Ona vs OpenAI Containers
Both now come from OpenAI, but they solve different problems. Ona gives your engineers and its Codex Agent a full dev environment that keeps its disk, sold through sales, while OpenAI Containers give a model a short-lived box to run code in during an API call.
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.
OpenAI Containers
OpenAI Containers are the sandboxes OpenAI runs for its own model tools: Code Interpreter, Hosted Shell and the Agents API's hosted sandbox.
This is a different kind of product from boat: a tool inside OpenAI's model API, not a machine you rent. You create a container through the API or let a Responses call make one, and the model runs Python or shell commands in it on a fixed Debian 12 image without sudo, until it expires after 20 minutes without use. It is built for apps that already call OpenAI models and want them to run code, read files and make charts without running any servers.
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 | OpenAI Containers: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Ona gives each agent a VM with Docker and a disk that stays, which a container that expires after 20 idle minutes cannot; boat adds /dev/kvm and an API on every plan. | 324th of 367, with limits $7,315 a month | 356th of 367, with limits $17,371 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant needs a disk that survives: Ona keeps one if auto-stop is set to Never, an OpenAI container is deleted after 20 idle minutes, and boat runs with no session cap. | 83rd of 366, with limits $8,504 a month | 341st of 366, with limits $13,140 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 OpenAI Containers are built for this: the model runs Python in the same API call, while Ona is a dev environment meant for longer work. | 335th of 345, with limits $5,320 a month | 194th of 345, with limits $6,000 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 Neither is built to hand machines to your users: Ona is for your own engineers, and OpenAI containers have no inbound access; boat gives each sandbox HTTPS URLs and SSH. | 330th of 361, with limits $5,988 a month | 361st of 361, with limits $3,780 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 | 283rd of 360, with limits $9,773 a month | 191st of 360, with limits $30,000 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 | 334th of 364, with limits $5,768 a month | 360th of 364, with limits $5,760 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 Ona runs Docker in its environments but has no fork; OpenAI documents no Docker or root, and Code Interpreter containers start with no internet. | 365th of 377, with limits $5,461 a month | 345th of 377, with limits $1,728 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is a real dev box with browser, VS Code and JetBrains IDEs; OpenAI containers have no SSH and no persistent disk, and boat is a full VM you reach over SSH or a desktop. | 368th of 368, with limits $5,140 a month | 362nd of 368, with limits $1,051 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 OpenAI has a hosted browser for the Agents API computer_use tool, Ona has no graphical desktop, and boat streams a 60fps desktop you can embed. | 353rd of 369, with limits $5,691 a month | 351st of 369, with limits $5,280 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 | 150th of 367, with limits $5,346 a month | 328th of 367, with limits $1,440 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 | 146th of 346, with limits $5,468 a month | 328th of 346, with limits $1,755 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 | 261st of 338, with limits $14,360 a month | 311th of 338, with limits $35,100 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 Neither can copy a running machine: Ona starts new environments from a config or prebuild and OpenAI containers have no fork, while boat forks a prepared sandbox while it runs. | 93rd of 360, with limits $5,228 a month | 308th of 360, with limits $870 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 | Ona | OpenAI Containers | boat |
|---|---|---|---|
| What it is | A cloud dev environment platform for engineers and the Codex Agent | A sandbox tool the model uses inside OpenAI's API | A cloud VM you create, keep, stop and drive from code |
| Isolation | An isolated VM per environment, built from a Dev Container config | A fully sandboxed virtual machine; hypervisor not named | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Root, Docker and nested virtualization | Docker and root inside the Dev Container; no nested virtualization documented | Commands do not run with sudo; no Docker or /dev/kvm documented | Root, systemd, Docker and /dev/kvm on every machine |
| Files after a stop | Disk persists across stops; Core archives a stopped environment after 3 days, and on your own cloud the disk stays on your bill | Data is discarded when the container expires; Agents API keeps only files in /workspace/outputs | Disk saved every minute and on stop; a stopped sandbox costs nothing and comes back |
| How long it runs | Stops after 30 idle minutes by default; can be set to Never | Expires after 20 minutes without use; Agents API sandboxes after an hour | No session cap on paid plans; you set the time to live |
| Fork | No environment copy; you can make a project from an environment's config | No fork | Fork a running sandbox into copies with its files |
| Starting point | Dev Container config per repo, with scheduled prebuilds | Fixed Debian 12 image; you upload files or skills into each container | Named snapshots of a set-up machine, reused as templates |
| Getting started | New customers buy Enterprise through sales; Core is closed | Pay as you go on the OpenAI API, one tool line in a request | Self-serve plans from $20 a month, with a free trial |
| Driving it from code | Python, TypeScript and Go SDK on the Enterprise plan only | Containers API and the Responses tools; Agents API (beta) for a managed Codex harness | API and SDK on every plan, including the trial |
| Coding agents | Codex Agent from chat, a Linear issue or an automation; Claude Code you run yourself | Agents API (beta) drives a managed Codex harness with steering, events and webhooks | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Reaching it from outside | HTTPS URL per port and SSH; no raw TCP or public IP documented | None; you reach the container only through the API | SSH, HTTPS URLs for up to 50 ports, raw TCP |
| Outbound internet | Open internet | Code Interpreter and Hosted Shell: off until an admin sets a domain allowlist; Agents API sandboxes open by default | Open internet on every plan |
| Keeping keys out of the sandbox | Secrets are injected as environment variables or files | domain_secrets: a sidecar adds the real header, the model sees a placeholder | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Desktop, GPUs and regions | No graphical desktop; GPU types such as an A10G on Enterprise runners in your own AWS or GCP account | Hosted browser for computer use; no GPU; US or EU processing for Code Interpreter | 60fps desktop and Chromium for computer use; no GPU; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Ona | OpenAI Containers | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | No | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | No | Yes |
| Pause/resume | Yes | No | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | No | No | Yes |
| Live fork (no pause) | No | No | Yes |
| Memory fork | No | No | No |
| Custom image (Docker or snapshot) | Yes | No | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | No | No | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | 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 | No | Yes |
| Audit logs | No | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Ona or for OpenAI Containers: neither was in the public benchmark runs we use, and OpenAI does not publish how many vCPU each container size gets. 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, on dedicated AMD Ryzen 9 9950X hosts.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Ona and OpenAI Containers 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 | OpenAI Containers, 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 | $228 · API pay as you go · with limits | $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 | $1,051 · API pay as you go · 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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · with limits | $11,405 · API 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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · with limits | $1,620 · API pay as you go · 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | $6,000 · API pay as you go · with limits | $2,000 · $2000/mo · with limits |
Ona: New Core subscriptions are closed, so the prices here use Ona's Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract, plus compute on your own AWS bill. Real Enterprise prices are negotiated with sales.
OpenAI Containers: OpenAI bills each container session by the minute for the memory size you pick, with a 5-minute minimum, and model tokens are billed on top. There is no plan fee.
OpenAI Containers: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Neither fits any of the five scenarios as published. Ona can only be bought on an Enterprise contract, and it publishes no Enterprise concurrency limit, so the table assumes 3 environments at once, as on its old free plan. OpenAI Containers have no persistent disk and no Docker, Code Interpreter and Hosted Shell start with no internet, and OpenAI publishes no limit on how many containers run at once, so 300 user sandboxes and 1,000 short jobs are unconfirmed. On boat the 1,000-job burst is limited by starts per minute and gets queued.
| Scenario | Ona | OpenAI Containers | 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, with environments that last for days, inside your own AWS or GCP account or with a GPU.
- A full cloud IDE for your team. Useful if engineers work in the same environments as their agents: browser, VS Code and JetBrains IDEs with Dev Containers and prebuilds.
- Machines that last for days. Useful if work spans days: an Ona environment keeps its disk across stops, with Docker and root inside.
- Your own cloud and GPUs. Useful if environments must run in your own AWS or GCP account, or need a GPU such as an A10G.
Use OpenAI Containers when
your app already calls OpenAI models and the model only needs to run short pieces of code or shell commands on files you give it.
- Built into the model call. Useful if your app already calls OpenAI models: one tool line in a request gives the model a place to run code.
- No contract to start. Useful if you want to try it today: containers are pay as you go by the minute, while new Ona customers go through sales.
- Locked-down network by default. Useful if code must reach only chosen hosts: Code Interpreter and Hosted Shell have no outbound access until an admin allows domains.
Where boat fits
If what you are really running is agents started by your own code, neither fits well: Ona is a team IDE whose API needs an Enterprise contract, and an OpenAI container forgets everything after 20 idle minutes. boat gives each agent a full VM that keeps its disk, with an API on every plan and any coding agent built in.
A whole machine with /dev/kvm
Android emulators and microVMs need /dev/kvm. Ona documents no nested virtualization, and OpenAI containers run without sudo or Docker, so the agent stops at the first apt install unless you host a sandbox yourself.
Work that is kept and forked
An OpenAI container discards its files when it expires, and Ona keeps them but cannot copy an environment, so parallel attempts rebuild from a prebuild. boat saves the disk every minute and forks a running sandbox.
An API, a desktop and open ports
Ona's SDK is Enterprise only and has no desktop or raw TCP; OpenAI containers accept no inbound connections at all. boat has an API on every plan, a 60fps desktop, HTTPS on 50 ports and raw TCP.
Use boat when your code starts and drives the agents: full VMs with root, Docker and /dev/kvm, a disk that is saved and forks while running, open ports, and an API on every plan. Compare it one to one: boat vs Ona and boat vs OpenAI Containers.
Questions people ask
Is Ona cheaper than OpenAI Containers?
For one agent, no: one coding agent on workdays comes to $5,030 a month on Ona's Enterprise listing and $228 on OpenAI, though OpenAI bills model tokens on top. For 50 agents in parallel it flips, at $6,521 on Ona against $11,405 on OpenAI. boat comes to $20 and $317 for the same two scenarios.
Which is faster, Ona or OpenAI Containers?
There is no comparable measurement for either one, and OpenAI does not publish the vCPU behind its container sizes. boat did 26.69 runs per second on the same Node.js build-and-test benchmark at 4 vCPU / 8 GB.
Can Ona or OpenAI Containers run Docker?
Ona runs Docker with root inside its Dev Container environments. OpenAI's hosted shell runs commands without sudo, and no Docker support is documented. boat gives every sandbox root, systemd, Docker and /dev/kvm.
Are Ona and OpenAI Containers from the same company?
Yes. Ona, formerly Gitpod, is now part of OpenAI, and its managed agent is Codex. The products are still separate: Ona is a dev environment platform sold through sales, and Containers are a tool in OpenAI's API.
Which one keeps my files?
Ona keeps an environment's disk across stops, though Core archives a stopped environment after 3 days. An OpenAI container expires after 20 minutes without use and its data is discarded. boat saves the disk every minute and on stop, and a stopped sandbox costs nothing.
Can I sign up for either today?
OpenAI Containers are pay as you go on the OpenAI API. 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.
Try boat
Install the CLI, then run boat new.
7-day free trial