🚀 One API for every frontier model on FastInfra

Browse models

Transparent per-token pricing → compare providers on FastInfra

View pricing

OpenAI-compatible chat completions → start in minutes

Read the docs

⚡ Server Auction → Enterprise bare metal from $78.15/mo (173 in stock)

Browse deals

CCX53 cloud VPS 32 vCPU, 128 GB RAM

The CCX53 is a Linux cloud VPS with 32 vCPU, 128 GB RAM and 600 GB SSD (Dedicated AMD EPYC vCPU), from $1.09 per hour with a monthly cap of $681. It deploys in 6 regions (Falkenstein (DE), Helsinki (FI), Nuremberg (DE), Ashburn, VA (US), Hillsboro, OR (US) and Singapore (SG)) with root SSH access on Ubuntu or Debian, is billed per minute while it exists, and shows its exact price in the configurator before you sign in.

From $1.09 / hr Capped at $681 / mo 600 GB SSD Dedicated vCPU

Prices from the live catalog · billed per minute

At a glance

CCX53 specs and pricing

vCPU
32
Dedicated AMD EPYC vCPU
Memory
128 GB
RAM
Storage
600 GB
local SSD
Hourly from
$1.09
billed per minute
Monthly cap
$681
$21.27 per vCPU
Regions
6
EU, US, Singapore

CCX53 belongs to the CCX line of dedicated-vCPU servers: every vCPU maps to a reserved physical core thread, so performance stays consistent under sustained load. That makes it the right choice for production databases, build servers, game servers and CPU-bound batch jobs.

At $681 per month that works out to $21.27 per vCPU and $5.32 per GB of RAM. Price varies by region: Falkenstein (DE) is the cheapest at $681 per month and Singapore (SG) the most expensive at $832.

Pricing

CCX53 price by region

Live prices. Servers bill per minute at the hourly rate, up to the monthly cap shown in the configurator.

CCX53 price per region
RegionPer hourMonthly cap
Falkenstein (DE) $1.09 $681 Deploy
Helsinki (FI) $1.09 $681 Deploy
Nuremberg (DE) $1.09 $681 Deploy
Ashburn, VA (US) $1.10 $687 Deploy
Hillsboro, OR (US) $1.10 $687 Deploy
Singapore (SG) $1.33 $832 Deploy

What a CCX53 costs over time

In Falkenstein (DE), the cheapest region for this plan.

CCX53 cost by duration
DurationCost
1 hour$1.09
1 day (24 hours)$26.17
1 week (168 hours)$183
Full month$681
Use cases

What to run on a CCX53

  • Sustained CPU-bound workloads
  • Large databases and caches
  • Analytics and search clusters
  • Kubernetes nodes for many pods
  • CPU inference of small quantized LLMs
  • Parallel builds and batch jobs

Need AI inference? CPU servers are a poor fit for large language models. Use the pay-per-token inference API for hosted models, or rent a GPU pod billed per minute for custom models and fine-tuning. Single-tenant hardware is available as dedicated bare-metal servers.

Alternatives

CCX53 vs similar plans

Live lowest monthly cap across regions.

Cloud VPS plans similar to CCX53
PlanvCPURAMSSDCPU typeFrom / mo
CCX53 (this page) 32128 GB600 GBDedicated AMD EPYC vCPU$681
CX53 1632 GB320 GBShared x86 vCPU, cost-optimized$38.44
CAX41 1632 GB320 GBShared Arm64 vCPU, Ampere Altra$53.02
CPX51 1632 GB360 GBShared AMD EPYC vCPU$90.82
CPX62 1632 GB640 GBShared AMD EPYC vCPU$166
CCX43 1664 GB360 GBDedicated AMD EPYC vCPU$352
CCX63 48192 GB960 GBDedicated AMD EPYC vCPU$1,088
FAQ

CCX53 VPS — frequently asked questions

How much does the CCX53 VPS cost?

From $1.09 per hour, capped at $681 per month in Falkenstein (DE). Prices by region range up to $832 per month. Billing is per minute while the server exists, and the configurator shows the hourly and monthly figures before you deploy.

What are the CCX53 specs?

32 vCPU (Dedicated AMD EPYC vCPU), 128 GB RAM and 600 GB of local SSD storage, with a public IPv4 address and root SSH access.

Where can I deploy a CCX53?

In Falkenstein (DE), Helsinki (FI), Nuremberg (DE), Ashburn, VA (US), Hillsboro, OR (US) and Singapore (SG). Pick the region closest to your users; prices are listed per region on this page.

What can I run on a CCX53?

Typical workloads: Sustained CPU-bound workloads; Large databases and caches; Analytics and search clusters; Kubernetes nodes for many pods. Small quantized language models can run on CPU with llama.cpp, but for production LLM traffic a GPU pod or the pay-per-token inference API is far faster and usually cheaper.

Is the CCX53 shared or dedicated vCPU?

Dedicated. Each vCPU is reserved for your server, so performance does not depend on other tenants. That suits sustained CPU-bound work.

Which operating systems does the CCX53 support?

Ubuntu and Debian, deployed with root SSH access. Install Docker, a web stack or any Linux package after boot.

Deploy a CCX53 in minutes

Pick a region and OS, see the exact hourly and monthly price, and SSH in as root. Billed per minute, no commitment.