Skip to content

razorBridge AI Blades

GPUs by the hour, SSH-ready.

Pick a GPU, see its price and billing minimum, and SSH in. Usually ready in a few minutes. Self-serve runs on a prepaid balance; universities and contracts pay by invoice.

From €1,09/h excl. VAT, 60-min minimum

How it works

Pick a GPU. See the price. SSH in.

Usually ready in a few minutes. Auto-stop means a forgotten GPU stops billing, and the Hub tells you how long your balance lasts before you launch.

  • Billed per second after a 60-minute minimum, excl. VAT.
  • A plain SSH host: scp, rsync and VS Code Remote work.
  • Multi-GPU classes are on the pricing page.

L4

24 GB VRAM

€1,09/h

first 60 minutes: €1,09 minimum

Light workloads & demos

L40S

48 GB VRAM

€1,99/h

first 60 minutes: €1,99 minimum

Training & workshops

H100

80 GB VRAM

€4,29/h

first 60 minutes: €4,29 minimum

Large model training

L4 for 1 h ≈ €1,09. Billed per second after a 60-minute minimum.

Drawn from the Hub's launch view. Prices are live; the layout is illustrative.

A real GPU over SSH

Each GPU is a plain host: ssh, scp, rsync and VS Code Remote work.

The price before you start

Every GPU shows its hourly price and its billing minimum in the Hub before you launch it.

Auto-stop

A forgotten GPU stops billing. Labs and events stop at their end time.

Shared or one each

Set how many students share a GPU, from one each to 20, per lab.

A REST API

Events, credits and the AI Gateway are also available through the REST API.

A company in the EU

KlusAI Labs SRL, Cluj-Napoca, Romania. The DPA names every sub-processor.

The Hub

This is the product, not a mock-up.

The razorBridge Hub is where you launch AI Blades, plan labs and events, and create API keys. Every GPU shows its price and its billing minimum before you start it.

The razorBridge Hub GPUs page: a card per GPU class with its hourly price and billing minimum, and a Launch button.

A screenshot of the razorBridge Hub with demo data.Built and operated by KlusAI Labs SRL, Cluj-Napoca, Romania.

Pricing

GPUs by the hour.

Prices per GPU per hour, excl. VAT. Each row shows the minimum a session bills.

GPU prices per hour, excl. VAT
GPUVRAMBest forMinimum per session€ per hour, excl. VAT
RTX 4000 Ada 20 GB Light workloads & demos Not available in the EU
L4 24 GB Light workloads & demos No minimum €1,09
L40S 48 GB Training & workshops No minimum €1,99
RTX 6000 Ada 48 GB Training & workshops Not available in the EU
MI300X 192 GB Large model inference Not available in the EU
H100 80 GB Large model training No minimum €4,29
H200 141 GB Large model training Not available in the EU
L40S x4Sold out in the EU right now 192 GB Large model training No minimum €7,99
L40S x8Sold out in the EU right now 384 GB Distributed training No minimum €15,99
MI300X x8 1536 GB Multi-GPU inference Not available in the EU
H100 x8Sold out in the EU right now 640 GB Multi-GPU workloads No minimum €29,99
H200 x8 1128 GB Multi-GPU workloads Not available in the EU
Prices exclude VAT. Universities and public bodies can pay by invoice.AI Gateway is priced per token, per model.
L4 L40S H100 L40S x4 · Sold out L40S x8 · Sold out H100 x8 · Sold out

Check availability on the pricing page

Apple SiliconComing soon

Unified-memory Macs for private inference.

Tell me when it's ready

Events and labs

A GPU lab for your class, in one link.

For courses, workshops and hackathons, built on AI Blades. You plan it, students join, and it cleans up after itself.

Illustrative live board

01 Plan

See the total first.

GPU, seats and hours. The estimate is the event's cost before VAT.

02 Share

A link and a QR code.

Students sign in and join. Nobody enters a card.

03 Done

It tears itself down.

GPUs stop at the end time.

What will it cost?

Your event Event type
GPU
People

Labs and workshops usually share a GPU between 5. Hackathon teams get one each.

Schedule

Your local time. You can choose a date later.

Questions

Straight answers.

Something else? Talk to us.

How does billing work?

Self-serve accounts use a prepaid balance. Each GPU bills at least 60 minutes, then per second, and AI models bill per million tokens. Universities and contracts pay by invoice. You see the price before every start.

Where do the GPUs run?

In EU data centres only, operated by EU-headquartered cloud providers.

What happens when a lab or event ends?

Its GPUs stop at the end time, and billing stops with them.

What happens when credits run out?

We email you when your balance falls below about an hour of runtime. When it runs out, a self-serve session stops automatically, and anything not saved off the blade is lost. To keep going, email us and we add credit to your balance.

Get started

Price it. Launch it.

It stops when you do. From €1,09/h excl. VAT, 60-min minimum.