Pay for what you run.

Public models with published inference rates

Use pre-deployed models without selecting or running a GPU. Rates are shown in EUR per 1 million input and output tokens as a standard usage reference, and charges are calculated from recorded inference usage.

Read the Public Models guide
Public models with published inference rates
ModelResidencyInput rate / 1MOutput rate / 1M
deepseek-v3.2Global€0.35€1.43
deepseek-v3.2-europeanEuropean Union€0.81€2.18
gpt-oss-120b-europeanEuropean Union€0.34€1.37
gpt-oss-safeguard-120b-europeanEuropean Union€0.34€1.37
gpt-oss-20b-europeanEuropean Union€0.09€0.39
gpt-oss-safeguard-20b-europeanEuropean Union€0.09€0.39

Public Models use metered inference pricing at the published input and output rates. Compute below is separate and bills active GPU time.

Estimate GPU cost for a model

Search for a Hugging Face model to estimate the VRAM it needs and see compatible infrastructure at current GPU-hour prices. This is a GPU compute estimate, not token or API pricing for the model.

Model-based GPU estimate

Choose a model or quantized GGUF variant to estimate VRAM and GPU cost

Browse GPU prices directly

Already know the GPU or VRAM you need? Browse this inventory independently of the model estimate above. Compare live capacity, location, market type, and the infrastructure price per GPU hour.

All GPU configurations

Live infrastructure price per GPU hour

1796 configurations
Region
Market
Tier
VRAM
RTX 407012 GB
spotcommunityEurope, GB

€0.02/h

Limited capacity

4x RTX 306012 GB × 4 = 48 GB
spotcommunityNorth America, US

€0.03/h

Limited capacity

2x RTX A20006 GB × 2 = 12 GB
spotcommunityEurope, NO

€0.04/h

Limited capacity

GTX TITAN X12 GB
spotcommunityAsia, KR

€0.04/h

Limited capacity

RTX 306012 GB
spotcommunityAsia, KR

€0.04/h

Limited capacity

RTX A20006 GB
spotcommunityEurope, NO

€0.04/h

Limited capacity

RTX 3060 Ti8 GB
spotcommunityEurope, FR

€0.04/h

Limited capacity

2x RTX 306012 GB × 2 = 24 GB
spotcommunityAsia, TH

€0.04/h

Limited capacity

4x GTX 16504 GB × 4 = 16 GB
spotcommunityNorth America, US

€0.05/h

Limited capacity

2x RTX 306012 GB × 2 = 24 GB
spotcommunityEurope, NO

€0.05/h

Limited capacity

Showing 1-10 of 1690

Page 1 of 169

What your deployment can include

Firewall and Smart Balancers are included with every deployment, so protection and resilient routing do not add a separate platform fee. Add Flexible Vector Database only when your application needs managed semantic retrieval.

Flexible Vector Database

Vector storage billed by GB-hour

€0.0010/GB/h

Firewall

Included

Smart Balancers

Included

Prices updated 9/7/2026, 6:03:05 AM

How billing works

Review how QDivZero records debits, balances, top-ups, and invoices across your account.

Read the billing guide

Ready to run a model?

Compare GPU capacity, choose the configuration your workload needs, and deploy on QDivZero.