CodeSandbox SDK vs Unikraft Cloud

Both run each sandbox as a Firecracker microVM that sleeps when idle and wakes on the next request. CodeSandbox SDK gives you a dev VM with Docker inside that you size per sandbox, while Unikraft Cloud turns your Dockerfile into a tiny VM that boots in milliseconds and shares a flat plan pool.

The companies and products

CodeSandbox SDK

CodeSandbox SDK is an API from CodeSandbox, now a Together AI company, that starts sandboxed development VMs on the same infrastructure as the CodeSandbox editor.

Each sandbox is a Firecracker microVM built from a template or any Dockerfile. When it goes idle it hibernates with a memory snapshot, and it resumes or forks from that snapshot in seconds. You drive it from a TypeScript SDK through terminals, commands, files and HTTPS hosts. Together's docs now call it the legacy offering and point new users to its successor, the together-sandbox SDK.

Self-hosting
Not offered

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.

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. “46th cheapest of 345” means 45 of the other 344 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 workloadCodeSandbox SDK: price rankUnikraft Cloud: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
CodeSandbox SDK runs Docker inside each VM and Unikraft documents no container runtime inside, while boat adds SSH, systemd and /dev/kvm on top of Docker.
178th of 367, with limits
$1,939 a month
Can't run it3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
215th of 366, with limits
$2,478 a month
Can't run it5th 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 that sleep between calls suit both, but self-serve Unikraft caps you at 24 running instances, while CodeSandbox SDK's Scale plan allows 250.
46th cheapest of 345
$642 a month
Can't run it186th 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
CodeSandbox SDK caps Scale at 250 VMs at once and Unikraft Pro at 24 running instances, so 300 active users need Enterprise on either; boat fits on its paid plans.
140th of 361, with limits
$1,707 a month
Can't run itCheapest 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 fork from a memory snapshot, so many rollouts can branch from one warm state; boat forks a running sandbox with its disk.
348th of 360, with limits
$3,861 a month
Can't run it34th 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
64th cheapest of 364
$1,335 a month
Can't run it10th 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 fit CodeSandbox SDK, Unikraft has no documented Docker inside, and only boat gives /dev/kvm for emulators on every plan.
92nd cheapest of 377
$860 a month
Can't run it4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
Neither has SSH, so you work through each SDK or CLI; boat gives a full box you SSH into, kept all month.
310th of 368, with limits
$240 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
Neither CodeSandbox SDK nor Unikraft has a desktop built in; boat streams one at 60fps with Chromium and computer-use tools.
206th of 369, with limits
$691 a month
Can't run it6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
On both you build your own headless browser into an image; boat ships Chromium on a desktop in every sandbox.
251st of 367, with limits
$443 a month
Can't run it7th 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
281st of 346, with limits
$508 a month
Can't run it6th 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
193rd of 338, with limits
$7,390 a month
Can't run it71st 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
240th of 360, with limits
$326 a month
Can't run it2nd 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 itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run itCan't run it

Key features

FeatureCodeSandbox SDKUnikraft Cloudboat
IsolationFirecracker microVM with its own kernelMinimal Linux microVM on a customized Firecracker VMMFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine size2 to 16 cores per sandbox, up to 32 GB on Scale; 64 cores / 128 GB on EnterprisePlan pool shared by all running instances: 2 vCPU / 4 GiB, 8 vCPU / 8 GiB or 24 vCPU / 32 GiB4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB per sandbox on the $100 plan and above
Docker insideDocker and root; built from any DockerfileRuns as root; the Dockerfile becomes the VM image, with no container runtime inside documentedDocker, systemd and root, like any Ubuntu machine
Nested virtualizationNot documentedYes, with a per-instance flag, Enterprise onlyYes, /dev/kvm for Android emulators and VMs on every plan
Shell accessTerminals, commands and files through the SDK; no SSHCommands and files through the sandbox plugin and CLI; no SSH yetSSH, plus exec and files over the API
Sleep and wakeHibernates with a memory snapshot after an idle timeout; an HTTP request wakes itStandby after a 1 second idle cooldown by default; traffic wakes it in millisecondsDisk saved every minute and on stop; a stopped sandbox is started again by API
ForkFork a hibernated sandbox from its snapshot, or a running one sharing its memoryCheckpoint a running microVM's memory and volumes, then start new instances from itFork a running sandbox with its disk
Running at once (self-serve)250 VMs on Scale24 running instances on Pro, sharing 24 vCPU / 32 GiB100 to 2,000 sandboxes on paid plans
Inbound accessHTTPS host per port, public by default, signed tokens for private hosts; no raw TCPHTTP on 80, HTTPS on 443 and TLS-wrapped TCP on other ports through its load balancerHTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Desktop and browserNo desktop; a headless Chromium templateNone built in; run your own headless browser from a DockerfileLinux desktop streamed at 60fps, Chromium and computer-use tools
Coding agentsRun your own agent through the command APINone preinstalled; you bring the agent in your own imageClaude Code, Codex and others preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandboxSecrets passed in as environment variablesNetwork shield can inject secrets into traffic, Enterprise only, limited accessCredentials proxy for model providers and any HTTPS API, on every plan
RegionsA country hint steers scheduling, but placement is not guaranteedDallas, Frankfurt, San Francisco, Singapore and Washington DC; more on requestEU only (Germany, Finland, France)
Self-hostingNot offeredDedicated hosts, on-prem and your own cloud on EnterpriseNot offered
Every feature Battleships tracks (43)
FeatureCodeSandbox SDKUnikraft Cloudboat
Full VM (own kernel)YesYesYes
Docker insideYesNoYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdNot publishedNot publishedYes
Desktop GUINoNoYes
BrowserNoNoYes
Computer-use APINoNoYes
SSHNoNoYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesYesYes
Live fork (no pause)YesYesYes
Memory forkYesYesNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoNot publishedYes
Public IPv4NoNoNo
Egress allowlistNoYesNo
Secret proxyNoYesYes
Secret proxy for any APINoYesYes
Preinstalled agentsNoNoYes
Agent harness APINoNoYes
MCP serverNoNoNo
GPUNoYesNo
WindowsNoNoNo
Arm64NoYesNo
Self-hostingNoYesNo
BYOCNoYesNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)NoNoYes
Audit logsNot publishedYesNo
SSOYesNoNo
SOC 2YesYesNo
HIPAANoYesNo
EU data residencyNoYesYes
Zero data retentionNot publishedNot publishedYes

Performance

CodeSandbox SDKNot measured
Unikraft CloudNot measured
boat26.69 runs/s

There is no comparable CPU measurement for CodeSandbox SDK or Unikraft Cloud: neither was in the StarSling hpc-sandbox-benchmarks run. boat did 26.69 runs per second on its Node.js loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. Unikraft states cold starts under 10 ms, which is its own figure for 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. CodeSandbox SDK 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.

ScenarioCodeSandbox SDK, a monthUnikraft Cloud, a monthboat, 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
$193 · Scale$39 · Hobby$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$341 · Scale$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
$2,500 · ScaleCan'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
$815 · Scale · with limitsCan'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
$1,632 · Scale · with limitsCan't run it$2,000 · $2000/mo · with limits

CodeSandbox SDK: You buy VM credits and each size burns a fixed number per hour, billed per started minute while the VM runs, including idle time before it hibernates. Scale adds a monthly platform fee that is not usage credit, and a hibernated VM costs nothing.

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

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

Limits in those scenarios

Unikraft's pools are shared by every running instance, so one 4 vCPU / 8 GB agent fills the Team pool, and the 50-agent, user-sandbox and burst scenarios fit no self-serve plan. CodeSandbox SDK fits 50 agents at $2,500 a month but caps Scale at 250 VMs, so 300 user sandboxes or 1,000 jobs at once need Enterprise; its 20 GB disk and egress have no published price beyond that. boat fits every scenario except the burst, where even the $2,000 plan queues starts.

ScenarioCodeSandbox SDKUnikraft Cloudboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • 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
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • 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
  • egress price not published
  • no pool tier with 200 vCPU / 400 GiB for 50 VMs
  • no published per-resource rate
None that bite
Sandboxes for your users
  • Scale: max 250 concurrent
  • 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
  • Scale: max 250 concurrent
  • 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 CodeSandbox SDK when

you need sandboxes with Docker inside that hibernate with their memory and wake on the next HTTP request, in the hundreds at once, and you are fine building on what Together now calls its legacy SDK.

  • A real dev VM with Docker. Good when each sandbox needs Docker inside, built from any Dockerfile, with its own cores and memory up to 16 cores and 32 GB.
  • Hundreds of sandboxes self-serve. The Scale plan runs 250 VMs at once, far more than the 24 running instances of Unikraft's largest self-serve plan.
  • Memory forks of a running sandbox. Useful for branching many runs from one warm state: fork a running sandbox while it shares memory with its parent.

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 starts and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
  • Regions in the US and Asia. Pick Dallas, San Francisco, Washington DC, Singapore or Frankfurt, while CodeSandbox SDK only takes a best-effort country hint.
  • GPUs, arm64 and your own hardware. Enterprise customers can get NVIDIA GPUs, arm64 hosts, dedicated hosts, on-prem or their own cloud.

Where boat fits

CodeSandbox SDK and Unikraft Cloud are both built around sandboxes that sleep fast and wake on the next request. If your agents instead work for hours, installing tools, running Docker and emulators, opening a browser and serving things to other people, boat gives each one a full machine with the agent and its keys already set up.

A whole machine with SSH and /dev/kvm

Neither has SSH, Unikraft documents no Docker inside, and CodeSandbox SDK does not document nested virtualization. On Unikraft, /dev/kvm needs an Enterprise contract. boat has SSH, systemd, Docker and /dev/kvm on every plan.

Agents, desktop and keys built in

On both you bring your own agent and browser, and neither has a desktop. Keys go in as environment variables on CodeSandbox SDK, and Unikraft's secret injection is Enterprise only. boat preinstalls agents you drive from outside, a 60fps desktop and a credentials proxy.

Fleets of full-size sandboxes

Fifty agents at 4 vCPU / 8 GB exceed every self-serve Unikraft pool, and CodeSandbox SDK stops at 250 VMs on Scale. boat runs up to 2,000 sandboxes at once on paid plans, with no session cap.

Use boat when your agents need a real machine to work in: SSH, Docker, emulators, 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 CodeSandbox SDK and boat vs Unikraft Cloud.

Questions people ask

Is CodeSandbox SDK cheaper than Unikraft Cloud?

For one agent, no: a 4 vCPU / 8 GB agent that never stops is $341 a month on CodeSandbox SDK and $39 a month on Unikraft's Team pool, and boat comes to $26 a month. For 50 agents, CodeSandbox SDK fits at $2,500 a month while no self-serve Unikraft plan is big enough, and boat comes to $317 a month.

Which is faster?

Unikraft starts faster: its microVMs cold boot in milliseconds by its own figure, while CodeSandbox SDK resumes hibernated VMs in seconds. Neither has a comparable CPU benchmark; boat measured 26.69 runs per second at 4 vCPU / 8 GB.

Can CodeSandbox SDK or Unikraft Cloud run Docker?

CodeSandbox SDK runs Docker with root inside each VM. Unikraft uses your Dockerfile to build the VM itself and does not document a container runtime inside a running instance. boat sandboxes have Docker, systemd and /dev/kvm ready to use.

Can I SSH into either one?

No. CodeSandbox SDK connects through its SDK, Node and browser clients, and Unikraft has announced SSH as coming soon, with commands and files going through its sandbox plugin and CLI today. Every boat sandbox has SSH as well as an exec and files API.

How many sandboxes can run at once?

CodeSandbox SDK's Scale plan allows 250 VMs at once, and Unikraft's Pro plan allows 24 running instances sharing 24 vCPU and 32 GiB, with up to 5,000 more asleep. Beyond that both need Enterprise, while boat's paid plans run 100 to 2,000 sandboxes at once.

Is boat SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons