Orion AI Factory
NVIDIA B200 GPU cloud and token-priced inference hosted in Serbia
Orion AI Factory rents NVIDIA B200 capacity from a data center in Belgrade, in fractions of a GPU from 0.25x (48 GB) up to a full 192 GB card, billed per hour. It also sells pay-as-you-go inference over a REST API for a short list of open models, metered per input and output token. The service is run by Orion telekom d.o.o. and sold to businesses, with access set up through a sales form and a service agreement. Trial access is reviewed on request.
Pricing: Hourly
Choosing a GPU cloud right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a GPU cloud right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Orion AI Factory Alternatives
Explore 154 products in the Inference APIs category. View all Orion AI Factory alternatives.
CoreWeave
GPU cloud infrastructure built for large-scale AI training and inference workloads
Hetzner GPU Servers
Dedicated single-GPU servers with NVIDIA RTX PRO Blackwell cards, billed hourly, in Finland and Germany
Mistral
Use models in a few clicks with our platform. Download our open models for deep access.
Work on Orion AI Factory? Feature it at the top of Inference APIs.
Is your product missing?