boat vs IONOS Cloud
IONOS Cloud is a German public cloud that rents plain KVM servers, with GPUs, Windows and US regions, and bills its Cubes by the minute. boat is built for AI agents: each sandbox is a VM with a desktop, coding agents and a credentials proxy built in, and a stopped one costs nothing.
Where boat stands out
Coding agents you drive from outside
boat 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. The credentials proxy keeps real AI keys out of the sandbox and can switch to another account when one runs out of credits. An IONOS server is an empty Linux VM: its MCP server manages IONOS resources, not agents inside them.
A desktop and browser for every agent
Every boat sandbox can stream a 60fps desktop with Chromium, and agents get computer use and browser control. You can embed the stream in your own app. IONOS offers a remote console to fix servers, not a desktop for agents.
Snapshots every minute, and free stops
boat snapshots each sandbox's disk every minute and on stop, and a stopped sandbox costs nothing. On IONOS a snapshot is a manual full copy of one volume, and IONOS says suspended Cubes continue to incur costs. You can also fork a running boat sandbox in one call.
The companies and products
boat
boat.dev 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.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
IONOS Cloud
IONOS Cloud is the public cloud of IONOS, a German hosting company in the United Internet group. It is a hyperscaler-style IaaS cloud, not an agent sandbox.
You rent KVM virtual machines: Cubes (fixed sizes from 1 to 16 vCPU with a local NVMe disk, billed by the minute), vCPU servers up to 60 vCPU and 230 GB of RAM, Dedicated Core servers and H200 GPU VMs. You build them in the Data Center Designer or through the Cloud API, SDKs and Terraform, next to block storage, private networks, firewalls and managed services. It is for teams that want to run their own servers in Germany, the rest of Europe or the US, and set up everything on them themselves.
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 workload | boat: price rank | IONOS Cloud: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month IONOS gives you a root Linux VM where Docker runs, but no desktop, coding agents or snapshots on a schedule, so you build the agent setup yourself. | 3rd cheapest of 367 $634 a month | 64th of 367, with limits $492 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant fits on an IONOS VM, but there is no driving API or credentials proxy, so you wire up the agent, its keys and its desktop yourself. | 5th cheapest of 366 $657 a month | 107th of 366, with limits $540 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month IONOS bills Cubes by the minute with no plan fee, which suits short jobs if you can create and delete VMs fast enough through its API. | 186th of 345, with limits $2,000 a month | 53rd of 345, with limits $27 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month 300 sandboxes at once on IONOS depends on account limits it does not publish; you raise them through IONOS Cloud Support. | Cheapest of 361 $209 a month | 35th of 361, with limits $182 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 | 9th of 360, with limits $740 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 | 93rd of 364, with limits $137 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Both fit CI runners: IONOS rents plain VMs by the minute, and boat allows 8 vCPU from the $20 plan with Docker and /dev/kvm. | 4th cheapest of 377 $86 a month | Cheapest of 377 $60 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that stays on all month is what IONOS is built for, and it comes with a public IPv4 address. | 18th cheapest of 368 $26 a month | 9th cheapest of 368 $20 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month IONOS has no desktop stream or computer-use tools, only a remote console for fixing servers, so you would install and stream a desktop yourself. | 6th cheapest of 369 $200 a month | 86th of 369, with limits $137 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 | 156th of 367, with limits $74 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 | 153rd of 346, with limits $40 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 | 39th of 338, with limits $897 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 | 105th of 360, with limits $38 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month IONOS rents H200 GPU VMs by the hour; boat has no GPUs. | 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 |
Key features
| Feature | boat | IONOS Cloud |
|---|---|---|
| Kind of product | Sandboxes for AI agents, made and driven through an API | General-purpose cloud servers (Cubes, vCPU and Dedicated Core servers) plus storage, networks and managed services |
| Isolation | Every sandbox is a full VM with its own kernel | Every server is a KVM VM with its own kernel |
| Docker and nested virtualization | Docker, root, systemd and /dev/kvm ready on every machine | Root Linux VM where you install Docker; running your own VMs inside is not documented |
| Stopping a machine | A stopped sandbox costs nothing and keeps its disk | A suspended Cube releases CPU and RAM, but IONOS says suspended Cubes continue to incur costs; to stop paying you snapshot and delete it |
| Snapshots | Automatic snapshots every minute and on stop | Manual full snapshots of a block storage volume, Essential class only, usable only in the same location |
| Fork | Fork a running sandbox in one call; the copy boots from disk | Snapshot a disk, then create new VMs from it; disk only, no memory |
| Desktop and computer use | 60fps desktop and Chromium, computer use and browser control, embeddable stream | None; a remote console for troubleshooting servers |
| Coding agents | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API | None in the VM; an MCP server lets your own AI client manage IONOS resources |
| Keeping keys out of the sandbox | AI credentials proxy for model providers and any HTTPS API you register; switch a credential to another account when credits run out | None; you put secrets into the VM yourself |
| Reaching the machine | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 | Public IP on each VM and any port you open; reserved IPv4 billed per 30 days; private LANs and load balancers |
| Network rules | Open internet on every plan; no provider-side allowlist | Network Security Groups with ingress and egress rules by IP, port and protocol |
| GPUs | None | NVIDIA H200 PCIe VMs, 1 to 8 GPUs |
| Windows | No Windows guests; Wine for Windows apps | Windows Server VMs with a licence billed per vCPU |
| Regions | EU only: Germany, Finland, France | Germany, UK, France, Spain and the US |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | Not published |
Every feature Battleships tracks (43)
| Feature | boat | IONOS Cloud |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Yes |
| Nested virtualization | Yes | Not published |
| Root | Yes | Not published |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | No |
| Computer-use API | Yes | No |
| SSH | Yes | Yes |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | Yes |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | Yes |
| Live fork (no pause) | Yes | Yes |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | Yes |
| Idle auto-stop | No | No |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No | Yes |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | Yes |
| Windows | No | Yes |
| Arm64 | No | No |
| Self-hosting | No | No |
| BYOC | No | No |
| Open source | No | No |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | Yes |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Not published |
| HIPAA | No | No |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement for IONOS Cloud. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's public benchmark, on dedicated AMD Ryzen 9 9950X (Zen 5) hosts. IONOS was not in that run, and its CPU model varies by location.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. IONOS Cloud 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 | boat, a month | IONOS Cloud, 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 | $5 · Pay as you go |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $20 · Pay as you go |
| 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 | $240 · Pay as you go |
| 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 | $74 · Pay as you go · 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 | $148 · Pay as you go · with limits |
boat: 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.
IONOS Cloud: IONOS bills Cubes by the minute at a fixed rate per size, with the NVMe disk included, and vCPU servers per core and per GB of RAM. Suspended Cubes keep billing, so the low workday figure assumes you snapshot and delete the machine each night; reserved IPv4 addresses, extra storage and traffic past 2 TB a month cost extra.
Limits in those scenarios
IONOS does not publish how many machines a fresh account can run at once; you ask IONOS Cloud Support to raise the limits. That is why 300 sandboxes for your users and 1,000 short jobs at once are not confirmed there. On boat 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. One IONOS Cube tops out at 16 vCPU and 64 GB, and a vCPU server at 60 vCPU and 230 GB.
| Scenario | boat | IONOS Cloud |
|---|---|---|
| One coding agent, workdays | None that bite | None that bite |
| One agent that never stops | None that bite | 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 IONOS Cloud when
you need GPUs, Windows Server, UK or US data centers, or plain servers that sit next to the rest of your cloud.
- H200 GPUs. Useful if your agents train or serve models: IONOS rents NVIDIA H200 VMs with 1 to 8 GPUs.
- Windows, the UK and the US. Useful if you need Windows Server or servers in the UK or US: IONOS has both.
- A whole cloud with firewall rules. Useful if agents must sit next to your databases and private networks, behind IP and port firewall rules.
Use boat when
your agents need a ready machine: coding agents you drive by API, a desktop and browser, keys kept outside, and snapshots every minute with free stops.
- Coding agents you drive from outside. On IONOS you install each agent, copy real API keys into the VM and write the code that starts, prompts and watches it. A prompt injection that reads the keys gets the real ones.
- A desktop and browser for every agent. Agents that click through web apps need a screen. On IONOS you would install a desktop, a VNC or WebRTC server and a browser on each VM, and keep that image up to date yourself.
- Snapshots every minute, and free stops. An agent that breaks its machine at minute 50 loses work unless someone took a snapshot. On IONOS, stopping the bill means a snapshot, a delete and a rebuild each time.
Questions people ask
Is boat cheaper than IONOS Cloud?
No, IONOS's list prices are lower in every scenario we priced: one agent running all month comes to $26 on boat and $20 on IONOS, and 50 agents in parallel come to $317 against $240. IONOS's workday figure assumes you delete the machine each night, since suspended Cubes keep billing. Sandboxes for your users and 1,000 short jobs at once are not confirmed on IONOS, because it does not publish its account limits.
Is IONOS Cloud a sandbox for AI agents?
No. IONOS Cloud is a general-purpose public cloud that rents KVM servers, storage and networks. You can run an agent on one of its VMs, but you install the agent, the desktop and the key handling yourself. boat gives you all three ready in each sandbox.
Does boat have GPUs or Windows like IONOS Cloud?
No. boat has no GPUs and no Windows guests; it runs Linux VMs on dedicated AMD Ryzen 9 9950X hosts and has Wine docs for Windows apps. IONOS rents H200 GPU VMs and Windows Server VMs.
Are both in the EU?
Yes. boat runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. IONOS is a German company with data centers in Germany, France and Spain, and also in the UK and the US.
Does a stopped machine cost money?
On boat, no: a stopped sandbox costs nothing and keeps its disk. IONOS says suspended Cubes continue to incur costs, and suggests snapshotting the disk and deleting the Cube to stop paying.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Oracle Cloud
- boat vs AWS AgentCore
- boat vs Contabo
- boat vs Azure Virtual Machines
- boat vs AWS Fargate
- boat vs netcup
- boat vs AWS EC2
- boat vs Gcore
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- AWS EC2 vs IONOS Cloud
- Google Compute Engine vs IONOS Cloud
- Azure Virtual Machines vs IONOS Cloud
- Oracle Cloud vs IONOS Cloud
- DigitalOcean vs IONOS Cloud
- Hetzner Cloud vs IONOS Cloud
- Vultr vs IONOS Cloud
- Linode vs IONOS Cloud