bochka vs CodeSandbox SDK

Both give each agent its own Linux VM that keeps its disk. bochka gives it a fuller machine with SSH, a desktop, nested virtualization and coding agents built in, while CodeSandbox SDK is strongest at VMs that hibernate with their memory and wake on the next request.

Where bochka stands out

A whole machine, not just a code box

A bochka sandbox is a full VM with SSH, systemd, root, Docker and /dev/kvm, so Android emulators and nested VMs run too. CodeSandbox SDK gives you terminals and commands through its SDK, with no SSH and no documented nested virtualization.

Agents, desktop and keys built in

Claude Code, Codex and other agents come preinstalled, and you prompt, steer and follow them through one API. Each sandbox also has a 60fps desktop with Chromium for computer use, and real API keys stay outside it in a credentials proxy.

Hosting beyond HTTPS

bochka serves HTTPS on up to 50 ports per sandbox, token-protected by default, and also takes raw TCP on a dedicated IPv6 or IPv4. Data stays in the EU, with zero data retention.

The companies and products

bochka

bochka.xyz runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.

You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.

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

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. “3rd cheapest of 367” means 2 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 workloadbochka: price rankCodeSandbox SDK: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Both run Docker and keep their disk, but bochka adds SSH, nested virtualization for Android emulators and preinstalled coding agents you drive by API.
3rd cheapest of 367
$634 a month
178th of 367, with limits
$1,939 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month fits either, but bochka's agents, browser and credentials proxy come built in rather than assembled.
5th cheapest of 366
$657 a month
215th of 366, with limits
$2,478 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
CodeSandbox SDK suits this well: short code runs on VMs that hibernate with their memory and wake on the next request, billed only while running.
186th of 345, with limits
$2,000 a month
46th cheapest of 345
$642 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Both fit; CodeSandbox SDK wakes a user's sandbox on their next HTTP request, while bochka gives each user raw TCP, SSH and a desktop as well as HTTPS.
Cheapest of 361
$209 a month
140th of 361, with limits
$1,707 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
CodeSandbox SDK's memory forks let many rollouts branch from the same running state.
34th of 360, with limits
$2,000 a month
348th of 360, with limits
$3,861 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
10th cheapest of 364
$200 a month
64th cheapest of 364
$1,335 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 VM images need /dev/kvm, which bochka has and CodeSandbox SDK does not document.
4th cheapest of 377
$86 a month
92nd cheapest of 377
$860 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
18th cheapest of 368
$26 a month
310th of 368, with limits
$240 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 and a browser, which bochka streams at 60fps and CodeSandbox SDK does not offer.
6th cheapest of 369
$200 a month
206th of 369, with limits
$691 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
bochka ships Chromium on a full desktop in every sandbox; on CodeSandbox SDK you build a headless browser template yourself.
7th cheapest of 367
$200 a month
251st of 367, with limits
$443 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
6th cheapest of 346
$90 a month
281st of 346, with limits
$508 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
71st of 338, with limits
$1,800 a month
193rd of 338, with limits
$7,390 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
2nd cheapest of 360
$200 a month
240th of 360, with limits
$326 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 it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Can't run itCan't run it

Key features

FeaturebochkaCodeSandbox SDK
IsolationFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hostsFirecracker microVM with its own kernel
Biggest machineUp to 16 vCPU / 32 GB on the $100 plan and aboveUp to 16 cores / 32 GB on Scale, 64 cores / 128 GB on Enterprise
Session lengthNo cap on paid plans; you set the time to liveNo hard cap; hibernates after an idle timeout of up to one day
Pause and resumeDisk is saved every minute and on stop; resume boots the machine againHibernates with a memory snapshot; resumes with processes still running
ForkFork a running sandbox with its diskFork a hibernated sandbox from its snapshot, or a running one sharing its memory
Wake on requestNo; a stopped sandbox is started by APIYes; an HTTP request to a host wakes it, WebSocket optional
Nested virtualizationYes, /dev/kvm for Android emulators and VMsNot documented
Docker and rootDocker, systemd and rootDocker and root; built from any Dockerfile
Shell accessSSH, plus exec and files over the APITerminals, commands and files through the SDK; no SSH
Inbound accessHTTPS URLs for up to 50 ports, token-protected by default; raw TCP; a dedicated IPv6 or IPv4HTTPS host per port, public by default, signed tokens for private hosts; no raw TCP or public IP
Desktop and browserLinux desktop streamed at 60fps, Chromium and computer-use toolsNo desktop; a headless Chromium template
Coding agentsClaude Code, Codex and others preinstalled, with a prompt, steer and events APIRun your own agent through the command API
Keeping API keys out of the sandboxCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run outSecrets passed in as environment variables
Compliance and transparencySOC 2 is in progress. We're open about where we stand: live status and data retention policy.SOC 2
Every feature Battleships tracks (43)
FeaturebochkaCodeSandbox SDK
Full VM (own kernel)YesYes
Docker insideYesYes
Nested virtualizationYesNo
RootYesYes
SystemdYesNot published
Desktop GUIYesNo
BrowserYesNo
Computer-use APIYesNo
SSHYesNo
Persistent diskYesYes
Pause/resumeYesYes
Automatic snapshotsYesYes
Fork/cloneYesYes
Live fork (no pause)YesYes
Memory forkNoYes
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNoYes
Wake on requestNoYes
HTTPS preview URLsYesYes
Raw TCP inboundYesNo
Public IPv4NoNo
Egress allowlistNoNo
Secret proxyYesNo
Secret proxy for any APIYesNo
Preinstalled agentsYesNo
Agent harness APIYesNo
MCP serverNoNo
GPUNoNo
WindowsNoNo
Arm64NoNo
Self-hostingNoNo
BYOCNoNo
Open sourceNoNo
Scoped API keysYesNot published
Spend limitsYesNot published
Usage per sandbox (API)YesNo
Audit logsNoNot published
SSONoYes
SOC 2NoYes
HIPAANoNo
EU data residencyYesNo
Zero data retentionYesNot published

Performance

bochka26.69 runs/s
CodeSandbox SDKNot measured

There is no comparable CPU measurement for CodeSandbox SDK. bochka did 26.69 runs per second on the StarSling hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts, and CodeSandbox SDK was not part of that run.

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.

Scenariobochka, a monthCodeSandbox SDK, 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
$20 · $20/mo$193 · Scale
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$341 · Scale
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$317 · $20/mo × 3 seats$2,500 · Scale
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$200 · $100/mo × 2 seats$815 · Scale · with limits
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$2,000 · $2000/mo · with limits$1,632 · Scale · with limits

bochka: 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.

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. Larger teams pay a $170 monthly Scale platform fee on top, which is not usage credit, and a hibernated VM costs nothing.

Limits in those scenarios

CodeSandbox SDK's Scale plan allows 250 VMs at once, so the user-sandboxes and 1,000-job scenarios do not fit it without Enterprise. Each VM has a 20 GB disk, and the price for more disk and for egress is not published. bochka has no such cap at those sizes, but its start limits bite on bursts: at 1,000 short jobs at once, even the $2,000 plan queues starts.

ScenariobochkaCodeSandbox SDK
One coding agent, workdaysNone that bite
  • disk beyond 20 GiB: price unknown
  • egress price not published
One agent that never stopsNone that bite
  • disk beyond 20 GiB: price unknown
  • egress price not published
50 agents in parallelNone that bite
  • egress price not published
Sandboxes for your usersNone that bite
  • Scale: max 250 concurrent
  • egress price not published
1,000 short jobs at once
  • 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)
  • Scale: max 250 concurrent
  • egress price not published

Which one should you use?

Use CodeSandbox SDK when

you run previews or code runs that sleep between visits and should wake on the next HTTP request with their memory intact, and you are fine building on what Together now calls its legacy SDK.

  • Memory hibernation and wake on request. Useful for sandboxes that sleep between visits: an HTTP request wakes a hibernated VM with its processes still running.
  • Forks that share memory. Good for branching many runs from one warm state, such as rollouts or test variants.
  • Bigger machines on Enterprise. Teams that need very large single machines can get up to 64 cores and 128 GB through Enterprise sales.

Use bochka when

your agents do real work for hours: installs, builds, Docker, emulators, a browser and servers other people reach, on a full machine with the agent and its keys already set up.

  • A whole machine, not just a code box. Agents and their tools often expect SSH, a service manager or KVM. Without them, emulator builds and VM-based tests cannot start, and every tool has to be wired through an SDK call instead of a shell.
  • Agents, desktop and keys built in. On CodeSandbox SDK you build the harness, the browser and the desktop yourself, and keys go in as environment variables inside a machine the agent controls, where one prompt injection can leak them.
  • Hosting beyond HTTPS. CodeSandbox SDK hosts are HTTPS only and public unless you set them private, so databases, game servers or SSH tunnels an agent starts cannot be reached from outside.

Questions people ask

Is bochka cheaper than CodeSandbox SDK?

In four of the five scenarios on this page, yes, by a wide margin. For 1,000 short jobs at once neither fits: CodeSandbox SDK's Scale plan comes to $1,632 a month but caps at 250 VMs, and bochka's $2,000 plan queues the starts.

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.

Can bochka hibernate a sandbox with its memory like CodeSandbox SDK?

No. bochka saves the disk every minute and when the sandbox stops, so files survive, but resuming boots the machine again. CodeSandbox SDK resumes from a memory snapshot with processes still running.

Can I SSH into a CodeSandbox SDK sandbox?

Its docs list the SDK, Node and browser clients as the ways to connect, through terminals, commands and files, with no SSH. Every bochka sandbox has SSH as well as an exec and files API.

Can I run Docker and Android emulators in each?

Both run Docker inside the sandbox. bochka also exposes /dev/kvm for Android emulators and VMs, while CodeSandbox SDK does not document nested virtualization on its Firecracker VMs.

Is bochka SOC 2 compliant?

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

Start a sandbox

Install the CLI, then run bochka new.

Product preview

More comparisons

Bochka product preview · Pricing, benchmarks and commands are illustrative. Sandbox provisioning is not connected.