Daytona vs exe.dev
Daytona is a sandbox platform you drive from code: containers by default, with Linux VM, Windows and GPU classes when you need them. exe.dev rents persistent Linux VMs you reach over SSH and HTTPS, from a reserved pool or by the second, in nine regions.
The companies and products
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
exe.dev
exe.dev, made by Bold Software, Inc., rents Linux VMs for developers and AI agents that you reach over SSH and HTTPS.
You reserve a pool of vCPUs and memory, and your VMs share it; you can also start standalone VMs billed by the second. Each VM is KVM-isolated (they use Cloud Hypervisor), boots from a container image in about two seconds, and has root, systemd and Docker. It comes with Claude Code, Codex, Pi and exe.dev's own Shelley agent, and is aimed at developers who want a persistent dev box or a sandbox for their agents.
- Company
- Bold Software, Inc.
- Preinstalled agents
- claude, codex, pi and the Shelley web agent
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. “15th cheapest of 367” means 14 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 | Daytona: price rank | exe.dev: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Daytona fits a software factory fully with its Linux VM class, pause and fork; exe.dev runs the code but has no desktop or snapshots, and bochka fits with both built in. | 15th cheapest of 367 $4,111 a month | 253rd of 367, with limits $3,701 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Both fit always-on assistants: exe.dev's flat pool keeps a VM running all month, Daytona bills every running second, and bochka keeps each assistant on its own VM. | 24th cheapest of 366 $6,104 a month | 15th cheapest of 366 $3,833 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 Daytona fits short code interpreter runs well, creating hundreds of sandboxes a minute with no plan fee; exe.dev and bochka are compromises there. | 25th cheapest of 345 $271 a month | 235th of 345, with limits $175 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 Neither fits 300 user sandboxes at once on its plans: Daytona's Tier 4 pool stops at 500 vCPU and exe.dev Personal at 50 VMs, while bochka fits. | 154th of 361, with limits $2,000 a month | 257th of 361, with limits $1,226 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 | 130th of 360, with limits $8,261 a month | 265th of 360, with limits $5,250 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 | 189th of 364, with limits $2,000 a month | 283rd of 364, with limits $1,050 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 Both are a compromise for CI: Daytona caps a sandbox at 4 vCPU by default, and exe.dev pools bill whether jobs run or not; bochka fits. | 308th of 377, with limits $805 a month | 288th of 377, with limits $504 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB exe.dev is the better 24/7 dev box of the two, with a flat pool and SSH; Daytona bills per second around the clock, and bochka fits with a desktop in the browser. | 183rd of 368, with limits $245 a month | 25th cheapest of 368 $35 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 Daytona has a VNC desktop and a computer-use API on Linux and Windows, exe.dev VMs are headless, and bochka streams a 60fps desktop. | 26th cheapest of 369 $1,198 a month | 240th of 369, with limits $1,055 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 | 93rd of 367, with limits $598 a month | 130th of 367, with limits $530 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 | 38th cheapest of 346 $404 a month | 124th of 346, with limits $278 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 | 202nd of 338, with limits $8,073 a month | 166th of 338, with limits $5,490 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 | 12th cheapest of 360 $2,000 a month | 60th of 360, with limits $263 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 Only Daytona fits: it rents Nvidia and AMD GPUs by the hour, and neither exe.dev nor bochka has GPUs. | 20th cheapest of 98 $1,190 a month | 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 | Daytona | exe.dev | bochka |
|---|---|---|---|
| Isolation | Container by default; Linux VM and Windows VM classes have their own kernel | KVM VM with Cloud Hypervisor; you can't choose the kernel | Every sandbox is a full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| CPU speed (Node.js build-and-test, 4 vCPU / 8 GB) | 21.52 runs/s on the Linux VM class; the default container class reported no result | Not measured | 26.69 runs/s |
| Docker and nested virtualization | Docker in all classes; /dev/kvm only on Linux VMs, once KVM is turned on for your organization | Root, systemd and Docker; nested virtualization on Enterprise only | Docker, root, systemd and /dev/kvm on every machine |
| Desktop and computer use | VNC desktop and a computer-use API on Linux and Windows | Headless; no desktop or screen streaming | 60fps desktop and Chromium, computer use and browser control, embeddable stream |
| Saved state | Disk kept and billed while stopped; Linux VM and Windows classes pause and fork with memory kept | Disk persists and is streamed to a second server; no snapshots; cp copies a VM | Snapshots every minute and on stop; fork a running sandbox; a stopped sandbox costs nothing |
| Custom images | Docker images and declarative builds for containers; VM snapshots from an image | Boot each VM from your own Docker image | Named snapshots as templates, shareable by code; no Dockerfile builds |
| Coding agents | Guides to install agents and run them through process exec | Claude Code, Codex, Pi and the Shelley agent preinstalled; only Shelley takes prompts through the API | Claude Code, Codex, pi, OpenCode and more preinstalled, with a prompt, steer and events API |
| Reaching the sandbox | HTTPS preview URLs on any port, token-protected or public; SSH; no raw TCP or public IP | HTTPS proxy for ports 3000 to 9999, one of them public; SSH; no public IP or raw TCP | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 |
| Outbound internet | Tier 1 and 2 reach only package registries, git hosts and AI APIs; open internet and per-sandbox allowlists from Tier 3 | Open internet | Open internet on every plan; no provider-side allowlist |
| Keeping keys out of the sandbox | Secrets proxy swaps placeholders in HTTPS request headers for allowed hosts | Integrations inject secrets at the network edge for any HTTP host, S3, GitHub and more | AI credentials proxy for model providers and any HTTPS API; switch to another account when credits run out |
| GPUs and Windows | Nvidia and AMD GPUs by the hour; Windows VM sandboxes | No GPUs, no Windows | No GPUs; no Windows guests, Wine for Windows apps |
| Regions | US and EU, plus dedicated regions or your own machines | 9 regions in the US, Europe, Asia and Australia | EU only: Germany, Finland, France |
| How you pay | Per second for reserved vCPU, memory and disk, from a prepaid wallet | Flat reserved pool shared by your VMs, or standalone VMs per second | Monthly plan from $20, all of it usage credit spent per second while sandboxes run |
| Session length | No cap; TTL is off unless you set it | No cap; VMs run until you stop them | No cap on paid plans; you set the TTL |
Every feature Battleships tracks (43)
| Feature | Daytona | exe.dev | bochka |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | Yes | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Yes | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | No | Yes | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | No | No |
| Wake on request | No | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | Yes | No |
| GPU | Yes | No | No |
| Windows | Yes | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | No | No |
| BYOC | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | No | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's public run of 2026-09-29 at 4 vCPU / 8 GB, Daytona's Linux VM class did 21.52 Node.js build-and-test runs per second and bochka did 26.69. Daytona's default container class reported no result in that run. exe.dev is not in that benchmark, so there is no comparable CPU number for it.
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). exe.dev 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 | Daytona, a month | exe.dev, 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 | $56 · Tier 3 ($500 top-up) | $35 · Personal | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $245 · Tier 3 ($500 top-up) | $35 · Personal | $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 | $2,682 · Tier 3 ($500 top-up) | $1,848 · Personal | $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 | $2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits | $530 · Personal · with limits | $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 | $2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits | $1,050 · Personal · with limits | $2,000 · $2000/mo · with limits |
Daytona: Daytona bills per second for the vCPU, memory and disk you reserve, and keeps billing the disk while a sandbox 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).
exe.dev: exe.dev Personal is a flat monthly pool, paid upfront, that bills the same whether its VMs are busy or idle. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB hour, and pay only for disk while stopped.
exe.dev: 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.
Limits in those scenarios
Daytona limits the total vCPU running at once, up to 500 vCPU on Tier 4, and also caps one sandbox at 4 vCPU / 8 GB by default. exe.dev Personal stops at 50 VMs at once in its pool, plus up to 50 standalone VMs. So neither fits 300 user sandboxes or 1,000 short jobs at once on the plans we priced. bochka fits the 300 user sandboxes, but its start-rate limits queue the 1,000-job burst too.
| Scenario | Daytona | exe.dev | bochka |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
| None that bite | None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Daytona when
your app creates many short sandboxes from code, or your agents need GPUs, Windows, or machines in the US or on your own hardware.
- Sandboxes from code, fast. Useful if you create many short sandboxes from your app: Daytona's SDKs create hundreds a minute with no plan fee.
- GPUs and Windows. Useful if agents test models or need Windows: Daytona rents Nvidia and AMD GPUs by the hour and runs Windows VM sandboxes.
- Pause with memory kept. Daytona's VM classes pause and fork with memory kept, so a resumed sandbox picks up exactly where it was.
Use exe.dev when
you want a persistent Linux VM that stays on all month at a flat fee, close to users in the US, Asia or Australia.
- A persistent box at a flat fee. Useful for a dev box that stays on all month: an exe.dev pool costs the same whether your VMs are busy or idle.
- A real VM with agents ready. Every exe.dev VM is KVM-isolated with root, systemd and Docker, and comes with Claude Code, Codex and Pi installed.
- Regions around the world. Useful if your users are far from Europe: exe.dev runs in nine regions across the US, Europe, Asia and Australia.
Where bochka fits
If your agents do long, real work like installs, builds, tests and UI checks, look at bochka. It gives every sandbox a full VM with a desktop and coding agents you drive from outside, which Daytona offers only in its VM class and exe.dev leaves headless.
A full VM with /dev/kvm, every time
Daytona's default is a container sharing the host kernel; its VM class needs KVM turned on for your organization. exe.dev runs real VMs, but nested virtualization is Enterprise only, so emulators and VMs inside wait for a sales call.
A screen and state saved every minute
exe.dev VMs are headless and have no snapshots, so a computer-use agent has no screen and a bad step can cost a session. Daytona has a VNC desktop, but keeps billing the disk of a stopped sandbox.
Drive agents inside from outside
On Daytona you install each agent and run it as a process. On exe.dev only Shelley takes prompts through the API. Either way you script the start, prompt and watch loop yourself, while bochka has one prompt, steer and events API.
Use bochka when your agents do real work for hours: builds, tests, Docker and emulators on a full, faster VM with a desktop, state saved every minute and one API to drive agents inside from outside. Compare it one to one: bochka vs Daytona and bochka vs exe.dev.
Questions people ask
Is Daytona cheaper than exe.dev?
In our scenarios, exe.dev's bill is lower: one agent running all month comes to $35 on exe.dev and $245 on Daytona, and 50 agents in parallel come to $1,848 against $2,682. bochka comes to $26 and $317 for the same two.
Which is faster, Daytona or exe.dev?
We can't say. Daytona's Linux VM class did 21.52 runs per second in StarSling's Node.js benchmark at 4 vCPU / 8 GB, but exe.dev is not in that benchmark. bochka did 26.69 in the same run.
Are Daytona and exe.dev sandboxes containers or VMs?
A Daytona sandbox is a container by default, with Linux VM and Windows VM classes that have their own kernel. Every exe.dev machine is a KVM VM using Cloud Hypervisor. bochka gives every sandbox a full VM.
Can Daytona and exe.dev run Docker?
Yes, both run Docker inside. For nested virtualization, Daytona needs its Linux VM class with KVM turned on for your organization, and exe.dev offers it only on Enterprise. bochka has /dev/kvm on every plan.
Do Daytona or exe.dev have a desktop for computer use?
Daytona has a VNC desktop and a computer-use API on Linux and Windows. exe.dev VMs are headless, with no desktop stream. bochka streams a 60fps desktop with Chromium that you can embed in your app.
Which has more regions?
exe.dev runs in nine regions across the US, Europe, Asia and Australia. Daytona runs in the US and EU, plus dedicated regions and your own machines. bochka runs only in the EU, in Germany, Finland and France.
Try bochka
Install the CLI, then run bochka new.
Product preview