Hugging Face adds H200 inference endpoints at $5 per GPU-hour with one-click deploy recipes

lhoestq · x · 2026-11-21

Hugging Face announced that NVIDIA H200 GPUs are now available on its Inference Endpoints service at just $5/hour per GPU.

The company ships optimized one-click deployment recipes, letting developers deploy open models on H200s without managing their own GPU clusters.

Original post →

More from Infra

Infra channel →