bochka vs Daytona

Daytona runs sandboxes as containers by default and sells Linux VMs, Windows and GPUs as extra classes. bochka gives every sandbox its own VM with Docker, a desktop and coding agents built in, and it costs less in most of the scenarios below.

Where bochka stands out

A full VM for every sandbox

On bochka every sandbox has its own kernel, with root, systemd, Docker and /dev/kvm ready. On Daytona the default is a container that shares the host kernel. Its Linux VM class closes that gap, but it is built only from VM snapshots, and KVM must be turned on for your organization.

Faster CPU in the same test

In the same public benchmark run at 4 vCPU / 8 GB, bochka did 26.69 runs per second and Daytona's Linux VM class did 21.52. bochka also finished the Better Auth install, lint, build and test workflow first. Daytona's default container class reported no result in that run.

Coding agents built in

bochka ships Claude Code, Codex, pi, OpenCode and other agents inside each sandbox, and you drive them from outside with a prompt, steer and events API. On Daytona you install the agent yourself and run it as a process. bochka's credentials proxy also keeps real AI keys out of the sandbox and can switch to another account when one runs out of credits.

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.

Daytona

Daytona is a cloud for running AI-generated code: you create sandboxes from code through its API and SDKs.

By default a Daytona sandbox is a Linux container with its own namespaces and reserved vCPU, memory and disk. You can also pick a Linux VM class (pause, fork, memory snapshots, /dev/kvm), a Windows VM class, or a GPU class with Nvidia and AMD cards. It is built for teams that run agent code, code interpreters and evals through Python, TypeScript, Ruby, Go or Java SDKs.

Founded
2023

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 rankDaytona: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Both fit; bochka has Docker, a desktop and nested virtualization on every machine, while on Daytona you choose the Linux VM class to get pause, fork and /dev/kvm.
3rd cheapest of 367
$634 a month
15th cheapest of 367
$4,111 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
Both fit; bochka keeps each assistant on its own VM by default, while Daytona needs its Linux VM class to avoid a shared kernel.
5th cheapest of 366
$657 a month
24th cheapest of 366
$6,104 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Daytona fits one-minute runs better: it creates up to 300 to 600 sandboxes a minute with no plan fee, while bochka's start limits make big bursts a compromise.
186th of 345, with limits
$2,000 a month
25th cheapest of 345
$271 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
300 sandboxes of 2 vCPU at once need 600 vCPU, more than Daytona's Tier 4 pool of 500 vCPU, so it needs a custom limit there.
Cheapest of 361
$209 a month
154th of 361, with limits
$2,000 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
34th of 360, with limits
$2,000 a month
130th of 360, with limits
$8,261 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
189th of 364, with limits
$2,000 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Daytona caps a sandbox at 4 vCPU by default, so an 8 vCPU CI job needs a raised limit; bochka allows 8 vCPU from the $20 plan.
4th cheapest of 377
$86 a month
308th of 377, with limits
$805 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
18th cheapest of 368
$26 a month
183rd of 368, with limits
$245 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Both fit: Daytona has VNC and a computer-use API on Linux and Windows, and bochka streams a 60fps desktop you can embed in your app.
6th cheapest of 369
$200 a month
26th cheapest of 369
$1,198 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
7th cheapest of 367
$200 a month
93rd of 367, with limits
$598 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
38th cheapest of 346
$404 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
202nd of 338, with limits
$8,073 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
12th cheapest of 360
$2,000 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Only Daytona fits: it rents GPUs by the hour, and bochka has no GPUs.
Can't run it20th cheapest of 98
$1,190 a month
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

FeaturebochkaDaytona
IsolationEvery sandbox is a full VM with its own kernelContainer by default; Linux VM and Windows VM classes on request
CPU speed (Node.js build-and-test, 4 vCPU / 8 GB)26.69 runs/s21.52 runs/s on the Linux VM class; the default container class reported no result
Docker and nested virtualizationDocker, root, systemd and /dev/kvm on every machineDocker in all classes; /dev/kvm only on Linux VMs, and KVM must be turned on for your organization
Desktop and computer use60fps desktop and Chromium, computer use and browser control, embeddable streamVNC desktop (xfce4) and a computer-use API on Linux and Windows
Files after a stopSnapshots every minute and on stop; a stopped sandbox costs nothingThe disk is kept and billed while stopped; archived containers are free
Pause and forkFork a running sandbox; resume reboots from disk (no memory snapshots)Linux VM and Windows: pause, resume and fork with memory kept; containers: no pause or fork
Custom imagesNamed snapshots (templates), shareable by code; no Dockerfile buildsDocker images and declarative builds for containers; VM snapshots from an image
Reaching the sandboxHTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4HTTPS preview URLs on any port, token-protected or public; SSH; no raw TCP or public IP
Outbound internetOpen internet on every plan; no provider-side allowlistTier 1 and 2 reach only package registries, git hosts and AI APIs; Tier 3 and up get open internet plus per-sandbox domain or CIDR allowlists
Keeping keys out of the sandboxAI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run outSecrets proxy swaps placeholders in HTTPS request headers for allowed hosts
Coding agentsClaude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events APIGuides install agents and run them through process exec
GPUsNoneNvidia and AMD GPUs, on-demand or cheaper preemptible
WindowsNo Windows guests; Wine for Windows appsWindows VM sandboxes in three sizes
RegionsEU only: Germany, Finland, FranceUS and EU, plus dedicated regions or your own machines (BYOC)
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)
FeaturebochkaDaytona
Full VM (own kernel)YesNo
Docker insideYesYes
Nested virtualizationYesYes
RootYesYes
SystemdYesNot published
Desktop GUIYesYes
BrowserYesYes
Computer-use APIYesYes
SSHYesYes
Persistent diskYesYes
Pause/resumeYesYes
Automatic snapshotsYesYes
Fork/cloneYesYes
Live fork (no pause)YesNo
Memory forkNoYes
Custom image (Docker or snapshot)YesYes
≥24 h sessionsYesYes
Idle auto-stopNoYes
Wake on requestNoNo
HTTPS preview URLsYesYes
Raw TCP inboundYesNo
Public IPv4NoNo
Egress allowlistNoYes
Secret proxyYesYes
Secret proxy for any APIYesYes
Preinstalled agentsYesYes
Agent harness APIYesNo
MCP serverNoYes
GPUNoYes
WindowsNoYes
Arm64NoNo
Self-hostingNoNo
BYOCNoYes
Open sourceNoNo
Scoped API keysYesYes
Spend limitsYesNot published
Usage per sandbox (API)YesYes
Audit logsNoYes
SSONoYes
SOC 2NoYes
HIPAANoYes
EU data residencyYesYes
Zero data retentionYesNot published

Performance

bochka26.69 runs/s
Daytona21.52 runs/s

In StarSling's public run of 2026-09-29, at 4 vCPU / 8 GB, bochka did 26.69 Node.js build-and-test runs per second and Daytona's Linux VM class did 21.52. Daytona's default container class was also in that run but reported no result, so there is no CPU number for the class most Daytona sandboxes use.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Daytona measured on: Linux VM sandbox (same rates; KVM / nested virt per-org feature).

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 monthDaytona, 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$56 · Tier 3 ($500 top-up)
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$26 · $20/mo$245 · Tier 3 ($500 top-up)
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$2,682 · Tier 3 ($500 top-up)
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$2,000 · Tier 4 ($2,000 top-up every 30 days) · 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$2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits

bochka: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Daytona: Daytona bills per second for the vCPU, memory and disk you reserve, including while a sandbox is starting or stopping, and keeps billing the disk while it is stopped. You pay from a prepaid wallet: open internet needs a $500 top-up (Tier 3), and the biggest pool needs $2,000 every 30 days (Tier 4).

Limits in those scenarios

Daytona limits the total vCPU, memory and disk running at once, not the number of sandboxes: 10, 100, 250 or 500 vCPU from Tier 1 to Tier 4. That is why 300 sandboxes for your users (600 vCPU) and 1,000 short jobs at once (2,000 vCPU) do not fit even Tier 4 without a custom limit. On bochka the limit is a sandbox count (100 to 2,000 by plan) plus starts per minute, so the 1,000-job burst gets queued and needs more starts per day than the $2,000 plan allows. Daytona also caps one sandbox at 4 vCPU / 8 GB by default and only opens the internet from Tier 3.

ScenariobochkaDaytona
One coding agent, workdaysNone that bite
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
One agent that never stopsNone that bite
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
50 agents in parallelNone that bite
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
Sandboxes for your usersNone that bite
  • max 500 vCPU running at once (needs 600)
  • max 1,000 GiB running at once (needs 1,200)
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)
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)
  • max 500 vCPU running at once (needs 2,000)
  • max 1,000 GiB running at once (needs 4,000)
  • egress price not published
  • Tier 1 (email verified), Tier 2 (card + $25 top-up) reach only an allowlist (package registries, git, AI APIs)

Which one should you use?

Use Daytona when

your agents need GPUs or Windows, or must run in the US or on your own machines.

  • GPUs by the hour. Useful if your agents train or test models: Daytona rents Nvidia and AMD GPUs by the hour, from RTX 4090 to B300.
  • Windows and memory pause. Useful if you need Windows desktops, or a sandbox that pauses and comes back with its memory: Daytona's VM classes do both.
  • Network rules, US region, your own machines. From Tier 3 a sandbox can be limited to chosen domains, and Daytona also runs in the US and on your own machines.

Use bochka when

your agents do real work for hours: installs, builds, tests, Docker and emulators on a full, faster VM with a desktop and coding agents built in.

  • A full VM for every sandbox. A container shares the host kernel, so a kernel bug is a way out for code an agent wrote, and emulators need /dev/kvm. On Daytona you avoid both only by choosing the VM class and getting KVM turned on.
  • Faster CPU in the same test. At 21.52 runs per second against 26.69, every install, build and test takes about a quarter longer on Daytona's VM class, and you pay for the waiting. Its default containers have no measured number at all.
  • Coding agents built in. Without a driving API you write and maintain the code that starts, prompts and watches each agent yourself. When an account runs out of credits, bochka switches the credential, so the agent keeps working instead of stopping.

Questions people ask

Is bochka cheaper than Daytona?

In most of the scenarios we priced, yes: one coding agent on workdays comes to $20 a month on bochka and $56 on Daytona, and one agent running all month comes to $26 versus $245. 50 agents in parallel come to $317 versus $2,682. For 1,000 short jobs at once, both land at $2,000 and neither fits without higher limits.

Are Daytona sandboxes containers or VMs?

Both. The default class is a Linux container with its own namespaces and reserved resources. Daytona also offers Linux VM and Windows VM classes with their own kernel, which add pause, fork and memory snapshots. On bochka, every sandbox is a full VM.

Does bochka have GPUs or Windows like Daytona?

No. bochka has no GPUs and no Windows guests; it runs Linux VMs on AMD Ryzen 9 9950X machines and has Wine docs for Windows apps. If you need GPUs or a Windows desktop, Daytona has both.

Can Daytona sandboxes reach the internet?

On Tier 1 and Tier 2, only a list of essential services is reachable, such as package registries, git hosts and AI APIs. Open internet starts at Tier 3, which needs a $500 top-up, and from there you can set allowlists per sandbox. bochka sandboxes have open internet on every plan.

Where does my data run?

bochka runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. Daytona offers US and EU regions, plus dedicated regions and custom regions on your own machines.

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. Daytona says on its pricing page that it meets HIPAA, SOC 2 and GDPR standards.

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.