Pay for what you run.
Create your free account and deploy models from Hugging Face or our catalog. We manage the infrastructure; you choose the model and pay for your deployment's compute capacity.
Choose how you want to explore pricing
Estimate infrastructure for a specific model, compare our GPU inventory directly, or check rates for public models.
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 guidePublic 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.
Run this 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.
Create a deploymentAll GPU configurations
Live infrastructure price per GPU hour
1592 configurations
All GPU configurations
Live infrastructure price per GPU hour
€0.01/h
Limited capacity
€0.03/h
Limited capacity
€0.03/h
Limited capacity
€0.03/h
Limited capacity
€0.03/h
Limited capacity
€0.03/h
Limited capacity
€0.04/h
Limited capacity
€0.04/h
Limited capacity
€0.04/h
Limited capacity
€0.04/h
Limited capacity
Showing 1-10 of 1572
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 09/17/2026, 08:07:33 UTC
How billing works
Creating an account is free. You only need to add a card when you are ready to deploy a model. You pay for compute capacity for as long as your deployment is active.
- Free account, no card required
- Creating your account is free. You can explore the platform and model catalog. You do not need to add a card while deciding what to deploy. Add it only when you are making your first deployment.
- Compute billed by the second
- You pay for compute capacity while your deployment is active. The hourly GPU rate is prorated by the second. The rate is fixed when the instance starts. It does not depend on tokens.
- You control active time
- An active instance incurs charges even when it receives no requests. Stop the deployment when you no longer need it. Review charges and balance in the platform. Your account invoices are available there as well.
If you use public models that are already deployed, the input and output inference rates listed above apply. Storage and other resources are billed at their own rates.
Read the billing guideHow to start building with QDivZero
Choose your model and prepare the deployment in one place. Work with image, text, video, audio-generation, and embedding models, and much more. We manage the infrastructure, so you do not need to configure servers or maintain GPUs.
Create your free account
Sign up with your email address and explore the platform and catalog without a card. Add it only when you are ready for your first deployment.
Choose the model you want to use
Choose a model from Hugging Face or our catalog. We check compatibility and prepare the resources you need.
Add your card and deploy
Add your card and credit when you are ready to deploy. QDivZero manages the infrastructure and provides the endpoint for your application.
Ready to run a model?
Open your free account, choose the model that fits, and prepare the launch at your own pace. You only need a card when you decide to activate it.