Cloud platform
What is actually underneath the server you rent.
Virtual machines on SSD and NVMe disks, in 67 regions. Below is how it is put together, including the parts that are not finished.
Network
67 regions, and the price in each.
Deploy where your users are. Region choice is about latency and data residency: most plans cost the same in every location, and the few that are city-priced show that city's price before you deploy.
Europe
- Frankfurtfra
- Helsinkihel
- Amsterdamams
- Londonlon
- Parispar
- Nurembergnue
- Lauterbourglau
- Warsawwaw
- Madridmad
- Stockholmsto
- Copenhagencph
- Stavangersvg
- Manchesterman
- Milanmil
- Marseillemrs
- Athensath
- Sofiasof
- Bucharestotp
Middle East
- Dubaidxb
- Istanbulist
- Tel Avivtlv
- Dohadoh
- Bahrainbah
- Baghdadbgw
- Cairocai
Americas
- New Yorknyc
- Ashburnash
- Silicon Valleysfo
- Torontotor
- Vint Hill (VA)vin
- Hillsboro (OR)hil
- Sao Paulogru
- Santiagoscl
- Chicagoord
- Atlantaatl
- Los Angeleslax
- Miamimia
- Seattlesea
- Dallasdfw
- Washingtoniad
- Mexico Citymex
- Honoluluhnl
- Bogotabog
- Buenos Airesbue
- Quitouio
Asia-Pacific
- Singaporesgp
- Tokyonrt
- Mumbaibom
- Sydneysyd
- Bangaloreblr
- Osakaitm
- Hong Konghkg
- Melbournemel
- Seoulsel
- Delhi NCRdel
- Jakartacgk
- Chennaimaa
- Dhakadac
- Kathmanduktm
- Phnom Penhpnh
- Hanoihan
- Ho Chi Minh Citysgn
- Kuala Lumpurkul
- Manilamnl
- Bangkokbkk
- Taipeitpe
Africa
- Johannesburgjnb
- One dedicated IPv4 address
- The address belongs to the server for its whole life, including through a rebuild.
- Transfer is stated on every plan
- Each plan prints its monthly allowance before you buy, and the Unmetered line has no allowance at all. There is no private network between servers: traffic between two of your own servers uses their public addresses.
Compute
Real virtual machines, not containers in costume.
Every server is a KVM virtual machine with its own kernel. You can load kernel modules, run your own firewall, mount what you like and reboot into whatever you built. Nothing on the platform depends on you leaving the machine as we shipped it.
The processor family depends on the supplier and the city, and the configurator names it where the supplier states it. If you are sizing a fleet and need to know precisely what you are landing on, ask and we will tell you what serves that region today.
The Standard and Flex lines share physical cores between tenants, which is why they are cheap and why sustained full load is not guaranteed. The Dedicated CPU line does not share: those cores are pinned to your virtual machine and nobody else can take them.
Storage
Disks, and what happens when a host fails.
Every plan is on SSD, and a plan says NVMe only where its supplier states it; each plan page names which. We do not describe a storage layout a supplier has not published, so the spec names the disk and stops there.
If the host under a server fails, recovery is a restore, and we would rather say that plainly than bury it. Keep a backup: nightly backups are offered at 20% of the plan price on the plans and cities whose supplier runs them, and there is no snapshot button yet.
Backups
- Backups — nightly, 20% of the plan price
- Taken automatically every night, kept for 7 days and stored off the host that runs the server, so a host failure cannot take the backup with it. Switch it on in the configurator, where the plan and city offer it.
Images
Clean images, and a way to configure them before first boot.
Nothing is preinstalled that you did not ask for — no agents, no telemetry, no vendor packages you have to unpick later.
- Ubuntu 24.04 LTSubuntu-24.04
- Ubuntu 22.04 LTSubuntu-22.04
- Debian 12debian-12
- AlmaLinux 9almalinux-9
- Rocky Linux 9rocky-9
- Ubuntu 24.04 + Dockerdocker
- Windows Server 2022windows-2022
- Windows Server 2019windows-2019
A start-up script is accepted when the server is created, on the plans whose supplier runs one, so you can hand over an SSH key, a package list and a first-run script and have the machine ready before you log in. Rebuilding onto a different image takes about a minute and keeps the same IP address.
API
No public API yet.
The storefront and the panel run on our own internal API, but there are no customer tokens and no published reference today.
What a public API would cover, and how to tell us you need it, is on the developers page.
Limits
What the platform does not do.
Every provider has this list. Most of them keep it internal. Read it before you commit an architecture to us.
A host failure is a restore
If the host under your server fails, the server comes back from your most recent backup or from your own copy. Nothing on the platform promises to move a running machine to a healthy host, so plan your copies for that.
No snapshots or size changes from the panel
There is no snapshot button yet, so a copy before a risky change is yours to take. Changing size is a support request: we tell you whether your server can change in place and what it costs before anything is billed.
Regions cannot be changed in place
Moving a server from Frankfurt to Singapore means building a new one, copying your data across and cutting DNS over, on a schedule you choose.
Terms are prepaid and not pro-rated on early exit
Destroying a server before its term ends stops future billing but does not refund the remainder. Monthly terms keep that exposure small — that is why monthly is the default.
There is no live status feed yet
The status page is written by hand and dated. Per-region health checks and public incident history are being built.