AI Industry & Strategy
What Is a Neocloud? Why AI Chipmakers Are Becoming Cloud Providers
A new class of cloud provider called the neocloud has emerged to supply the raw GPU power that AI labs need and traditional cloud giants struggle to deliver fast enough. Understanding how neoclouds work, who funds them, and what risks they carry is essential for anyone trying to reason clearly about the AI infrastructure race.
Key takeaways
- Neoclouds are AI-first cloud providers that sell GPU compute almost exclusively, offering faster access and lower per-GPU costs than traditional hyperscalers by stripping away general-purpose services.
- NVIDIA has invested billions of dollars in multiple neocloud companies including CoreWeave and Nebius, creating a circular financing loop where investment capital is often used to purchase more NVIDIA hardware.
- Counterintuitively, the biggest customers of neoclouds include the hyperscalers themselves. Microsoft, Meta, and OpenAI have signed tens of billions of dollars in commitments to secure GPU capacity they cannot build fast enough on their own.
- The biggest risks for neoclouds are customer concentration, heavy debt loads, rapid GPU hardware obsolescence, and hyperscalers using custom AI chips and price cuts to erode the neocloud pricing advantage.
- The most likely long-term prediction is a bifurcated market where a few well-capitalized, software-capable neoclouds survive as a permanent infrastructure layer, while the weaker GPU rental businesses consolidate or exit.