Daytona vs Runloop
Daytona runs sandboxes as containers by default and sells Linux VMs, Windows and GPUs as extra classes, while Runloop puts every devbox in its own micro-VM. Daytona's VM class ran about 2.6 times faster on CPU and cost less in most scenarios, but Runloop fits big bursts that Daytona's resource pool does not.
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
Runloop
Runloop is a US platform of sandboxes, called devboxes, for building, running and testing AI coding agents.
You get Linux devboxes built from Dockerfile-style blueprints, disk snapshots, HTTPS tunnels, agent gateways that hide API keys, and Axons, event streams that drive agents such as Claude Code. Each devbox runs in a micro-VM on Runloop's own bare-metal hypervisor, with a container layer inside. It is built for teams shipping coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.
- Compliance
- SOC 2 Type 2
- Architectures
- x86_64 and arm64 base blueprints
- Own-cloud deploy
- Deploy to VPC on AWS, GCP and Azure (Enterprise)
- Regions
- Not documented or selectable
- Company
- Runloop AI, Inc.
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 | Runloop: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month All three fit; Daytona ranks 15th and Runloop 20th, and bochka ranks 3rd with Docker, a desktop and /dev/kvm on every machine. | 15th cheapest of 367 $4,111 a month | 20th cheapest of 367 $8,152 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 24th cheapest of 366 $6,104 a month | 32nd cheapest of 366 $10,194 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 runs better than Runloop, creating hundreds of sandboxes a minute with no plan fee; bochka's start limits make big bursts a compromise. | 25th cheapest of 345 $271 a month | 44th cheapest of 345 $525 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 300 sandboxes of 2 vCPU at once need 600 vCPU, more than Daytona's Tier 4 pool of 500 vCPU, while Runloop publishes no such cap and fits. | 154th of 361, with limits $2,000 a month | 26th cheapest of 361 $3,301 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 Runloop ranks 4th for RL rollouts: it starts large waves with no published concurrency cap, while Daytona's vCPU pool makes it a compromise. | 130th of 360, with limits $8,261 a month | 4th cheapest of 360 $15,922 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 | 81st cheapest of 364 $2,562 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 Daytona caps one sandbox at 4 vCPU by default, so bigger CI jobs need a raised limit; Runloop fits, and bochka's faster CPUs finish builds sooner. | 308th of 377, with limits $805 a month | 121st cheapest of 377 $1,554 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 183rd of 368, with limits $245 a month | 113th cheapest of 368 $410 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 Both ship a desktop an agent can control: Daytona on Linux and Windows, Runloop on Linux; bochka streams a 60fps desktop you can embed in your app. | 26th cheapest of 369 $1,198 a month | 39th cheapest of 369 $2,306 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 | 40th cheapest of 367 $1,153 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 | 68th cheapest of 346 $781 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 | 266th of 338, with limits $15,611 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 | 10th cheapest of 360 $770 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 Runloop 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 | Runloop | bochka |
|---|---|---|---|
| Isolation | Container by default; Linux VM and Windows VM classes with their own kernel | Micro-VM on a custom hypervisor for every devbox, plus a container layer | 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 | 8.29 runs/s | 26.69 runs/s |
| Docker and nested virtualization | Docker in all classes; /dev/kvm only on Linux VMs, and KVM must be turned on for your organization | Docker-in-Docker blueprints as root; nested virtualization not documented | Docker, root, systemd and /dev/kvm on every machine |
| Pause and fork | Linux VM and Windows: pause, resume and fork with memory kept; containers: no pause or fork | Suspend and resume on the Pro plan; disk snapshots | Fork a running sandbox; resume reboots from disk (no memory snapshots) |
| Files after a stop | The disk is kept and billed while stopped; archived containers are free | Disk kept through suspend (Pro) or manual disk snapshots; shutdown ends the devbox | Snapshots every minute and on stop; a stopped sandbox costs nothing |
| Custom images | Docker images and declarative builds for containers; VM snapshots from an image | Blueprints built from Dockerfiles, plus disk snapshots | Named snapshots (templates), shareable by code; no Dockerfile builds |
| CPU architecture | No arm64 listed | x86_64 and arm64 | x86_64 only |
| GPUs and Windows | Nvidia and AMD GPUs, on-demand or preemptible; Windows VM sandboxes | No GPUs; Linux only | No GPUs; no Windows guests, Wine for Windows apps |
| Desktop and computer use | VNC desktop (xfce4) and a computer-use API on Linux and Windows | A desktop and a browser your agent can control | 60fps desktop and Chromium, computer use and browser control, embeddable stream |
| Reaching the sandbox | HTTPS preview URLs on any port, token-protected or public; SSH; no raw TCP or public IP | One HTTPS tunnel per devbox, open or bearer token, with wake on request (Pro); SSH through a TLS proxy; no public IP | 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; Tier 3 and up get open internet plus domain or CIDR allowlists | Open internet, or a hostname allowlist with wildcards, or block all | 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 | Agent gateways for any API endpoint with bearer, header or basic auth | AI credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Coding agents | Guides install agents and run them through process exec | Claude Code, Codex, OpenCode, Gemini CLI, DeepAgents, driven through Axons and Broker | Claude Code, Codex, pi, OpenCode and more preinstalled, with a prompt, steer and events API |
| Where it runs | US and EU, plus dedicated regions or your own machines | Regions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise) | EU only: Germany, Finland, France, with EU data residency |
Every feature Battleships tracks (43)
| Feature | Daytona | Runloop | bochka |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | Yes | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | 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 | Yes | No |
| Wake on request | No | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | 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 | Yes | 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 | No | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Not published | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
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, Daytona's Linux VM class 21.52 and Runloop 8.29. That puts Daytona's VM class about 2.6 times faster than Runloop, and bochka about 3.2 times faster than Runloop. Daytona's default container class 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.
| Scenario | Daytona, a month | Runloop, 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) | $113 · Basic | $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) | $429 · Basic | $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) | $5,268 · Basic | $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 | $1,441 · Basic | $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 | $3,184 · Basic | $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).
Runloop: Runloop bills per second for CPU and memory while a devbox is starting, running, suspending or resuming, and bills its disk for the devbox's whole life. Basic has no plan fee; Pro adds $250 a month that is not usage credit and unlocks suspend and resume.
Runloop: Plans start at $20 a month and the whole fee is usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Daytona limits the total vCPU running at once, from 10 vCPU on Tier 1 to 500 on Tier 4, so 300 sandboxes for your users (600 vCPU) and 1,000 short jobs at once (2,000 vCPU) do not fit without a custom limit. It also caps one sandbox at 4 vCPU / 8 GB by default and opens the internet only from Tier 3. Runloop publishes no concurrency cap on paid plans, so both fit there, but its fixed lifetime tops out at 48 hours unless you set an idle policy, and its disk tops out at 64 GiB. On bochka the limit that bites is start rate, so the 1,000-job burst gets queued.
| Scenario | Daytona | Runloop | bochka |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| 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 agents need GPUs, Windows or memory pause and fork, or must run in the US or on your own machines.
- GPUs and Windows. Useful if your agents test models or need Windows: Daytona rents Nvidia and AMD GPUs by the hour and runs Windows VM sandboxes.
- Pause and fork with memory. Daytona's VM classes pause, resume and fork with memory kept, so a sandbox picks up exactly where it was.
- Faster CPU than Runloop. In the same benchmark, Daytona's Linux VM class did 21.52 runs per second and Runloop 8.29, so builds and tests finish sooner.
Use Runloop when
you launch very large bursts of short jobs, want a VM for every devbox without picking a class, or need arm64, Dockerfile builds or devboxes inside your own cloud.
- A VM for every devbox. Every Runloop devbox runs in its own micro-VM, while Daytona's default class is a container that shares the host kernel.
- Room for big bursts. Runloop publishes no concurrency cap on paid plans, so 1,000 short jobs at once fit where Daytona's 500 vCPU pool does not.
- arm64, Dockerfiles and your own cloud. Runloop builds devboxes from Dockerfiles, offers arm64, and on Enterprise runs inside your own AWS, GCP or Azure account.
Where bochka fits
If your agents do real work for hours, with installs, builds, tests, Docker and emulators, look at bochka as well. Every bochka sandbox is a full VM with /dev/kvm on a faster CPU, its files are saved every minute, and coding agents come built in. Pick Daytona for GPUs or Windows, and Runloop for huge bursts of short jobs.
A full VM with /dev/kvm on every machine
Daytona's default container shares the host kernel, and /dev/kvm needs its VM class plus KVM turned on for your organization. Runloop does not document nested virtualization, so an Android emulator or a VM inside may not start at all.
The fastest CPU of the three
bochka did 26.69 runs per second, Daytona's VM class 21.52 and Runloop 8.29. Each install, build and test an agent waits on takes about a quarter longer on Daytona and about three times as long on Runloop.
Files kept, stops free, a real address
Daytona keeps billing a stopped disk, and a Runloop devbox is gone at shutdown unless you pay for Pro suspend or write snapshot code. Neither offers raw TCP or a public IP; bochka gives HTTPS on 50 ports, raw TCP and its own IP.
Use bochka when your agents do real work for hours: installs, builds, tests, Docker and emulators on the fastest full VM of the three, with files kept and coding agents built in. Compare it one to one: bochka vs Daytona and bochka vs Runloop.
Questions people ask
Is Daytona cheaper than Runloop?
In most of the scenarios we priced, yes: one coding agent on workdays comes to $56 a month on Daytona and $113 on Runloop, and 50 agents in parallel to $2,682 versus $5,268. For 300 sandboxes for your users, Runloop fits at $1,441 a month and Daytona needs a custom limit. On bochka the same workday agent comes to $20 a month.
Which is faster, Daytona or Runloop?
On CPU, Daytona's Linux VM class did 21.52 runs per second and Runloop 8.29 in the same benchmark at 4 vCPU / 8 GB. Daytona's default container class reported no result. bochka did 26.69.
Are Daytona and Runloop sandboxes containers or VMs?
Daytona's default class is a Linux container, with Linux VM and Windows VM classes that have their own kernel. Runloop runs every devbox in a micro-VM with a container layer inside. On bochka, every sandbox is a full VM.
Can Daytona or Runloop run Docker and Android emulators?
Both run Docker. Daytona offers /dev/kvm only on its Linux VM class, once KVM is turned on for your organization, and Runloop does not document nested virtualization. bochka exposes /dev/kvm on every machine, so emulators and VMs run inside.
Can I limit which websites a sandbox can reach?
On both, yes. Runloop lets a devbox reach only the hostnames you list, or nothing at all. Daytona allows domain or CIDR allowlists from Tier 3, and on Tier 1 and 2 only package registries, git hosts and AI APIs are reachable. bochka has open internet on every plan and no provider-side allowlist.
Do Daytona or Runloop have GPUs?
Daytona does: it rents Nvidia and AMD GPUs from RTX 4090 to B300, on demand or preemptible. Runloop and bochka have no GPUs.
Try bochka
Install the CLI, then run bochka new.
Product preview