Together Code Sandbox vs Unikraft Cloud

Together Code Sandbox starts VMs from Docker-image snapshots and can save their memory when they end, but Together has to turn it on for your organization. Unikraft Cloud is self-serve today: it turns a Dockerfile into a tiny microVM that sleeps when idle and wakes in milliseconds on the next request.

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

Unikraft Cloud

Unikraft Cloud is a microVM cloud from Unikraft Inc. that runs any Dockerfile-based workload as a minimal Linux microVM with millisecond cold starts and scale-to-zero.

Your Dockerfile becomes the VM image at build time, and each instance runs on a heavily customized Firecracker VMM, so it boots in milliseconds and can go into standby when no traffic arrives. It is a general compute platform built for dense, bursty work such as HTTP services, headless browsers and agent fleets, sold as flat self-serve plans plus Enterprise dedicated hosts, on-prem and bring your own cloud. It is not a dev machine you log into: instances are reached through services, the CLI and a sandbox plugin for commands and files.

Isolation: Linux microVM per instance on a customized Firecracker VMM; full VMs on Enterprise
Plans: Hobby free, Team $39/mo, Pro $199/mo, Enterprise custom; each caps running instances, vCPUs and memory
Running capacity: 2 / 8 / 24 running instances with 4 / 8 / 32 GiB memory in total on Hobby / Team / Pro
Regions: Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default; more metros on request
Self-hosting: Dedicated host fleet, on-prem and BYOC on Enterprise
Compliance: SOC2, HIPAA and audit logs listed on Enterprise
Open source: The unikraft CLI is open source; the cloud platform is commercial

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	Unikraft Cloud: 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 Docker, root and often /dev/kvm; neither Together nor Unikraft documents Docker inside a sandbox, Unikraft keeps nested virtualization for Enterprise, and boat has all three on every machine.	65th of 367, with limits $528 a month	Can't run it	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 needs room to work; Unikraft's Team pool is 8 GiB shared by every running instance, and Together's self-serve Code Interpreter ends each session after 60 minutes.	152nd of 366, with limits $1,095 a month	Can't run it	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 suit both: Together's Code Interpreter runs Python in sessions billed per 60 minutes, while Unikraft wakes a sleeping microVM in milliseconds but caps self-serve plans at 24 running instances.	326th of 345, with limits $2,190 a month	Can't run it	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 Unikraft Pro holds 5,000 sleeping instances but only 24 running ones, and every Together port is public with preview URLs still coming soon, so boat's token-protected HTTPS URLs need less work for hundreds of users.	234th of 361, with limits $900 a month	Can't run it	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 branch runs from a warm state: Together saves a sandbox with its memory when it ends, and Unikraft checkpoints a running microVM, but Together's VMs need Together to enable them and Unikraft's self-serve pools are small.	315th of 360, with limits $21,900 a month	Can't run it	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	258th of 364, with limits $450 a month	Can't run it	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 Docker images or run Android emulators need a container runtime and /dev/kvm, which boat has on every plan and which Unikraft offers only on Enterprise.	251st of 377, with limits $180 a month	Can't run it	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Unikraft's Team pool keeps one box around all month and Together's priced product is a 60-minute Python session, and neither offers SSH, so on both you work through a CLI or SDK instead of logging in.	210th of 368, with limits $22 a month	219th of 368, with limits $39 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 desktop to see and click; boat streams one at 60fps, while Together and Unikraft both leave you to build your own inside the image.	184th of 369, with limits $600 a month	Can't run it	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	Can't run it	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	Can't run it	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	Can't run it	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	Can't run it	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	Unikraft Cloud	boat
Isolation	A VM per sandbox on Together's infrastructure	Minimal Linux microVM on a customized Firecracker VMM	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; only Code Interpreter is self-serve	Self-serve plans, with a free Hobby plan and no card	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	Plan pool shared by all running instances: 2 vCPU / 4 GiB, 8 vCPU / 8 GiB or 24 vCPU / 32 GiB	4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB per sandbox on the $100 plan and above
Docker, root and systemd	Commands run as user 1000 by default, root on request; Docker inside not documented	Runs as root; the Dockerfile becomes the VM image, with no container runtime inside documented	Docker, systemd and root on every machine
Nested virtualization	Not documented	Yes, with a per-instance flag and permission, Enterprise only	Yes, /dev/kvm for Android emulators and VMs on every plan
Shell access	Commands, interactive shells and files through the SDK and CLI; no SSH	No SSH yet; commands and files through the sandbox plugin and CLI	SSH, plus exec and files over the API
Idle and wake	Time to live counts from creation; no idle detection and no wake on request	Standby after a 1 second idle cooldown by default; incoming traffic wakes it in milliseconds	Runs until you stop it or its time to live ends; started again by API
Snapshots and fork	End a sandbox with a snapshot of its disk and memory, then start many sandboxes from it; no live fork	Checkpoint memory and volumes of a running microVM with a pause of a few milliseconds, then start new instances from it	Disk saved every minute and on stop; fork a running sandbox while the original keeps running
Reaching the sandbox	All ports public; preview URLs coming soon; an experimental inbound allowlist by IP or token	Services on its load balancer: HTTP on 80, HTTPS on 443, TLS-wrapped TCP on other ports; no public IP per instance	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	None built in; you can run your own headless browser from a Dockerfile	Linux desktop streamed at 60fps, Chromium and computer-use tools
Coding agents	Run your own agent through execs; a Harbor guide for agent evals	None preinstalled; you bring the agent in your own image	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandbox	No credentials proxy documented	Network shield can inject secrets into traffic, Enterprise only, limited access	Credentials proxy for model providers and any HTTPS API, on every plan
Hosted code interpreter	Code Interpreter API runs Python in sessions billed per 60 minutes	None	No separate product; run code through exec in a sandbox
Regions	Not published	Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default; more on request	EU only (Germany, Finland, France)

Every feature Battleships tracks (43)

Feature	Together Code Sandbox	Unikraft Cloud	boat
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	No	Yes
Nested virtualization	No	Yes	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	No	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	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	Yes	Yes
Secret proxy for any API	No	Yes	Yes
Preinstalled agents	No	No	Yes
Agent harness API	No	No	Yes
MCP server	Yes	No	No
GPU	No	Yes	No
Windows	No	No	No
Arm64	No	Yes	No
Self-hosting	No	Yes	No
BYOC	No	Yes	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	Yes	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	No	Yes	No
EU data residency	Not published	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

Together Code SandboxNot measured

Unikraft CloudNot measured

boat26.69 runs/s

There is no comparable CPU measurement for Together Code Sandbox or Unikraft Cloud: neither was in the StarSling hpc-sandbox-benchmarks run that measured boat at 26.69 runs per second at 4 vCPU / 8 GB. Unikraft states cold starts under 10 ms, which is its own figure and measures start time, 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 Unikraft Cloud 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	Unikraft Cloud, 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	$39 · Hobby	$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	$39 · Hobby	$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	Can't run it	$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	Can't run it	$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	Can't run it	$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 table prices Code Interpreter: $0.03 per 60-minute session from prepaid credits, with a $5 minimum purchase.

Unikraft Cloud: Unikraft charges a flat monthly fee for a pool of running capacity: free for 2 vCPU / 4 GiB, $39 for 8 vCPU / 8 GiB, $199 for 24 vCPU / 32 GiB, with sleeping instances not counted. It publishes no per-hour rate, so anything bigger is an Enterprise quote.

Unikraft Cloud: 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, and it fits no scenario: sessions last 60 minutes, nothing is kept after a session, it runs only Python, and the machine size is not published. Unikraft fits one agent, since a single 4 vCPU / 8 GB agent fills the Team pool, but 50 agents, sandboxes for your users and 1,000 short jobs are above every self-serve pool and need Enterprise. On boat the limit that bites is starts: at 1,000 short jobs at once, even the $2,000 plan queues them.

Scenario	Together Code Sandbox	Unikraft Cloud	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	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown egress price not published	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	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown egress price not published	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	no pool tier with 200 vCPU / 400 GiB for 50 VMs no published per-resource rate	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	no pool tier with 600 vCPU / 1,200 GiB for 300 VMs no published per-resource rate	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	no pool tier with 2,000 vCPU / 4,000 GiB for 1,000 VMs 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 Together Code Sandbox when

you already run models on Together and want light sandboxes, from a tenth of a core, that you can save with their memory and branch from, or a simple Python runner billed per session.

Memory snapshots to branch from. Useful for rollouts and test variants: 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.
Very small machines and a Python runner. Good for many light jobs: sandboxes start at a tenth of a core, and a Python interpreter API bills per session.

Use Unikraft Cloud when

you run many small services or headless browsers that sleep most of the time and must wake in milliseconds, need US or Asia regions, or want GPUs, on-prem or your own cloud under an Enterprise contract.

Millisecond wake and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
Self-serve from day one. You can sign up and run instances today on a free Hobby plan, without asking anyone to enable your account.
Regions and your own hardware. Runs in the US, Frankfurt and Singapore, and Enterprise adds GPUs, arm64, dedicated hosts, on-prem or your own cloud.

Where boat fits

Together and Unikraft both run code in small VMs that you drive through an SDK or CLI. If what you are really running is agents that work for hours, install tools, run Docker and serve apps, boat gives each one a whole machine you can sign up for today, with the agent and its keys already set up.

A whole machine the agent can work in

Neither Together nor Unikraft documents Docker inside a sandbox or offers SSH, and Unikraft keeps /dev/kvm for Enterprise. The workaround is baking every tool into the image up front. boat has root, systemd, Docker, SSH and /dev/kvm on every plan.

Agents, desktop and keys built in

On both, you build the agent, browser and desktop into your own image. Together has no credentials proxy and Unikraft's secret injection is Enterprise only, so keys sit inside a machine the agent controls. boat keeps them in a proxy outside.

Big fleets of full-size sandboxes, self-serve

Fifty agents at 4 vCPU / 8 GB are above every Unikraft self-serve pool, and Together's VMs need Together to turn them on. boat's paid plans run 100 to 2,000 sandboxes at once with no session cap and no sales call.

Use boat when your agents need a real machine to work in for hours: Docker, emulators, SSH, a desktop and a browser, coding agents you drive from outside, and fleets of full-size sandboxes without a sales call. Compare it one to one: boat vs Together Code Sandbox and boat vs Unikraft Cloud.

Questions people ask

Is Together Code Sandbox cheaper than Unikraft Cloud?

Together's only self-serve price is Code Interpreter at $0.03 per 60-minute session, which keeps no disk and does not fit an agent that works all day. Unikraft's $39 Team pool fits one 4 vCPU / 8 GB agent, but for 50 agents or hundreds of user sandboxes no self-serve Unikraft plan is big enough. On boat, 50 agents cost $317 a month and sandboxes for your users $200 a month.

Which is faster, Together Code Sandbox or Unikraft Cloud?

Neither has a comparable CPU measurement, so there is no fair speed ratio. Unikraft is built to start fast: its microVMs cold boot in milliseconds and wake on the next request. Together sandboxes have no wake on request, and you start them from snapshots through the SDK.

Can Together Code Sandbox or Unikraft Cloud run Docker?

Both build sandboxes from Docker images, but neither documents running Docker inside a running sandbox. A boat sandbox is a full Ubuntu VM with Docker, systemd and /dev/kvm ready to use.

Can I SSH into Together Code Sandbox or Unikraft Cloud?

No. Together gives you commands, interactive shells and files through its SDK and CLI, and Unikraft uses its sandbox plugin and CLI. You can SSH into every boat sandbox or drive it through its API.

Can I start using them today?

Unikraft Cloud yes: the Hobby plan is free with no card. Together's VM sandboxes must be enabled for your organization, so you ask Together first; only Code Interpreter is self-serve on prepaid credits.

Try boat

Install the CLI, then run boat new.

7-day free trial