw TCP | HTTPS on up to 16 ports, open to anyone with the URL | HTTPS on up to 50 ports, token-protected by default; raw TCP too |
| SSH | SSH, used by VS Code and JetBrains | SSH gateway with short-lived certificates, SSH tokens and mosh | SSH into every sandbox |
| Keeping API keys out | Secrets injected as environment variables or files | Vault writes secrets into each machine as environment variables or files | Credentials proxy: real keys never enter the sandbox, for any HTTPS API |
| Regions | Your own AWS or GCP account, in many regions | Not published | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Ona | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | No | Yes | Yes |
| Live fork (no pause) | No | No | Yes |
| Memory fork | No | 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 | No | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Not published | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | Yes | 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 | Yes | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Yes | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | No | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | No | Not published | No |
| EU data residency | Yes | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Ona or Instabox: neither was in the public benchmark runs we use, so this page makes no speed claim between them. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run of 2026-09-29. Instabox says you are in a new machine's shell in under a second; that has not been measured.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Ona 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 | Ona, 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 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $5,140 · Enterprise (AWS Marketplace 12-month contract) · with limits | 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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · with limits | 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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · with limits | 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | No published price | $2,000 · $2000/mo · with limits |
Ona: New Core subscriptions are closed, 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 AWS bill. Real Enterprise prices are negotiated with sales.
Instabox: Instabox is free during the beta ("Free until we figure it out"), with 5 free machines per user, and publishes no price yet, so no bill can be compared with Ona or boat.
Instabox: Plans start at $20 a month, and the whole fee is usage credit spent per second while sandboxes run. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
No Ona scenario fits as published, because a new customer can only buy Enterprise through sales, and the table assumes 3 environments at once since Ona publishes no Enterprise limit. Instabox has no published per-resource rate, so no scenario can be priced, and its 5 machines per account, paused and stopped ones included, rule out 50 agents or 300 user sandboxes today. Every Instabox machine is 4 vCPU / 8 GiB, and an API exec call runs at most 10 minutes, 4 at once. boat fits every scenario but the 1,000-job burst, which needs more starts per hour and per day than its $2,000 plan allows.
| Scenario | Ona | 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 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 engineers share environments with agents: Ona has browser, VS Code and JetBrains IDEs, Dev Containers and prebuilds.
- Runs in your own cloud. Useful if machines 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: Ona's Enterprise runners can use GPU instance types, such as one NVIDIA A10G.
Use Instabox when
you have an invite and want to try a few free 4 vCPU / 8 GiB agent machines during its beta, with memory pause and mosh.
- Free to try during the beta. Useful if you have an invite and want to try things: each account gets 5 machines of 4 vCPU / 8 GiB for free.
- Pause with memory. A paused Instabox machine keeps its memory and running programs, and usually resumes in about a second.
- SSH gateway with mosh. Its SSH gateway relays mosh and gives paste-anywhere SSH tokens, so a terminal survives sleep and network changes.
Where boat fits
If your own code starts and drives the agents, look at boat. Ona is built for engineers and is sold through sales, and Instabox is a small free beta with one machine size and 5 machines per account. boat gives every agent a full VM with an API on every plan, published terms and room for a fleet.
Fork work while it runs
Ona has no way to copy an environment, so each parallel attempt rebuilds from a prebuild. Instabox forks only a stopped machine, which ends its running programs. boat forks a running sandbox and the original keeps working.
The whole machine, with private ports
Neither Ona nor Instabox documents /dev/kvm, Ona has no desktop or raw TCP, and Instabox port URLs are open to anyone. boat has /dev/kvm, a 60fps desktop, raw TCP and token-protected URLs on 50 ports.
Room for a fleet, driven from code
Ona's SDK needs an Enterprise contract, and Instabox stops at 5 machines of one size. boat has its API on every plan, sizes up to 16 vCPU / 32 GB, coding agents preinstalled and a proxy that keeps API keys out.
Use boat when your code starts and drives the agents: full VMs with /dev/kvm, a desktop and private port URLs, an API on every plan, forks of running work and published terms. Compare it one to one: boat vs Ona and boat vs Instabox.
Questions people ask
Is Ona 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 Ona's. New Ona customers buy Enterprise through sales; its AWS Marketplace listing is a 12-month, $60,000 contract, plus compute on your own cloud bill.
Which is faster, Ona or Instabox?
Neither has a comparable CPU measurement, so we make no speed claim between them. Instabox says a new machine's shell is ready in under a second, which has not been measured. boat did 26.69 runs per second on the same benchmark at 4 vCPU / 8 GB.
Can Ona and Instabox run Docker?
Yes. Ona runs Docker with root inside the Dev Container, and Instabox runs Docker and Docker Compose inside its microVM. Neither documents nested virtualization (/dev/kvm), which boat has on every machine.
Can I sign up for Ona or Instabox today?
Instabox is an invite-only beta: you sign in with GitHub or Google and need an invite. Ona's billing docs say new Core subscriptions are no longer available, so new customers go through sales. boat's plans are self-serve, from a free trial up.
Is Ona the same as Gitpod?
Yes. Gitpod renamed itself Ona in 2025 and moved toward background coding agents, and Ona is now part of OpenAI. Its managed agent is Codex.
Are Instabox port URLs private?
No. Its docs say a published URL is not a secret, and anyone can reach the service until you unpublish it. Ona lets you share a port with yourself, your organization or everyone, and boat's port URLs carry a token by default.
Try boat
Install the CLI, then run boat new.
7-day free trial