Docker Cloud Sandboxes vs OpenAI Containers

Docker Cloud Sandboxes gives each coding agent its own microVM with Docker inside, for up to 24 hours, started from the same sbx CLI you use on your laptop. OpenAI Containers are a tool inside OpenAI's model API: the model runs Python or shell commands in a box without sudo that expires after 20 minutes without use.

The companies and products

Docker Cloud Sandboxes

Docker Cloud Sandboxes runs Docker's sbx coding-agent microVMs on Docker-managed compute instead of your laptop.

Each sandbox is a microVM with its own Linux kernel and its own Docker Engine, started from the same sbx CLI you use locally, with Claude Code, Codex and other agents ready to run. You can move a sandbox from your laptop to the cloud and back, publish HTTPS ports and SSH in. It launched on September 24, 2026, is billed pay-as-you-go on a personal Docker account, and is built for developers who want their local agent sandboxes to keep going off their machine.

Isolation: MicroVM per sandbox with its own Linux kernel and its own Docker Engine
Launched: September 24, 2026
Machine sizes: 1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, CPU only, amd64 or arm64 by account
Session length: 1 hour by default, extendable to 24 hours from creation
Default quota: 10 concurrent and 50 stored sandboxes per account
Account: Pay-as-you-go plan on a personal Docker account, even inside an organization
Regions: Not published

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

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. “280th cheapest of 367” means 279 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	Docker Cloud Sandboxes: 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 A software factory needs agents that run for days and by the dozen; Docker stops each sandbox at 24 hours and runs 10 at once, and OpenAI containers have no Docker or persistent disk.	280th of 367, with limits $4,928 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 assistant that lives on its machine all month fits neither: Docker ends a session 24 hours after creation, and an OpenAI container is deleted after 20 idle minutes.	276th of 366, with limits $5,110 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 Short code runs are where both fit best; Docker's small sandboxes billed by the second rank ahead of both OpenAI and boat here, while OpenAI's runs live inside the model call itself.	119th of 345, with limits $233 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 Serving your own users needs many sandboxes and a way in; Docker allows 10 at once by default, and OpenAI containers accept no inbound connections.	136th of 361, with limits $1,628 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	114th of 360, with limits $7,000 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	167th of 364, with limits $1,400 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 CI needs Docker, root and open internet; Docker has all three, OpenAI documents no Docker or root, and boat adds /dev/kvm for Android and VM builds.	172nd of 377, with limits $672 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 A dev box you keep all month needs no session cap and a disk that stays; Docker gives the disk but caps sessions at 24 hours, OpenAI gives neither.	127th of 368, with limits $204 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's Agents API has a hosted browser for computer use and Docker's sandboxes are terminal only; boat streams a full 60fps desktop with Chromium.	268th of 369, with limits $1,400 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 Docker ships no browser in the sandbox, OpenAI's hosted browser is driven by its own Codex harness, and boat runs Chromium you can drive with any agent.	277th of 367, with limits $700 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	262nd of 346, with limits $350 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	190th of 338, with limits $7,000 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	248th of 360, with limits $350 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	Docker Cloud Sandboxes	OpenAI Containers	boat
What it is	A microVM you start, stop and SSH into from the sbx CLI	A sandbox tool the model uses inside OpenAI's API	A cloud VM you create, keep, stop and reach from outside
Isolation	MicroVM with its own Linux kernel and Docker Engine; hypervisor not named	A fully sandboxed virtual machine; hypervisor not named	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Root and Docker inside	Its own Docker Engine; agent runs as a non-root user with sudo	Commands do not run with sudo; no Docker documented	Root, systemd and Docker on every machine
Nested virtualization	Not documented	Not documented	Yes, /dev/kvm for Android emulators and VMs
Machine size	1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, amd64 or arm64 by account	1, 4, 16 or 64 GB of memory; vCPU not published	4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB
Session length	1 hour by default, at most 24 hours from creation	Expires after 20 minutes without use; Agents API sandboxes after an hour without activity	No cap on paid plans; you set the time to live
Files after the session	Stop keeps memory and files; stopped snapshots are deleted after 7 days of non-use	Data is discarded when the container expires	Disk saved every minute and on stop; a stopped sandbox costs nothing and comes back
Fork	Snapshot a running sandbox with disk or disk and memory, restore it as a new one	No fork	Fork a running sandbox with its disk
Sandboxes at once	10 by default; no published way to raise it	Not published	100 on the $20 plan, up to 2,000 on higher plans
Inbound access	Public HTTPS URL per published port and SSH	None; you reach the container only through the API	SSH, HTTPS URLs for up to 50 ports, raw TCP
Outbound internet	Allow and deny rules by host, with allow-all, balanced and deny-all presets	Code Interpreter and Hosted Shell: off until an admin sets an org allowlist	Open internet, no provider-side allowlist
Keeping API keys out of the sandbox	Cloud proxy sets the auth header; the sandbox sees a placeholder	domain_secrets: a sidecar adds the real header for approved domains	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Coding agents	Claude Code, Codex, Copilot, OpenCode and more, attached to from the sbx CLI	Agents API (beta) drives a managed Codex harness with steering and events	Seven agents preinstalled, with a prompt, steer and events API to drive them from outside
Desktop and computer use	Terminal sessions only	Hosted browser for the Agents API computer_use tool	60fps Linux desktop with Chromium and computer use

Every feature Battleships tracks (43)

Feature	Docker Cloud Sandboxes	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	No	Yes	Yes
Computer-use API	No	Yes	Yes
SSH	Yes	No	Yes
Persistent disk	Yes	No	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	Yes	No	Yes
Fork/clone	Yes	No	Yes
Live fork (no pause)	Yes	No	Yes
Memory fork	Yes	No	No
Custom image (Docker or snapshot)	Yes	No	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	No	Yes	No
Wake on request	Not published	No	No
HTTPS preview URLs	Yes	No	Yes
Raw TCP inbound	Not published	No	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	Yes	Yes	Yes
Secret proxy for any API	Yes	Yes	Yes
Preinstalled agents	Yes	No	Yes
Agent harness API	No	Yes	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	Yes	No	No
Self-hosting	No	Yes	No
BYOC	No	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Not published	Not published	Yes
Usage per sandbox (API)	No	No	Yes
Audit logs	Not published	Not published	No
SSO	Yes	Yes	No
SOC 2	No	Yes	No
HIPAA	No	Yes	No
EU data residency	No	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

Docker Cloud SandboxesNot measured

OpenAI ContainersNot measured

boat26.69 runs/s

There is no comparable measurement for either one. Docker Cloud Sandboxes launched in September 2026 and is not in the hpc-sandbox-benchmarks runs, and OpenAI does not publish the vCPU behind each container size. boat did 26.69 runs per second on the same Node.js build-and-test benchmark at 4 vCPU / 8 GB.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Docker Cloud Sandboxes 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	Docker Cloud Sandboxes, 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	$49 · Docker Agentic Platform (pay-as-you-go)	$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	$204 · Docker Agentic Platform (pay-as-you-go) · 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	$2,464 · Docker Agentic Platform (pay-as-you-go) · 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	$700 · Docker Agentic Platform (pay-as-you-go) · 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	$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits	$6,000 · API pay as you go · with limits	$2,000 · $2000/mo · with limits

Docker Cloud Sandboxes: Docker bills per second for the size you pick, from $0.07 an hour for 1 vCPU / 2 GiB to $1.12 an hour for 16 vCPU / 32 GiB, with no monthly fee. A stopped sandbox costs nothing, and model calls are billed by your model provider.

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. The scenarios use the 16 GB size for 8 GB needs and the 4 GB size for 4 GB needs, since vCPU is not published.

OpenAI Containers: Plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Docker fits one coding agent on workdays, but its 24-hour session cap rules out an agent that never stops, and its default of 10 sandboxes at once rules out 50 agents, 300 user sandboxes and a 1,000-job burst. OpenAI Containers fit none of the five scenarios: no persistent disk, no Docker, no internet until an admin sets an allowlist, and no published vCPU or concurrency limit. On boat the 1,000-job burst is limited by starts per minute, so even the $2,000 plan queues those starts.

Scenario	Docker Cloud Sandboxes	OpenAI Containers	boat
One coding agent, workdays	None that bite	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	None that bite
One agent that never stops	Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h	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	None that bite
50 agents in parallel	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	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	None that bite
Sandboxes for your users	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	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)	None that bite
1,000 short jobs at once	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	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)	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 Docker Cloud Sandboxes when

you already run agents in sbx on your laptop and want a few of them to keep going in the cloud for up to a day, with Docker inside and memory kept across stops.

A real machine with Docker inside. For coding agents that build and test: each sandbox has its own kernel, its own Docker Engine, sudo and SSH.
Stop and fork with memory. For agents that pause between steps: a stopped sandbox comes back with memory and processes, and can be forked.
The same sandbox on your laptop. If you already run sbx locally, the cloud is the same microVM and CLI, and you can move work between them.

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. 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. If code must only reach chosen hosts, Code Interpreter and Hosted Shell have no outbound access until an admin allows domains.
US or EU processing and your own compute. Code Interpreter can process data in the US or Europe, and the Agents API can drive a sandbox you host.

Where boat fits

If your agents run for days, by the dozen, or need a screen, look at boat. Docker caps each session at 24 hours and 10 at once, and OpenAI's containers expire after 20 idle minutes with no Docker or root. boat gives each agent a full VM with no session cap on paid plans.

Runs as long as the work

A multi-day agent on Docker must be stopped and resumed by your code before 24 hours. On OpenAI it must touch the container every 20 minutes or lose everything. boat has no session cap and saves the disk every minute.

A whole machine, screen included

Docker gives a terminal with no /dev/kvm, and OpenAI gives no sudo or Docker. boat has root, systemd, Docker, /dev/kvm for Android emulators and a 60fps desktop with Chromium, so one machine covers builds, tests and clicking through a UI.

Drive agents inside from outside

On Docker you attach to an agent's terminal and parse its text; on OpenAI the Agents API drives only its own Codex harness. boat preinstalls seven agents and drives any of them through one prompt, steer and events API.

Use boat when your agents run for days or by the dozen, need root, Docker, Android emulators or a desktop, or have to be driven from your own app through an API. Compare it one to one: boat vs Docker Cloud Sandboxes and boat vs OpenAI Containers.

Questions people ask

Is Docker Cloud Sandboxes cheaper than OpenAI Containers?

For one coding agent on workdays, Docker comes to $49 a month against $228 on OpenAI, and OpenAI also bills model tokens on top. boat comes to $20 a month for the same 4 vCPU / 8 GB machine.

Which is faster?

Neither has a public CPU measurement: Docker's cloud sandboxes are too new for the benchmark, and OpenAI does not publish the vCPU behind its containers. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB.

Can OpenAI Containers run Docker?

No Docker support is documented, and hosted shell commands do not run with sudo. Docker Cloud Sandboxes give each sandbox its own Docker Engine, and boat gives root, systemd, Docker and /dev/kvm.

How long can a sandbox run on each?

A Docker cloud sandbox runs 1 hour by default and at most 24 hours from creation. An OpenAI container expires after 20 minutes without use, and its data is discarded. boat has no session cap on paid plans.

Can I open a web app running inside the sandbox?

On Docker, yes: each published port gets a public HTTPS URL, and you can SSH in. OpenAI containers have no ports, URLs or SSH. boat gives HTTPS URLs for up to 50 ports, raw TCP and SSH.

Can I use OpenAI models with Docker Cloud Sandboxes or boat?

Yes. Both run Codex inside the sandbox, and both keep your real API key outside it with a credentials proxy. On boat the proxy also covers any HTTPS API.

Try boat

Install the CLI, then run boat new.

7-day free trial