Servers, bandwidth, and inference on one invoice.

Every resource on the Carpathian platform carries a published rate. Your invoice is the sum of the ones you are running, prorated to the day you add or release each one, and it arrives as a single monthly bill rather than a set of separate charges to reconcile.

carpathian.ai / dashboard / billing

Base Spark instance

ComponentIncludedMonthly
vCPU1 core$4.00
Memory1 GB$4.00
Disk20 GB$2.00
Network100 Mbps / 50 GBIncluded
Total$10.00 / mo
Prorated
To the day
Setup fee
None
Minimum
None
Invoices
Monthly

Price a footprint before you provision it

Set the resources, add as many instances as you plan to run, and the total updates against the same catalog rates the dashboard charges. The figure below is not an estimate or a starting-from number, it is what the configuration costs.

carpathian.ai / dashboard / provision

Configure Spark instances

Resources per instance1 vCPU / 1 GB / 20 GB
vCPU$4.00 / mo
Cores1 of 32
Memory$4.00 / mo
Gigabytes1 of 64
Disk$2.00 / mo
Gigabytes20 of 2000
How many1 instance
Instances1 of 10

Every instance in this configuration gets the same resources. Mixed sizes are priced the same way, one instance at a time.

Network

Bandwidth is billed once per network and shared by every server on it, so the plan above covers all 1 instance rather than being charged against each one.

Monthly costprorated to the day
$10.00per month
vCPU1 x $4.00$4.00
Memory1 GB x $4.00$4.00
Disk20 GB x $0.10$2.00
Network100 Mbps / 50 GB 100 Mbps 50 GB included, shared by all 1 instanceIncluded
Total$10.00 / mo

Provision partway through a month and the first invoice covers only the days remaining, then $10.00 a month after that. There is no setup fee and no minimum term.

What each component costs

Every resource is priced on its own, so memory scales without dragging cores along with it and disk grows without pushing you to the next size up. These are the live catalog rates, read from the same source the dashboard bills against.

Compute and memory
ComponentMonthly
Intel i7 vCPU CorePer core$3.00
Intel i9 vCPU CorePer core$15.00
Intel Xeon vCPU CorePer core$28.00
MemoryPer GB$4.00
DiskPer GB$0.10
Storage
ComponentMonthly
Object StoragePer GB$0.25
Integrated HDD StoragePer 100 GB block$5.00
Block HDD StoragePer 100 GB block$10.00
Integrated SSD StoragePer 100 GB block$55.00
Block SSD StoragePer 100 GB block$80.00
Databases
ComponentMonthly
Redis DatabasePer month$6.00
MySQL DatabasePer month$8.00
PostgreSQL DatabasePer month$8.00
MongoDB DatabasePer month$12.00

Two ways to run

A Spark instance is a virtual machine on a compute node we own and keep well under capacity. A Quasar instance is a physical machine of your own, for workloads that would rather not share anything.

Spark instance

Virtual machines with full root access, built from the components above and resized whenever the workload changes.

$10.00per month to start
  • vCPU, memory, and disk scale independently
  • Ubuntu, Debian, CentOS, or Windows Server
  • SSH, RDP, or screen sharing from the first boot
  • Standard disk images you can export at any time

Every instance includes the base network tier, monitoring, and DDoS mitigation.

Quasar instance

In development

Dedicated bare metal with an optional GPU, managed by Carpathian and configured in the builder the same way a Spark instance is.

$75.00per month to start
  • A physical machine rather than a share of one
  • Hardware maintained and replaced by Carpathian
  • Configured component by component, as Spark is

Dedicated hardware is expensive to overprovision, so start with what the workload needs and scale up as it grows. Quasar is not yet available to provision.

Network plans

Every instance arrives with a base speed tier and data allowance. Beyond that, a network plan belongs to your organization rather than to a machine, so every server on the network shares one plan instead of each carrying its own bandwidth charge.

100 Mbps / 50 GB

100 Mbps with 50 GB of data

Includedwith every instance

500 Mbps / 500 GB

500 Mbps with 500 GB of data

$8.00per month

1 Gbps / 3 TB

1 Gbps with 3 TB of data

$25.00per month

Unlimited data

An add-on to any speed tier. The data allowance comes off and the speed you chose stays.

$120.00per month

When you reach the data allowance

You decide in advance what happens, and the setting belongs to the organization rather than to an individual server. Neither option interrupts anything or takes a machine offline.

  • Throttle mode
    The default. Speed drops to the base tier until the next billing cycle and nothing further is charged, so the invoice cannot move on you.
  • Overage mode
    Opt in and full speed continues past the allowance, with the additional usage billed and capped at $120 a month.
carpathian.ai / infra / network path
traffic on the active pathtraffic on the standby pathdevice reporting healthy

AI inference rates

Models are metered per million input and output tokens at the rate published for each one. Usage lands on the same monthly invoice as your infrastructure, with no separate AI subscription and no minimum spend.

ModelInput / 1MOutput / 1M
Osprey 1.0 (32K Context)Medium32K token context window$0.50$1.25

Medium grade

Enhanced reasoning and deeper analysis. Grades group models by capability and cost, and every one of them is reachable through the same API key and the same endpoint.

What the price includes

No setup fees
Provisioning a resource costs nothing beyond its monthly rate
No minimum term
Release a resource and billing for it stops that same day
One invoice
Infrastructure, bandwidth, and AI usage on a single monthly bill
Published rates
Every figure on this page is the rate the dashboard charges

Why the rates look the way they do

The hardware is ours. It sits in our own racks in a Midwest datacenter, and much of it is equipment retired on a depreciation schedule rather than because anything failed, rebuilt to spec and burned in before it carries a workload.

Because we are not servicing the cost of new equipment or reselling somebody else's capacity, the difference shows up in the rate rather than in a margin. That is also why the rate can stay put: there is no promotional period to expire and no second-year price to discover.

  • Compute nodes we own, in a facility our own staff can walk into
  • Node density kept low, so a busy neighbour is not your problem
  • One team accountable from the metal up to the application
carpathian.ai / infra / rack elevation

Questions about billing

How is my monthly bill calculated?
Every resource on the platform has a published monthly rate. Your invoice is the sum of the rates for the resources you are running, prorated to the day you add or remove each one, and it arrives as a single bill rather than a set of separate charges.
Am I billed for CPU time, requests, or traffic?
No. Compute is priced by the resources you reserve rather than by how hard you use them, so an instance that runs flat out all month costs the same as one that sits idle. There is no per-request billing and no compute overage line.
What happens if I add or remove a resource partway through the month?
The change is prorated to the day. You are billed for the days a resource existed and nothing more, and adding one carries no setup fee.
Is bandwidth billed per gigabyte?
Every instance includes a base speed tier and data allowance. Beyond that you choose a network plan for your organization, and the plan covers every server on that network rather than being charged per machine. When you reach the data allowance you either drop to the base speed until the next billing cycle, which is the default and costs nothing extra, or opt into overage billing and keep full speed.
Do I need a contract or a minimum term?
No. There is no minimum term, no setup fee, and no cancellation fee. Billing is monthly, and you can change or release resources whenever you want.
How is AI usage priced?
Per million input tokens and per million output tokens, at the published rate for each model. Usage is added to the same monthly invoice as your infrastructure, so there is no separate AI subscription to manage.
Can I price a configuration before I commit to it?
Yes. The instance builder on this page prices any combination of vCPU, memory, disk, and bandwidth against the same catalog rates the dashboard charges, so the figure you see there is the figure you are billed.
What is a Quasar instance?
A Quasar instance is dedicated bare metal hardware rather than a share of a compute node, managed by Carpathian and configured the same way a Spark instance is. It is still in development and is not yet available to provision.

Configure it, price it, then deploy it.

Create an account, build the footprint you priced above, and have it running with an IP address and root access in minutes. Nothing on the invoice will be a component you did not choose.