Together Code Sandbox vs Docker Cloud Sandboxes

Together Code Sandbox gives you VMs started from Docker-image snapshots that run until you end them, but Together has to enable it for your organization. Docker Cloud Sandboxes is self-serve and runs the same sbx microVM you use on your laptop, with Docker inside, but each sandbox ends 24 hours after creation and you get 10 at a time by default.

The companies and products

Together Code Sandbox

Together AI is a cloud for running and training AI models, and Code Sandbox is its product for running code in isolated VMs.

You build a snapshot from a Docker image or Dockerfile on Together's builder, then start sandboxes from it and run commands and file operations through the together-sandbox SDK or CLI. When a sandbox ends you can save its disk, and its memory too, as a new snapshot to start more sandboxes from. It is aimed at model-generated code, agent tool calls and reinforcement learning rollouts, and it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.

Company: Together AI, a cloud for model inference, fine-tuning and GPU clusters
Isolation: A virtual machine per sandbox on Together's infrastructure
Access: The SDK and CLI must be enabled for your organization; you ask Together for access
Machine size: 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size is not configurable
History: Built on CodeSandbox, now a Together company; the CodeSandbox-based SDK is deprecated and together-sandbox is its successor
Source code: The SDKs and CLI are MIT-licensed on GitHub; the platform itself is not

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

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. “65th cheapest of 367” means 64 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	Together Code Sandbox: price rank	Docker Cloud Sandboxes: 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 runs many agents for days with Docker inside; Docker caps each sandbox at 24 hours and 10 at once, Together does not document Docker inside, and boat has Docker, root and /dev/kvm on every machine with no session cap on paid plans.	65th of 367, with limits $528 a month	280th of 367, with limits $4,928 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 does not fit one Docker session, and Together has no wake on request, so you start and stop its sandboxes from your own backend.	152nd of 366, with limits $1,095 a month	276th of 366, with limits $5,110 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 For short code runs Docker fits better than Together's Code Interpreter here: small sandboxes billed by the second, against Python-only sessions billed per 60 minutes.	326th of 345, with limits $2,190 a month	119th of 345, with limits $233 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 more than Docker's default of 10 sandboxes at once, and on Together every port is public with preview URLs still coming soon; boat's HTTPS URLs are token-protected by default.	234th of 361, with limits $900 a month	136th of 361, with limits $1,628 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 Both can snapshot a sandbox with its memory and start many copies from it, which suits rollouts that branch from one warm state, but Together's VMs need Together to enable them and Docker allows 10 at once by default.	315th of 360, with limits $21,900 a month	114th of 360, with limits $7,000 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 Together documents a Harbor guide for agent evals and Docker runs agents you attach to from the sbx CLI; boat ships the agents with an API to prompt, steer and follow each run.	258th of 364, with limits $450 a month	167th of 364, with limits $1,400 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	251st of 377, with limits $180 a month	172nd of 377, with limits $672 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that stays on all month needs no session cap; Docker's sandboxes end 24 hours after creation, while Together's run until you end them once your organization has access.	210th of 368, with limits $22 a month	127th of 368, with limits $204 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 Computer-use agents need a screen; neither Together nor Docker offers a desktop, while boat streams a Linux desktop with Chromium at 60fps.	184th of 369, with limits $600 a month	268th of 369, with limits $1,400 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	301st of 367, with limits $900 a month	277th of 367, with limits $700 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	219th of 346, with limits $180 a month	262nd of 346, with limits $350 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	124th of 338, with limits $3,600 a month	190th of 338, with limits $7,000 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	167th of 360, with limits $150 a month	248th of 360, with limits $350 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	Together Code Sandbox	Docker Cloud Sandboxes	boat
Isolation	A VM per sandbox on Together's infrastructure	MicroVM with its own Linux kernel and its own Docker Engine; hypervisor not named	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Getting access	The SDK and CLI must be enabled for your organization by Together	Self-serve pay-as-you-go plan on a personal Docker account	Sign up and start a sandbox from the API, CLI or dashboard
Machine size	0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed	1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, amd64 or arm64 by account	2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above
Session length	Runs until you end it, or until a time to live set at creation	1 hour by default, at most 24 hours from creation; resuming starts a new timer	No cap on paid plans; you set the time to live
Sandboxes at once	Not published	10 by default; no published way to raise it	100 on the $20 plan, up to 2,000 on higher plans, self-serve
Docker, root and systemd	Commands run as user 1000 by default, root on request; Docker inside not documented	Its own Docker Engine inside; the agent runs as a non-root user with sudo	Docker, systemd and root on every machine
Nested virtualization	Not documented	Not documented	Yes, /dev/kvm for Android emulators and VMs
Saving state	End a sandbox with a snapshot of its disk, or disk and memory; a new sandbox resumes with processes running	Stop keeps memory and files and resume picks up where it left off; unused snapshots are deleted after 7 days	Disk saved every minute and on stop; a stopped sandbox costs nothing; resume boots the machine again
Fork	No live fork: the parent stops, then you start many sandboxes from its snapshot	Snapshot a running sandbox with disk or disk and memory, then restore it as a new sandbox	Fork a running sandbox with its disk; the original keeps running
Reaching the sandbox	All ports public; preview URLs coming soon; no SSH	Public HTTPS URL per published port; not a TCP tunnel; SSH with Docker-issued certificates	SSH; HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Outbound rules	No outbound allowlist documented	Allow and deny rules by host, with allow-all, balanced and deny-all presets	Open internet, no provider-side allowlist
Desktop and browser	None; headless command and file access only	Terminal sessions only	60fps Linux desktop with Chromium and computer use
Coding agents	Run your own agent through execs; a Harbor guide for agent evals	Claude Code, Codex, Copilot, OpenCode and more, run and attached to from the sbx CLI	Seven agents preinstalled, with a prompt, steer and events API to drive them from outside
Keeping API keys out of the sandbox	No credentials proxy documented	Cloud proxy sets the auth header for built-in AI services and custom hosts	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out

Every feature Battleships tracks (43)

Feature	Together Code Sandbox	Docker Cloud Sandboxes	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	No	No	Yes
Computer-use API	No	No	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	No	Yes	Yes
Fork/clone	Yes	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	Yes	Yes	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	No	No	No
Wake on request	No	Not published	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	No	Not published	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	No	Yes	Yes
Agent harness API	No	No	Yes
MCP server	Yes	Yes	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	Yes	No
Self-hosting	No	No	No
BYOC	No	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)	Yes	No	Yes
Audit logs	Not published	Not published	No
SSO	Yes	Yes	No
SOC 2	Yes	No	No
HIPAA	No	No	No
EU data residency	Not published	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

Together Code SandboxNot measured

Docker Cloud SandboxesNot measured

boat26.69 runs/s

There is no comparable CPU measurement for Together Code Sandbox or Docker Cloud Sandboxes: neither is in the hpc-sandbox-benchmarks runs, and Docker does not say what hardware it uses. boat did 26.69 runs per second on the StarSling Node.js test at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts, so no speed ratio can be given for this pair.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Together Code Sandbox and Docker Cloud Sandboxes 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	Together Code Sandbox, a month	Docker Cloud Sandboxes, 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 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits	$49 · Docker Agentic Platform (pay-as-you-go)	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits	$204 · Docker Agentic Platform (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	$264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits	$2,464 · Docker Agentic Platform (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	$900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits	$700 · Docker Agentic Platform (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	$6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits	$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits	$2,000 · $2000/mo · with limits

Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, but the VMs must be enabled for your organization, so the tables price Code Interpreter: $0.03 per 60-minute session from prepaid credits, $5 minimum. Code Interpreter runs only Python and keeps no disk.

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 volumes and egress are free.

Docker Cloud Sandboxes: Plans start at $20 a month, and the whole fee becomes usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

The Together column is Code Interpreter, so it fits none of the scenarios: sessions last 60 minutes, nothing is kept after a session, it runs only Python and its machine size is not published. Docker fits one coding agent on workdays, but its 24-hour cap rules out one agent that never stops, and its default of 10 sandboxes at once rules out 50 agents, sandboxes for your users and 1,000 short jobs. boat fits every scenario except the 1,000-job burst, where its start limits queue the starts even on the $2,000 plan.

Scenario	Together Code Sandbox	Docker Cloud Sandboxes	boat
One coding agent, workdays	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk machine size not published different kind of product: code interpreter	None that bite	None that bite
One agent that never stops	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk machine size not published different kind of product: code interpreter	Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h	None that bite
50 agents in parallel	Together pay-as-you-go (prepaid credits; Code Interpreter only): sessions capped at 1 h missing persistent disk, Docker inside machine size not published different kind of product: code interpreter	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	None that bite
Sandboxes for your users	machine size not published different kind of product: code interpreter machine size per session not published egress price not published	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	None that bite
1,000 short jobs at once	machine size not published different kind of product: code interpreter machine size per session not published egress price not published	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	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 Together Code Sandbox when

you already run models on Together, can get the VMs enabled for your organization, and want light sandboxes from a tenth of a core that you can save with their memory and branch from.

Memory snapshots to branch from. Useful for rollouts: end a sandbox with its memory saved and start many copies with processes still running.
Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account and API key.
Tiny machines and a Python runner. Good for many light jobs: sandboxes start at a tenth of a core, and Code Interpreter runs Python per session.

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 memory kept across stops and strict outbound rules.

Stop and fork with memory. Useful for agents that pause between steps: a stopped sandbox comes back with its memory and running processes.
Outbound rules at the proxy. Teams that must limit where an agent connects can set allow and deny rules by host, enforced outside the VM.
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.

Where boat fits

If your agents do real work for hours or days, look at boat as well. Together's VMs need Together to switch them on and Docker's sandboxes stop at 24 hours, while boat is a full machine you can start today with no session cap on paid plans. Both Together and Docker also leave out the desktop, /dev/kvm and an API to drive the agent inside from outside.

A whole machine with /dev/kvm

Android emulator builds and VM-based tests need /dev/kvm, which neither Together nor Docker documents. Together also runs commands as a normal user and does not document Docker inside, so compose stacks need extra work there.

Runs as long and as wide as the work

On Docker your code must stop and resume an agent before the 24-hour mark, and the eleventh agent waits for a slot. On Together you first wait for access. boat runs 100 at once on the $20 plan with no session cap.

Agents, desktop and private hosting built in

On both you reach the agent through execs or a terminal and parse its text, and there is no screen for computer use. boat ships seven agents with a prompt and events API, a 60fps desktop and token-protected HTTPS on 50 ports.

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

Questions people ask

Is Together Code Sandbox cheaper than Docker Cloud Sandboxes?

Together's only self-serve price is Code Interpreter, which looks cheaper for long runs, $264 against $2,464 a month for 50 agents, but fits none of the scenarios because sessions end after 60 minutes and keep no disk. For short jobs Docker costs less: $700 against $900 for sandboxes for your users, and $1,400 against $6,000 for 1,000 short jobs at once.

Which is faster, Together Code Sandbox or Docker Cloud Sandboxes?

Neither has a comparable CPU measurement, so there is no fair answer yet. boat did 26.69 runs per second on the StarSling Node.js test at 4 vCPU / 8 GB, a run that included neither of them.

Can Together Code Sandbox run Docker?

Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox and does not read Dev Containers or Docker Compose. Docker Cloud Sandboxes runs its own Docker Engine in each sandbox, and boat runs Docker, systemd and root on every machine.

Can a Docker cloud sandbox run longer than 24 hours?

Not in one session. A Docker cloud sandbox expires after one hour by default, and extensions cannot go past 24 hours from creation. Together's sandboxes run until you end them, and boat has no session cap on paid plans.

Can I sign up for Together Code Sandbox today?

The together-sandbox SDK and CLI must be enabled for your organization, so you ask Together for access first. Docker Cloud Sandboxes and boat are both self-serve.

Try boat

Install the CLI, then run boat new.

7-day free trial