CodeSandbox SDK vs Freestyle

Both pause a sandbox with its memory and wake it on the next request. CodeSandbox SDK runs Firecracker microVMs you drive through a TypeScript SDK and that Together now calls legacy, while Freestyle runs full KVM VMs with systemd, nested virtualization, agent CLIs and a default-deny firewall.

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

Freestyle

Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.

Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.

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 rankFreestyle: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Freestyle runs systemd, Docker and emulators where CodeSandbox SDK documents no nested virtualization, and boat adds CPUs that did about 2.8 times Freestyle's work.
178th of 367, with limits
$1,939 a month
241st of 367, with limits
$3,311 a month
3rd 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
263rd of 366, with limits
$4,195 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
Both suit short code runs that sleep between calls and wake with their memory, and the two rank close together here.
46th cheapest of 345
$642 a month
40th cheapest of 345
$482 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
Freestyle fits this scenario and CodeSandbox SDK does not, because Scale stops at 250 VMs at once; boat fits it too and gives each user a desktop and raw TCP.
140th of 361, with limits
$1,707 a month
16th cheapest of 361
$1,358 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 fork a running sandbox from its memory, which suits rollouts that branch from one state.
348th of 360, with limits
$3,861 a month
107th of 360, with limits
$6,600 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
64th cheapest of 364
$1,335 a month
53rd cheapest of 364
$1,046 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
CodeSandbox SDK fits CI runs fully here, while Freestyle's docs send sustained heavy CPU work elsewhere; boat runs builds on dedicated AMD Ryzen 9 9950X hosts.
92nd cheapest of 377
$860 a month
168th of 377, with limits
$625 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
Freestyle fits a dev box kept all month, while CodeSandbox SDK caps each VM at a 20 GB disk with no published price for more.
310th of 368, with limits
$240 a month
98th cheapest of 368
$151 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 ships a desktop: CodeSandbox SDK has none and Freestyle has guides to install one, while boat streams a 60fps desktop with computer use built in.
206th of 369, with limits
$691 a month
234th of 369, with limits
$940 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
CodeSandbox SDK offers a headless Chromium template and Freestyle a guide to install Chromium, while boat has Chromium on a full desktop in every sandbox.
251st of 367, with limits
$443 a month
257th of 367, with limits
$482 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
281st of 346, with limits
$508 a month
278th of 346, with limits
$482 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
193rd of 338, with limits
$7,390 a month
183rd of 338, with limits
$6,560 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
240th of 360, with limits
$326 a month
272nd of 360, with limits
$482 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 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 SDKFreestyleboat
IsolationFirecracker microVM with its own kernelFull KVM VM with its own kernel on bare metal serversFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU benchmark (4 vCPU / 8 GB)Not measured9.64 runs/s26.69 runs/s
Root, systemd and DockerDocker and root, built from any DockerfileRoot, systemd as pid 1, Docker from bootRoot, systemd and Docker
Nested virtualizationNot documentedYes, full KVM supportYes, /dev/kvm for Android emulators and VMs
Biggest machine16 cores / 32 GB on Scale, 64 / 128 GB on Enterprise32 vCPU / 64 GiB on Pro, 64 / 128 with custom limits16 vCPU / 32 GB on the $100 plan and above
Pause and resumeHibernates with a memory snapshot; resumes with processes runningPause saves memory and disk; the same processes resumeDisk saved every minute and on stop; resume boots the machine again
ForkFork a hibernated sandbox, or a running one sharing its memoryClone a running VM without pausing it; snapshots hold memory and diskFork a running sandbox with its disk
Wake on requestYes, an HTTP request to a host wakes itYes, a paused VM resumes on the next trafficNo; a stopped sandbox is started by API
Inbound accessHTTPS host per port, public by default; no raw TCPHTTPS on style.dev names or your own domain, forward auth, other public protocolsHTTPS URLs for up to 50 ports, token-protected by default; raw TCP
Outbound rulesNo provider-side allowlistDefault-deny firewall with allow rules by IP, VM, VPC or domainOpen internet, no provider-side allowlist
Coding agentsRun your own agent through the command APIclaude, codex, opencode and openclaw preinstalled, driven through execSeven agents preinstalled, with a prompt, steer and events API
Desktop and browserNo desktop; a headless Chromium templateGuides to install GNOME or Xvfb, VNC and Chromium yourselfLinux desktop streamed at 60fps, Chromium and computer use built in
Keeping API keys out of the sandboxSecrets passed in as environment variablesCredentials injected at the edge for HTTPS, Postgres and S3Credentials proxy for model providers and any HTTPS API, with account switching
RegionsA country hint, such as a cluster in Europe, but no guaranteeNot listed; the docs name a San Jose, US data centerEU only (Germany, Finland, France), zero data retention
Every feature Battleships tracks (43)
FeatureCodeSandbox SDKFreestyleboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdNot publishedYesYes
Desktop GUINoNoYes
BrowserNoNoYes
Computer-use APINoNoYes
SSHNoYesYes
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 inboundNoYesYes
Public IPv4NoNoNo
Egress allowlistNoYesNo
Secret proxyNoYesYes
Secret proxy for any APINoYesYes
Preinstalled agentsNoYesYes
Agent harness APINoNoYes
MCP serverNoNoNo
GPUNoYesNo
WindowsNoNoNo
Arm64NoNoNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedYesYes
Spend limitsNot publishedNot publishedYes
Usage per sandbox (API)NoNoYes
Audit logsNot publishedYesNo
SSOYesYesNo
SOC 2YesNot publishedNo
HIPAANoNot publishedNo
EU data residencyNoNoYes
Zero data retentionNot publishedNot publishedYes

Performance

CodeSandbox SDKNot measured
Freestyle9.64 runs/s
boat26.69 runs/s

On the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, Freestyle did 9.64 runs per second and boat did 26.69, about 2.8 times the work in the same time. CodeSandbox SDK has no comparable CPU measurement. This test measures CPU speed only, not start time.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. CodeSandbox SDK has 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 monthFreestyle, 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$27 · Free$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$341 · Scale$159 · Free$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 · Scale$2,139 · 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
$815 · Scale · with limits$581 · Pro$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 limits$1,305 · Pro · with limits$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 the idle time before it hibernates. Scale adds a $170 monthly platform fee that is not usage credit.

Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances. Hobby and Pro set a $50 or $500 monthly minimum that counts as usage, and a paused VM bills only for storage.

Freestyle: 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

CodeSandbox SDK's Scale plan allows 250 VMs at once, so it does not fit the user-sandboxes scenario with 300 at once, and each VM has a 20 GB disk with no published price for more. Freestyle Pro allows 400 at once, which covers 300 user sandboxes but not 1,000 short jobs. On Freestyle Free the monthly allowances are hard stops, and there is no idle timeout unless you set one. boat has no concurrency cap at these sizes, but even its $2,000 plan queues starts above 90 a minute.

ScenarioCodeSandbox SDKFreestyleboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
None that biteNone that bite
One agent that never stops
  • disk beyond 20 GiB: price unknown
  • egress price not published
None that biteNone that bite
50 agents in parallel
  • egress price not published
None that biteNone that bite
Sandboxes for your users
  • Scale: max 250 concurrent
  • egress price not published
None that biteNone that bite
1,000 short jobs at once
  • Scale: max 250 concurrent
  • egress price not published
  • Pro: max 400 concurrent
  • shared vCPUs on this tier”): heavy, sustained CPU use can be slowed by other tenants
  • 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

your sandboxes are previews or code runs built from a Dockerfile that sleep between visits and wake on the next HTTP request, and you are fine building on what Together now calls its legacy SDK.

  • Sleeps cheaply between visits. A hibernated VM costs nothing, and the next HTTP request wakes it with its memory and running processes.
  • Built from any Dockerfile. Teams with an existing Dockerfile can turn it into a sandbox template without building a VM snapshot.
  • Per-minute credits, no allocation billing. You pay credits only while a VM runs, and no storage fee is documented for a hibernated one.

Use Freestyle when

you want full VMs with systemd and nested virtualization that pause with their memory, a default-deny firewall per VM, or more than 250 sandboxes at once.

  • A full machine for agents. Each VM has systemd, Docker, nested virtualization and agent CLIs ready, so emulators and services run as on a server.
  • Network controls per VM. Every VM starts behind a default-deny firewall, with allow rules by IP, VM, VPC or exact domain.
  • Bigger machines and more at once. Pro allows 400 VMs at once and machines up to 32 vCPU / 64 GiB, larger with custom limits.

Where boat fits

Both are strongest at sandboxes that sleep and wake with their memory. If your agents instead work for hours on builds, tests, Docker and a browser, boat gives each one a full VM on faster CPUs with a desktop and the agents already set up.

Faster CPUs for builds and tests

Freestyle did 9.64 runs per second on the CPU benchmark and boat did 26.69, so every install and test waits almost three times as long there. CodeSandbox SDK has no comparable measurement.

A desktop and browser, ready

CodeSandbox SDK has no desktop and Freestyle leaves you to install GNOME, VNC and Chromium. boat streams a 60fps desktop with Chromium and computer use in every sandbox, so the agent can use web pages on day one.

Agents driven from outside

On CodeSandbox SDK you install and run your own agent; on Freestyle you start a CLI through exec and parse its output. boat lets you prompt, steer and follow the agents inside through one API, and switch a credential when credits run out.

Use boat when your agents do real work for hours: builds, tests, Docker, emulators, a desktop and a browser, on fast CPUs, with an API to drive the agents inside from outside. Compare it one to one: boat vs CodeSandbox SDK and boat vs Freestyle.

Questions people ask

Is CodeSandbox SDK cheaper than Freestyle?

Not in these scenarios. One coding agent on workdays comes to $193 a month on CodeSandbox SDK against $27 on Freestyle, and one agent running all month is $341 against $159. boat is $20 and $26 for the same two.

Which is faster, CodeSandbox SDK or Freestyle?

Freestyle did 9.64 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and CodeSandbox SDK was not measured, so there is no direct CPU comparison. boat did 26.69 on the same test.

Can CodeSandbox SDK and Freestyle run Docker?

Both run Docker inside the sandbox. Freestyle also has systemd and full KVM support for Android emulators and VMs, while CodeSandbox SDK does not document nested virtualization.

Do both pause a sandbox with its memory?

Yes. CodeSandbox SDK hibernates with a memory snapshot and Freestyle pauses with memory and disk, and both can wake on the next request. boat saves the disk every minute instead, and resuming boots the machine again.

Is CodeSandbox SDK still maintained?

CodeSandbox is now part of Together AI. Together's docs call the CodeSandbox-based SDK deprecated and name together-sandbox as its successor, while self-serve sign-up still runs through CodeSandbox.

How many sandboxes can run at once?

CodeSandbox SDK's Scale plan allows 250 VMs at once and Freestyle Pro allows 400, with more on Enterprise for both. Neither fits 1,000 short jobs at once on a self-serve plan.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons