GitHub Codespaces vs Modal VM Sandboxes

GitHub Codespaces gives a developer a ready VS Code environment for a GitHub repository, kept between stops but cut off after 12 hours. Modal VM Sandboxes give your code short-lived VMs with their own kernel, made to start in huge numbers and gone within 24 hours.

The companies and products

GitHub Codespaces

GitHub Codespaces is GitHub's cloud development environment: a ready-to-code Linux machine for a repository, opened in the browser, VS Code or the GitHub CLI.

Codespaces is a different kind of product from bochka: a dev environment for people working on a GitHub repository, not a sandbox API for agents. Each codespace is a Docker container built from the repo's dev container config, running on its own newly built VM on Azure, with 2 to 32 cores. It is built for developers and teams who want every contributor to start from the same setup, with prebuilds, port forwarding and GitHub billing.

Isolation: A Docker container on its own newly built VM, with its own virtual network
Operating system: Linux only; Windows and macOS are not supported for the remote container
Machine sizes: 2, 4, 8, 16 or 32 cores, with 4 GB of memory per core
Lifetime: Stops after 30 idle minutes by default (5 to 240), and after 12 hours at most even while in use
Regions: US East, US West, Europe West and Southeast Asia
Free usage: Personal Free accounts get 120 core-hours and 15 GB-month a month, Pro 180 and 20; organizations get no free quota
Compliance: GitHub Enterprise Cloud lists SOC 1, SOC 2 and SOC 3 reports and ISO 27001

Modal VM Sandboxes

Modal is a serverless cloud for AI work, and VM Sandboxes are the version of its sandboxes that run in a virtual machine with their own Linux kernel.

You create a VM Sandbox from Python, TypeScript or Go code with runtime="vm", run commands in it, and terminate it when the job is done. Modal built the runtime on the Rust-based Cloud Hypervisor, so Docker, FUSE, systemd and nested cgroups work, with the same API, images and prices as its gVisor sandboxes. It became generally available on 1 October 2026 and suits teams that want many short-lived agent machines next to Modal's inference and training.

Founders: Erik Bernhardsson and Akshat Bubna
Offices: New York, Stockholm and San Francisco
Funding: Over $466M raised
Isolation: Virtual machine per sandbox on Cloud Hypervisor, with its own Linux 7.2 kernel
Generally available: 1 October 2026; early customers launched over 20 million VMs before that
Session length: Default 5 minutes, maximum 24 hours
Compliance: SOC 2 on every plan; HIPAA on Enterprise

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. “274th cheapest of 367” means 273 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	GitHub Codespaces: price rank	Modal VM Sandboxes: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both are compromises here: a codespace stops at 12 hours and documents no /dev/kvm, and a Modal VM ends within 24 hours and loses files outside a Volume, while bochka keeps its disk and adds a desktop.	274th of 367, with limits $4,618 a month	84th of 367, with limits $759 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant fits neither without restarts, since codespaces stop after 12 hours at most and Modal VM Sandboxes after 24, while bochka has no session cap on paid plans.	309th of 366, with limits $6,970 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 Modal's fast starts and per-second billing better than a codespace, which builds a dev container on a new VM each time.	288th of 345, with limits $619 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 Modal Team runs up to 5,000 containers at once, while GitHub does not publish how many codespaces can run at once, so 300 user sandboxes are not confirmed there.	281st of 361, with limits $1,964 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 Huge bursts of short rollouts are what Modal is built for and not what Codespaces is for, and bochka's per-plan start limits queue large bursts.	282nd of 360, with limits $9,489 a month	171st of 360, with limits $16,322 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	295th of 364, with limits $1,519 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 All three run Docker builds; /dev/kvm for Android emulators is not documented on Codespaces, is on request on Modal Team and Enterprise, and is on every bochka plan.	314th of 377, with limits $909 a month	188th of 377, with limits $1,064 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Codespaces is the closer fit for a human dev box, with VS Code per repo and a disk kept across stops, but it stops after 12 hours, while bochka keeps running.	130th of 368, with limits $270 a month	Can't run it	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: a codespace has an editor and a terminal, Modal shows how to set up Xvfb and VNC yourself, and bochka streams a 60fps desktop with Chromium.	267th of 369, with limits $1,367 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	275th of 367, with limits $678 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	310th of 346, with limits $922 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	280th of 338, with limits $18,637 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	267th of 360, with limits $445 a month	294th of 360, with limits $642 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 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	GitHub Codespaces	Modal VM Sandboxes	bochka
Isolation	A Docker container on its own newly built VM, with its own virtual network	A VM with its own Linux kernel on Cloud Hypervisor	A full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
How you use it	Opened from a repo, branch or pull request in VS Code, the browser, JupyterLab or the GitHub CLI	Created from Python, TypeScript or Go code with runtime="vm"	API and SDK to create, fork, stop and run commands, plus a desktop stream
Longest session	12 hours at most, even while in use; stops after 30 idle minutes by default	24 hours at most; default timeout 5 minutes	No cap on paid plans; you set the time to live
Files after a stop	Kept, with storage billed; stopped codespaces are deleted after 30 days by default	No paused state; only Volumes and snapshots keep files once a sandbox ends	Disk saved every minute and on stop; a stopped sandbox keeps it and costs nothing
Docker, root, systemd	Docker and sudo inside the dev container	Docker, systemd and root; you start dockerd yourself	Docker, root and systemd in every sandbox
Nested virtualization	/dev/kvm is not documented	Team and Enterprise plans only, on request	/dev/kvm on every plan
Copies and snapshots	No copy or snapshot endpoint; new codespaces start from a repo or a prebuild	Filesystem snapshots boot any number of copies; memory snapshots in alpha	Fork a running sandbox with its disk; named snapshots as templates; no memory snapshots
Desktop and computer use	Editor and terminal; no graphical desktop	Not offered; an example shows how to set up Xvfb and VNC yourself	60fps desktop, Chromium and a computer-use API built in
Coding agents and API keys	GitHub Copilot as a VS Code extension; secrets copied in as environment variables	Examples only; secrets are environment variables, or you run your own proxy in a sidecar	Claude Code, Codex and others preinstalled with a prompt, steer and events API; real keys stay outside through the credentials proxy
Reaching the machine	A URL per forwarded port, plus SSH and CLI tunnels; no public IP	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP
Outbound network rules	Open internet; GitHub says there is no way to restrict it	Block all, IP-range allowlist, domain allowlist (beta)	Open internet, no provider-side allowlist
CPU benchmark (4 vCPU / 8 GB)	Not measured	15.54 runs/s	26.69 runs/s
Regions	US East, US West, Europe West and Southeast Asia, same price in each	US, EU and Asia-Pacific plus narrower regions; pinning costs 1.15x to 1.75x	EU only: Germany, Finland, France
GPUs	None	None on the VM runtime; GPU sandboxes need gVisor	None

Every feature Battleships tracks (43)

Feature	GitHub Codespaces	Modal VM Sandboxes	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	No	Yes	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Yes	Yes
Desktop GUI	No	No	Yes
Browser	No	No	Yes
Computer-use API	No	No	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	No	No	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	No	Yes	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	No	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	No	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	No	Yes	Yes
Public IPv4	No	No	No
Egress allowlist	No	Yes	No
Secret proxy	No	No	Yes
Secret proxy for any API	No	No	Yes
Preinstalled agents	No	No	Yes
Agent harness API	No	No	Yes
MCP server	No	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	No	No	No
BYOC	No	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	No	Not published	Yes
Audit logs	Yes	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Yes	No
HIPAA	No	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

GitHub CodespacesNot measured

Modal VM Sandboxes15.54 runs/s

bochka26.69 runs/s

There is no comparable measurement for GitHub Codespaces: it was not in the public benchmark runs we use. In StarSling's run of 29 September 2026 at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 Node.js build-and-test runs per second and bochka did 26.69, about 1.7 times the CPU work in the same time, on dedicated AMD Ryzen 9 9950X hosts.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Modal VM Sandboxes measured on: VM Sandbox, request = size. GitHub Codespaces 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.

Scenario	GitHub Codespaces, a month	Modal VM Sandboxes, a month	bochka, 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	$51 · Personal account: GitHub Free	$15 · Starter · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$270 · Personal account: GitHub Free · with limits	$178 · Starter · with limits	$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	$3,019 · Personal account: GitHub Free	$2,229 · Starter · with limits	$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	$850 · Personal account: GitHub Free · with limits	$792 · Team	$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	$1,889 · Personal account: GitHub Free · with limits	$3,193 · Team · with limits	$2,000 · $2000/mo · with limits

GitHub Codespaces: Codespaces bills $0.09 per core-hour while a codespace is active, plus $0.07 per GB-month of storage while it exists, stopped too. There is no 4-core machine with 8 GB, so 4 vCPU / 8 GB jobs are priced on the 4-core 16 GB machine; personal accounts get a free monthly quota and organizations do not.

Modal VM Sandboxes: Modal bills by the second for the higher of the CPU and memory you request or what you use, until the sandbox ends. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and pinning a region multiplies the price by 1.15x to 1.75x.

Modal VM Sandboxes: bochka plans start at $20 a month and the whole fee becomes usage credit, spent by the second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Every codespace stops after 12 hours at most, so it does not fit the always-on scenario, and GitHub does not publish how many codespaces can run at once, so 300 user sandboxes and 1,000 short jobs are not confirmed. A Modal VM Sandbox lives at most 24 hours and its root disk is gone when it ends, so the workday, always-on and 50-agent scenarios keep only files in a Volume or a snapshot, and the 1,000-job burst runs on shared CPU above its small request. On bochka the limit that bites is start speed: even the $2,000 plan starts 90 sandboxes a minute, so 1,000 jobs at once queue and exceed the daily start limit.

Scenario	GitHub Codespaces	Modal VM Sandboxes	bochka
One coding agent, workdays	None that bite	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
One agent that never stops	Personal account: GitHub Free: sessions capped at 12 h	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
50 agents in parallel	how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
Sandboxes for your users	not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	None that bite	None that bite
1,000 short jobs at once	not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	shared vCPUs on this tier (Modal (VM Sandboxes) sells dedicated cores separately as “VM Sandbox, request = size”): 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 GitHub Codespaces when

your developers want a ready VS Code environment for a GitHub repository, opened from a branch or pull request, that keeps their files between work sessions.

Built into GitHub. Useful if your team lives on GitHub: open a codespace from any repo, branch or pull request, with the dev container set up.
A disk that survives stops. Useful for people who come back each day: a stopped codespace keeps its files and installed packages until you restart it.
Free hours for personal accounts. Useful for occasional personal work: a GitHub Free account includes 120 core-hours and 15 GB-month of storage each month.

Use Modal VM Sandboxes when

your code launches huge bursts of short jobs that finish within a day, needs strict outbound rules or regions outside Europe, or already runs models on Modal.

Very large bursts. Useful for huge bursts of short jobs: Modal runs 5,000 containers at once on Team, with fast starts and per-second billing.
Outbound rules and regions. Useful when agents must reach only chosen hosts: block all outbound traffic or allow set domains, in the US, EU or Asia-Pacific.
One platform with inference and training. Useful if you already serve or train models on Modal: sandboxes and models sit on one account and one bill.

Where bochka fits

If what you are really running is coding agents that work for hours or days, both fall short in the same places: they cut sessions off, ship no desktop and leave the agent setup to you. bochka gives each agent a full VM that keeps running, keeps its disk and comes with agents and a desktop ready.

Sessions that do not end

A codespace stops at 12 hours even while in use, and a Modal VM ends within 24 hours and loses its root disk. Either way you write restart or snapshot code. bochka has no session cap on paid plans and saves its disk every minute.

/dev/kvm, a desktop and open ports

Codespaces documents no /dev/kvm and no desktop. Modal gives /dev/kvm only on Team and Enterprise after you ask, and you install Xvfb and VNC yourself. bochka has /dev/kvm, a 60fps desktop and HTTPS on 50 ports on every plan.

Agents driven from outside, keys kept out

On both, secrets sit in environment variables any code the agent runs can read, and you script each agent yourself; Modal's fix is a proxy you run in a sidecar. bochka preinstalls the agents and keeps real keys outside.

Use bochka when your agents work for hours or days in a machine they come back to: a full VM with /dev/kvm, a desktop and open ports, built-in coding agents with keys kept outside, a disk saved every minute and no session cap on paid plans. Compare it one to one: bochka vs GitHub Codespaces and bochka vs Modal VM Sandboxes.

Questions people ask

Is GitHub Codespaces cheaper than Modal VM Sandboxes?

Mostly no. One agent running all month is $270 on Codespaces against $178 on Modal, 50 agents in parallel $3,019 against $2,229, and 300 user sandboxes $850 against $792; for 1,000 short jobs Codespaces is cheaper at $1,889 against $3,193. bochka comes to $26, $317 and $200 for the first three.

Which is faster, GitHub Codespaces or Modal VM Sandboxes?

We have no comparable CPU measurement for Codespaces. On the same benchmark at 4 vCPU / 8 GB, Modal's VM runtime did 15.54 runs per second and bochka did 26.69.

How long can each one run?

A codespace stops after 12 hours at most, even while in use, and after 30 idle minutes by default, but keeps its files. A Modal VM Sandbox defaults to 5 minutes and lasts 24 hours at most, and its root disk is gone when it ends. bochka has no session cap on paid plans.

Can I run Docker and Android emulators in each?

Both run Docker. Codespaces does not document /dev/kvm, and Modal offers nested virtualization on Team and Enterprise after you ask support. Every bochka machine has Docker, systemd and /dev/kvm.

Can I run Claude Code in GitHub Codespaces or Modal VM Sandboxes?

Yes, on both you install it yourself and pass your API key as a secret, which arrives as an environment variable. bochka ships Claude Code, Codex and others preinstalled, keeps the real keys outside the sandbox, and gives you one API to prompt, steer and watch them.

Where do they run?

Codespaces runs in US East, US West, Europe West and Southeast Asia. Modal runs in the US, the EU and Asia-Pacific, and pinning a region costs 1.15x to 1.75x. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview