Together Code Sandbox vs smol machines

Together Code Sandbox runs VMs from Docker-image snapshots on Together's AI cloud, but Together has to enable it for your organization. smol machines runs open-source microVMs you can sign up for today, on its hosted cloud, your laptop or your own servers.

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

smol machines

smol machines makes fast, isolated Linux microVMs that run the same way on your laptop, in their hosted cloud, or on your own servers.

The core is smolvm, an open-source microVM engine built on libkrun, where each machine has its own guest kernel. smol cloud is the paid hosted service that runs fleets of those machines behind a REST API and Node, Python and Rust SDKs. It is built for developers who want one VM model from local development to production, with live branching of running machines.

Isolation: Hardware-isolated microVM with its own guest kernel (libkrun)
Company: Founded 2026, Y Combinator Spring 2026, San Francisco, team of one listed
Open source: smolvm engine and smol SDK are open source and run on macOS, Linux and Windows hosts
Guests: Linux only; no Windows or macOS guests
Regions: No region field in the cloud create API
Uptime SLA: 99.95% on Pro, Startup and Enterprise

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	smol machines: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month smol machines runs Docker inside its VMs and Together does not document it; boat adds root, systemd, /dev/kvm and SSH on every machine.	65th of 367, with limits $528 a month	73rd of 367, with limits $604 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Neither has a desktop, a browser or a way to keep keys out of the VM for an assistant that lives on its machine; boat has all three built in.	152nd of 366, with limits $1,095 a month	148th of 366, with limits $1,038 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 smol machines fits short code runs well with a one-minute minimum and a /code endpoint, while Together's self-serve Code Interpreter bills each 60-minute session.	326th of 345, with limits $2,190 a month	12th cheapest of 345 $140 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 smol machines wakes a stopped machine on the next command and serves up to 16 ports; on Together every port is public and preview URLs are listed as coming soon.	234th of 361, with limits $900 a month	7th cheapest of 361 $531 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 start many runs from a saved memory state, but smol branches a running machine live, while Together saves the snapshot only when the sandbox ends.	315th of 360, with limits $21,900 a month	111th of 360, with limits $6,978 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 Both document a Harbor setup for agent evals; boat ships the coding agents themselves, with an API to prompt, steer and follow each run.	258th of 364, with limits $450 a month	36th cheapest of 364 $670 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 jobs that build Android apps or boot VMs need nested virtualization, which boat has and neither Together nor smol cloud exposes.	251st of 377, with limits $180 a month	66th cheapest of 377 $514 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	210th of 368, with limits $22 a month	216th of 368, with limits $29 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 Neither Together nor smol cloud offers a hosted desktop, so you build your own; boat streams a Linux desktop at 60fps with computer use.	184th of 369, with limits $600 a month	90th of 369, with limits $156 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	176th of 367, with limits $136 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	241st of 346, with limits $242 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	148th of 338, with limits $4,344 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	252nd of 360, with limits $377 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	smol machines	boat
Isolation	A VM per sandbox on Together's infrastructure	libkrun microVM with its own guest kernel	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Getting started	The SDK and CLI must be enabled for your organization by Together	Sign up for smol cloud, or run the open-source engine yourself	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	Up to 32 vCPU / 32 GB on Startup, 16 vCPU / 24 GB on Pro	2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above
Docker, root and systemd	Commands run as user 1000 by default, root on request; Docker inside not documented	Docker runs inside the machine, with its data on the ext4 disk	Docker, systemd and root on every machine
Nested virtualization	Not documented	Not exposed in the cloud create API; a local smolvm flag only	Yes, /dev/kvm for Android emulators and VMs
Shell access	Commands, interactive shells and files through the SDK and CLI; no SSH	Command API, sessions and a WebSocket terminal capped at one hour per connection; no SSH	SSH, plus exec and files over the API
Saving state	End a sandbox with a snapshot of its disk, or disk and memory	Filesystem survives a stop; stopped disk keeps billing; checkpoints capture RAM to a file	Disk saved every minute and on stop; a stopped sandbox costs nothing
Fork	No live fork: the parent stops, then you start many sandboxes from its snapshot	Branch a running machine with its memory and processes	Fork a running sandbox with its disk; the original keeps running
Idle and wake	Time to live counts from creation; no idle detection and no wake on request	A command or terminal starts a stopped machine; idle apps wake on the next request	Runs until you stop it or its time to live ends; started again by API
Reaching the sandbox	All ports public; preview URLs coming soon; an experimental inbound allowlist	Up to 16 published ports through a returned URL or an authenticated connect route	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Desktop and browser	None; headless command and file access only	No hosted desktop; a guide shows running your own Chromium inside a machine	Linux desktop streamed at 60fps, Chromium and computer use built in
Coding agents	Run your own agent through execs; a Harbor guide for agent evals	Registry images with the Codex CLI and the Harbor eval harness, run through the command API	Claude Code, Codex and more preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandbox	No credentials proxy documented	Cloud secrets are environment variables the guest can read	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Self-hosting	No; the SDKs and CLI are open source, the platform is not	Open-source smolvm runs on your laptop or your own servers	No; hosted in the EU (Germany, Finland, France) with EU data residency

Every feature Battleships tracks (43)

Feature	Together Code Sandbox	smol machines	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Yes	Not published	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	No	No	Yes
Computer-use API	No	No	Yes
SSH	No	No	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	No	No	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	Yes	No
Wake on request	No	Yes	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	No	Yes
Secret proxy for any API	No	No	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	Yes	No
BYOC	No	Yes	No
Open source	No	Yes	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Yes	Yes
Usage per sandbox (API)	Yes	Yes	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

smol machinesNot measured

boat26.69 runs/s

There is no comparable CPU measurement for Together Code Sandbox or smol machines: neither was part of the StarSling hpc-sandbox-benchmarks run. boat did 26.69 runs per second on that Node.js test at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. smol machines publishes a boot time under 200ms for smolvm, which is a start-time figure, not CPU speed.

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 smol machines 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	smol machines, 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	$25 · Standard	$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	$93 · Standard	$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	$1,139 · Pro	$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	$465 · Startup	$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	$1,389 · Startup	$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, with a $5 minimum purchase. Code Interpreter runs only Python and keeps no disk, so it does not fit these scenarios.

smol machines: smol cloud charges a base fee for every hour a machine runs, plus the CPU and memory the guest actually uses, with a one-minute minimum and disk billed even while stopped. Pro ($20 a month) and Startup ($150 a month) are fees added on top of usage, not credit.

Limits in those scenarios

The Together column is Code Interpreter, and its limits decide every row: sessions last 60 minutes, nothing is kept after a session, and the machine size is not published, so it fits none of the scenarios. smol machines fits all five, but caps how many machines you hold by plan: 20 on Standard, 100 on Pro and 1,000 on Startup, with stopped machines still holding a slot. On boat the limit that bites is starts: 1,000 short jobs at once need more starts per hour and per day than the $2,000 plan allows, so starts are queued.

Scenario	Together Code Sandbox	smol machines	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	None that bite	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	None that bite	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	None that bite	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	None that bite	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 and want very light sandboxes you can save with their memory, or a simple Python runner billed per session.

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.
Very small machines. Good for many light jobs: a sandbox can be as small as a tenth of a core, with 1 to 8 GB per core.
A simple Python runner. For plain Python, the Code Interpreter API runs code in sessions billed per 60 minutes, with no VM to manage.

Use smol machines when

you want one open-source VM engine from your laptop to your own servers, live branches of a running machine, or a hosted cloud that starts large bursts of short jobs.

Open source, from laptop to your own servers. Teams that want the same VM locally, in a hosted cloud and on their own servers get it from one open-source engine.
Live branches with memory. Useful for RL and test fan-out: branch a running machine with its memory and processes, and pay the minimum once.
Outbound allowlists and arm64. Teams that must limit which hosts a machine reaches, or need arm64 images, get both on smol cloud.

Where boat fits

Both Together and smol give you a VM boundary and a command API, then leave the rest to you. If your agents do real work for hours, with Docker, emulators, a browser and servers other people reach, boat gives each one a whole machine with the agent and its keys already set up.

A whole machine with /dev/kvm and SSH

Neither Together nor smol cloud exposes nested virtualization or SSH, so Android emulators and VM-based tests do not start, and SSH tools must be rewired to an exec API. boat has /dev/kvm, Docker, systemd and SSH on every machine.

A desktop and private hosting

Neither has a hosted desktop, so a computer-use agent waits until you build one. Together makes every port public, and smol caps you at 16 ports. boat streams a 60fps desktop and serves 50 token-protected HTTPS ports plus raw TCP.

Agents and keys built in

On both, keys you pass in sit inside a machine the agent controls, and you write the agent harness on exec calls yourself. boat preinstalls coding agents you drive from outside and keeps real keys in a credentials proxy for any HTTPS API.

Use boat when your agents need a whole machine for real work: Docker, emulators, SSH, a desktop and a browser, with coding agents you drive from outside and keys that never enter the sandbox. Compare it one to one: boat vs Together Code Sandbox and boat vs smol machines.

Questions people ask

Is Together Code Sandbox cheaper than smol machines?

Together's only self-serve price is Code Interpreter, and it fits none of these scenarios because sessions end after 60 minutes and keep no disk. Where it looks cheaper, like $264 against $1,139 a month for 50 agents, it is not doing the same job, and at scale it costs more: $6,000 against $1,389 for 1,000 short jobs at once.

Which is faster, Together Code Sandbox or smol machines?

Neither has a comparable CPU measurement, so this page cannot say. smol machines publishes a boot time under 200ms for smolvm, which is about start time, not CPU speed. boat did 26.69 runs per second on the StarSling Node.js test at 4 vCPU / 8 GB.

Can Together Code Sandbox or smol machines run Docker?

smol machines runs Docker inside a machine, and its guide says Docker data must live on the machine's ext4 disk. Together builds sandboxes from Docker images, but its new SDK does not document Docker inside a sandbox. boat runs Docker, systemd and root on every machine.

Can either fork a running sandbox?

smol machines branches a running machine into children that keep its memory and processes. Together has no live fork: a sandbox ends with a snapshot of its disk and memory, and you start many sandboxes from it. boat forks a running sandbox with its disk while the original keeps running.

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. Code Interpreter is self-serve with prepaid credits. smol cloud and boat are both open to sign up.

Is smol machines open source?

The engine, smolvm, and the smol SDK are open source and run on your own computer or servers; smol cloud, the hosted service, is paid. Together open-sources its SDKs and CLI but not the platform. boat is a hosted service only.

Try boat

Install the CLI, then run boat new.

7-day free trial