An NVMe system disk in front.
The operating system, the database and the index live on flash. Only the bulk sits on spindles, which is where bulk belongs.
Enterprise HDD for the bulk, an NVMe system disk in front of it. For the data you need to keep rather than the data you need to serve fast.
Size your server
Store 6
3 tiers
| Plan | vCPU | RAM | HDD | System | Transfer | Port | Ready in | Price | Order |
|---|---|---|---|---|---|---|---|---|---|
| Store 2 Backups, archives, seedboxes | 2 | 8 GB | 2 TB | 60 GB NVMe | Unlimited | 1 Gbps | ~3 min | $24$19/mo | Deploy Store 2 |
| Store 6 Media libraries, off-site replicas | 4 | 12 GB | 6 TB | 80 GB NVMe | Unlimited | 1 Gbps | ~3 min | $59$47/mo | Deploy Store 6 |
| Store 12 Long retention, large file hosting | 4 | 16 GB | 12 TB | 120 GB NVMe | Unlimited | 2 Gbps | ~3 min | $99$79/mo | Deploy Store 12 |
Every tier: NVMe system disk · 1 IPv4 · routed IPv6 /64 · always-on DDoS filtering · unlimited transfer · full API. Past twelve terabytes, a storage server is cheaper per terabyte.
What bulk costs
Nobody needs NVMe for a backup they read twice a year. Paying flash prices for cold data is the most common way to overspend on hosting — so the bulk is HDD, and the part you touch every day is not.
An NVMe system disk in front.
The operating system, the database and the index live on flash. Only the bulk sits on spindles, which is where bulk belongs.
Enterprise drives, not shucked desktop.
CMR, rated for continuous duty, replaced on SMART warning rather than on failure. A rebuild you never notice is the whole point.
Unlimited transfer, seriously.
A storage server you cannot read from is a paperweight. There is no egress meter and no fair-use clause hiding one.
Three minutes, not sixty seconds.
The bulk volume is carved and attached before you get the credentials. It is the one line here that is not instant, and we would rather say so.
No upsells
No protected-IP tier, no per-snapshot charge, no support plan to buy.
Full root, KVM
Real hardware virtualisation. Your own kernel, Docker, nested VMs, sysctl. Not a container wearing a server costume.
IPv4 + a routed /64
One IPv4 on every plan, more on request, and a whole /64 of IPv6 so you never subnet a /128.
DDoS filtering
Layer 3/4 scrubbing upstream of the port, on by default, at no charge and with nothing to enable.
Two snapshot slots
Take one before you break something. Restore in under a minute, as often as you like.
Custom ISO and console
Mount any image, including your own hardened build, and watch it boot over the serial console.
API and SSH keys
Provision, resize, snapshot and destroy from your own code. Keys installed at order time, password login off.
Before you order
Anything else, support answers in minutes — and says no plainly when the answer is no.
Open a ticketYes. Both are ordinary workloads here — see how complaints are handled for what that means in practice. The transfer is unlimited and the port is not shaped.
It is redundant at the array level, but redundancy is not a backup: it survives a dead disk, not a wrong rm. Keep a copy somewhere else, ideally with a different provider.
Sequential reads land between 150 and 200 MB/s, which saturates a gigabit port. Random I/O is what spindles are bad at — that is what the NVMe system disk is for.
Then this is the wrong line. A storage server starts at 64 TB raw and costs less per terabyte than stacking these. Support will do the arithmetic with you.
The rest of the range
Same jurisdiction, same network, same refusal to ask who you are. They differ on the one thing named in each title.
Ready when you are
No account needed to see every price, no identity needed to order. $24 a month gets you a server nobody can talk us into switching off.