OpenAI Containers vs Instabox

OpenAI Containers are a tool inside OpenAI's model API: the model runs code in a short-lived box without sudo, and the box is deleted after 20 idle minutes. Instabox, an invite-only beta that launched today, gives each agent its own Firecracker VM with root and Docker that it keeps, paused or running.

The companies and products

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.

Isolation: Each container is described as a fully sandboxed virtual machine; the hypervisor is not named
Runtime: Debian 12 with Python 3.11, Node.js 22.16, Java 17, PHP 8.2, Ruby 3.1 and Go 1.23; commands do not run with sudo
Sizes: Picked by memory: 1 GB (default), 4 GB, 16 GB or 64 GB; vCPU per size not published for Responses containers
Lifetime: A container expires after 20 minutes without use, and its data is discarded
Billing: By the minute with a 5-minute minimum per session, on top of model tokens
Regions: Code Interpreter processing in the United States or Europe; the Agents API supports data residency only in the US
Compliance: API Platform audited for SOC 2 Type 2; HIPAA BAA on request

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
Machine size: 4 vCPUs and 8 GiB of memory, the same for every machine; 20 GB storage
Machines per account: 5, in any state: paused and stopped ones count
Price: Free during the beta; no published price yet
Access: Invite-only beta; sign in with GitHub or Google
Regions: Not published; more regions are on the roadmap as an idea
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. “356th cheapest of 367” means 355 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	OpenAI Containers: 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 coding agent that installs packages and runs Docker for days needs root and a disk that stays: Instabox has both, OpenAI containers have neither, and boat adds forks of running sandboxes and bigger sizes.	356th of 367, with limits $17,371 a month	No published price	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An OpenAI container is deleted after 20 idle minutes; an Instabox machine can stay up with no session cap if you turn off its 30-minute idle pause, and boat has no session cap on paid plans.	341st of 366, with limits $13,140 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 This is what OpenAI Containers are built for: the model writes Python and runs it in the same API call, with no machine to manage.	194th of 345, with limits $6,000 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 Instabox allows 5 machines per account, paused and stopped ones included, and OpenAI containers accept no inbound connections, so neither fits sandboxes for many users today.	361st of 361, with limits $3,780 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	191st of 360, with limits $30,000 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 OpenAI does not publish how many containers can run at the same time.	360th of 364, with limits $5,760 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 need Docker and open internet: Instabox runs Docker, OpenAI documents no Docker and starts Code Interpreter containers with no internet, and only boat documents /dev/kvm for Android or VM builds.	345th of 377, with limits $1,728 a month	No published price	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Instabox works as a dev box with SSH and mosh; OpenAI containers have no SSH and no disk that survives.	362nd of 368, with limits $1,051 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 OpenAI has a hosted browser for the Agents API computer_use tool, Instabox has a Linux desktop with a screenshot and click API, and boat streams a 60fps desktop you can embed.	351st of 369, with limits $5,280 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	328th of 367, with limits $1,440 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	328th of 346, with limits $1,755 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	311th of 338, with limits $35,100 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	308th of 360, with limits $870 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	OpenAI Containers	Instabox	boat
Isolation	A fully sandboxed virtual machine; the hypervisor is not named	Firecracker microVM with its own kernel	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Root and Docker	Commands do not run with sudo; no Docker documented	Root, Docker and Docker Compose inside	Root, systemd, Docker and Compose on every machine
Nested virtualization	No /dev/kvm documented	Not documented	Yes, /dev/kvm for Android emulators and VMs
Machine size	1, 4, 16 or 64 GB of memory; vCPU not published	One size for everyone: 4 vCPU / 8 GiB with 20 GB storage	4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB
Files after the session	Data is discarded when the container expires	The machine keeps its files; snapshots saved by hand, up to 10	Disk saved every minute and on stop; a stopped sandbox costs nothing and comes back
Lifetime	Expires after 20 minutes without use	No maximum run time documented; pauses after 30 idle minutes unless you turn it off	No session cap on paid plans; you set the time to live
Pause and resume	No pause; an idle container expires	Pause keeps memory and running programs; resume usually takes about a second	Stop keeps the disk; start boots the machine again
Fork	No fork	Fork copies a stopped machine only	Fork a running sandbox with its disk
Inbound access	None; you reach the container only through the API	SSH gateway with mosh; HTTPS on up to 16 ports, open to anyone with the URL	SSH, HTTPS on up to 50 ports with a token by default, raw TCP
Keeping API keys out of the sandbox	domain_secrets: a sidecar adds the real header, the model sees a placeholder	Vault writes your secrets into each machine as environment variables or files	Credentials proxy for model providers and any HTTPS API; real keys never enter the sandbox
Coding agents	Agents API (beta) drives a managed Codex harness from outside	Templates and saved agent sign-ins in snapshots; you run the agent yourself	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Desktop and computer use	Hosted browser for the Agents API computer_use tool	Linux desktop on one template, screenshot and click API, shareable view or control links	60fps Linux desktop with Chromium, a computer-use agent and an embeddable stream
Regions	US or EU processing for Code Interpreter	Not published	EU only (Germany, Finland, France)
Access and billing	Open API, billed by the minute with a 5-minute minimum, plus model tokens	Invite-only beta, free for now with 5 machines per user; no published price	Plans from $20 a month, all of it usage credit spent per second

Every feature Battleships tracks (43)

Feature	OpenAI Containers	Instabox	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	No	Yes	Yes
Nested virtualization	No	Not published	Yes
Root	No	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	Yes	Yes	Yes
Browser	Yes	Yes	Yes
Computer-use API	Yes	Yes	Yes
SSH	No	Yes	Yes
Persistent disk	No	Yes	Yes
Pause/resume	No	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)	No	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	No	No	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	No	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	No	Not published	Yes
Agent harness API	Yes	Not published	Yes
MCP server	No	Not published	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	Not published	No
Self-hosting	Yes	Not published	No
BYOC	No	Not published	No
Open source	No	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	Yes	No	No
SOC 2	Yes	Not published	No
HIPAA	Yes	Not published	No
EU data residency	Yes	Not published	Yes
Zero data retention	Not published	Not published	Yes

Performance

OpenAI ContainersNot measured

InstaboxNot measured

boat26.69 runs/s

There is no comparable measurement for either: OpenAI Containers and Instabox are not in the public CPU benchmark, and OpenAI does not publish the vCPU behind each container size. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB. Instabox says a new machine's shell is ready 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. OpenAI Containers 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	OpenAI Containers, 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	$228 · API pay as you go · 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	$1,051 · API pay as you go · 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	$11,405 · API pay as you go · 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	$1,620 · API pay as you go · 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	$6,000 · API pay as you go · with limits	No published price	$2,000 · $2000/mo · with limits

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.

Instabox: Instabox is free during the beta, with 5 machines per user, and publishes no price or rate yet, so no bill can be compared with OpenAI's or boat's.

Instabox: Plans start at $20 a month, and the whole fee is usage credit spent per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

OpenAI Containers fit none of the five scenarios as written: no persistent disk, no Docker, no internet by default in Code Interpreter and Hosted Shell, and no published vCPU or concurrency. Instabox publishes no rate, so it is not priced here, and its 5-machine cap, counting paused and stopped ones, rules out the 50-agent fleet, the 300 user sandboxes and the 1,000-job burst; an API exec call also runs at most 10 minutes, with 4 at once. On boat the burst is limited by starts, so the $2,000 plan queues them.

Scenario	OpenAI Containers	Instabox	boat
One coding agent, workdays	no open internet: sandboxes reach only an allowlist (domains your org admin adds to the allow list) missing persistent disk machine size not published different kind of product: code interpreter	no published per-resource rate	None that bite
One agent that never stops	no open internet: sandboxes reach only an allowlist (domains your org admin adds to the allow list) missing persistent disk machine size not published different kind of product: code interpreter	no published per-resource rate	None that bite
50 agents in parallel	no open internet: sandboxes reach only an allowlist (domains your org admin adds to the allow list) missing persistent disk, Docker inside machine size not published different kind of product: code interpreter	no published per-resource rate	None that bite
Sandboxes for your users	no open internet: sandboxes reach only an allowlist (domains your org admin adds to the allow list) machine size not published different kind of product: code interpreter not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	no published per-resource rate	None that bite
1,000 short jobs at once	no open internet: sandboxes reach only an allowlist (domains your org admin adds to the allow list) machine size not published different kind of product: code interpreter not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	no published per-resource rate	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

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.
Locked-down network by default. Useful if code must only reach chosen hosts: Code Interpreter and Hosted Shell have no outbound access until an admin allows domains.
Open to everyone, US or EU. Any API account can use it today, and Code Interpreter can process data in the United States or Europe.

Use Instabox when

you have an invite and want to try a few free 4 vCPU / 8 GiB agent machines with root, Docker, memory pause and mosh during its beta.

A real machine the agent keeps. Useful if your agent needs root, Docker and files that stay: each Instabox machine is a Firecracker VM it keeps.
Pause with memory. A paused machine keeps its memory and running programs and usually resumes in about a second.
Free during the beta. If you get an invite, you can run 5 machines of 4 vCPU / 8 GiB for free while the beta lasts.

Where boat fits

If you want what Instabox offers but need it on published terms, in bigger sizes or for more than five agents, look at boat. It is also the step up from OpenAI Containers when the model's code needs a whole machine it keeps, reachable from outside.

A whole machine with root and /dev/kvm

OpenAI's shell runs without sudo and documents no Docker. Instabox has root and Docker but one 4 vCPU / 8 GiB size and no documented /dev/kvm. boat adds systemd, /dev/kvm and sizes up to 16 vCPU / 32 GB.

Fork running work, disk saved every minute

An OpenAI container discards its files after 20 idle minutes. Instabox forks only stopped machines, and a snapshot stops a running one first, ending its programs. boat forks a running sandbox and saves the disk every minute.

Private URLs and agents driven from outside

OpenAI containers accept no inbound connections. Instabox port URLs are open to anyone who has them, so you add your own login. boat URLs carry a token by default, and you drive agents inside from outside through one API.

Use boat when your agents need a real machine on published terms: root, Docker and /dev/kvm, forks of running work, private URLs, bigger sizes and more than five at once. Compare it one to one: boat vs OpenAI Containers and boat vs Instabox.

Questions people ask

Is OpenAI Containers cheaper than Instabox?

It can't be compared yet. Instabox is free during its beta and publishes no price, while OpenAI bills by the minute plus model tokens. For one coding agent on workdays, OpenAI comes to $228 a month here, without fully fitting the job.

Which is faster, OpenAI Containers or Instabox?

Neither has been measured on the public CPU benchmark, and OpenAI does not publish vCPU per container size. Instabox says a new shell is ready in under a second, which has not been measured either. boat did 26.69 runs per second at 4 vCPU / 8 GB.

Can I run Docker in OpenAI Containers or Instabox?

Instabox runs Docker and Docker Compose inside each machine, with root. OpenAI's hosted shell runs without sudo and documents no Docker. boat gives root, systemd, Docker and /dev/kvm on every sandbox.

Do files survive between sessions?

On Instabox, yes: the machine keeps its files when paused or stopped. An OpenAI container discards its data when it expires after 20 idle minutes. boat saves the disk every minute and on stop.

Is Instabox free, and can anyone sign up?

It is free during the beta, with 5 machines of 4 vCPU / 8 GiB per user, and no later price or end date is published. Access is invite-only, with sign-in through GitHub or Google.

Can I open a web app running inside them?

Not on OpenAI Containers: they have no ports, URLs or SSH. Instabox publishes HTTPS URLs for up to 16 ports, open to anyone with the link. boat gives up to 50 ports with a token by default, plus raw TCP and SSH.

Try boat

Install the CLI, then run boat new.

7-day free trial