Cloud VPS

Virtual machines sized for every workload.

Choose shared vCPU for sites and side projects, or dedicated vCPU for production apps, analytics and in-memory databases. Every machine gets SSD storage, its own IPv4 address and root access.

  • From $12 / month
  • Shared or dedicated vCPU
  • SSD and NVMe storage
  • Dedicated IPv4
vCPU per machine
1–48
RAM on the largest memory-optimized size
256 GB
RAM per vCPU on memory-optimized plans
8 GB
RAM-to-vCPU ratio on CPU-optimized plans
2:1

Cloud VPS

Pick a family and size

Basic plans share CPU threads; general purpose, CPU-optimized and memory-optimized plans use dedicated vCPU.

Choose a location

Same price in both locations. Your choice is added to the quote request.

Basic 1 GB

$12/ month

CPU
Shared
vCPU
1
RAM
1 GB
Storage
25 GB SSD
Transfer
1,000 GB
Get started

General purpose

$252/ month

CPU
Dedicated
vCPU
4
RAM
16 GB
Storage
50 GB SSD
Transfer
5,000 GB
Get started

CPU-optimized

$336/ month

CPU
Dedicated
vCPU
8
RAM
16 GB
Storage
100 GB SSD
Transfer
6,000 GB
Get started

Memory-optimized

$336/ month

CPU
Dedicated
vCPU
4
RAM
32 GB
Storage
100 GB NVMe
Transfer
6,000 GB
Get started

Prices in USD, billed monthly unless stated otherwise. Need a different size? Ask for a custom configuration.

What you get

Built in, not bolted on.

Shared or dedicated vCPU

Shared plans cost less and handle bursty traffic well. Dedicated plans reserve whole vCPU threads, so performance holds steady under constant load.

Resize when you need to

Move a machine to a larger size as your app grows, or add more machines and spread the load between them.

Snapshots and backups

Take a snapshot before a risky change, schedule automatic backups, and launch new machines from any saved image.

Firewall and monitoring

Decide which ports each machine exposes with firewall rules, and track CPU, memory and disk metrics with alerts when something drifts.

Private networking

Machines in the same region talk over a private network. Back-end servers can run with no public IP at all.

Your OS, your tools

Start from Ubuntu, Debian, AlmaLinux, Rocky Linux or Fedora, use a ready image with Docker or a LAMP stack, or upload a custom image.

Use cases

What teams run on it.

  • 01

    Web apps and APIs

    Run storefronts, SaaS back ends and busy sites on general purpose machines with a balanced CPU-to-RAM ratio.

  • 02

    Databases and caches

    Memory-optimized sizes give each vCPU 8 GB of RAM, so working sets for PostgreSQL, Redis or MongoDB stay in memory.

  • 03

    Media and batch jobs

    CPU-optimized machines suit transcoding, analytics and batch processing that keep every core busy.

  • 04

    Dev and test environments

    Start a small shared-CPU machine for staging, CI runners or a VPN, and remove it when the work is done.

How it works

Three steps to running.

  1. 01

    Choose a size

    Pick the family and plan that fit your workload. You can move up later.

  2. 02

    Set it up

    Select Istanbul or Nuremberg, an operating system and your SSH key.

  3. 03

    Connect

    Log in over SSH with root access as soon as the machine is ready.

Questions

Cloud VPS, answered.

What is the difference between shared and dedicated vCPU?

Shared vCPU plans run on CPU threads that other machines can also use, which keeps the price low and suits bursty workloads. Dedicated plans reserve full threads for your machine alone, so performance stays consistent.

Which operating systems can I install?

Popular Linux distributions such as Ubuntu, Debian, AlmaLinux, Rocky Linux and Fedora, plus ready images for Docker and LAMP. You can also bring your own custom image.

Does every machine get a public IPv4 address?

Yes, each machine comes with its own public IPv4 address. If a workload should not be reachable from the internet, you can keep it on the private network only.

Can I change my plan later?

Yes. Resize to a larger plan when you need more CPU, RAM or disk, or scale out by adding machines behind a load balancer.

How does data transfer work?

Each plan includes a monthly outbound transfer allowance, listed with the plan. Inbound traffic is free.

What storage do the machines use?

All plans run on SSD storage, and memory-optimized plans use NVMe SSDs for faster disk access on transaction-heavy workloads.

More cloud

Often used together.

GPU Cloud Servers

Virtual servers with a full NVIDIA RTX PRO 6000 and 96 GB of VRAM for AI, rendering and simulation.

From $2,398 / month

Explore

GPU Dedicated Servers

Bare-metal servers with NVIDIA RTX PRO Blackwell GPUs, from one 24 GB card to four 96 GB cards.

From $477.22 / month

Explore

Managed Kubernetes

Kubernetes clusters with a managed control plane. You pick the worker nodes; we run the rest.

From $24 / month

Explore

Talk to an engineer

Not sure which size fits?

Tell us what you want to run. An engineer suggests a configuration and sends you a written price.