KServe
Serve predictive and generative AI models on Kubernetes with standard inference resources.
What’s included for free?
KServe is ongoing-free under Apache-2.0 with no vendor inference quota; operators supply Kubernetes, models, accelerators and storage.
Where it runs: Self-hosted
Provider information ↗Checked 2026-11-01
Before you use it
Apache-2.0 covers KServe. Model servers, images, weights, clusters and cloud services retain separate terms.
Provider terms can change. Check current pricing and usage rights before starting a project.