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.
More from Infra
- JapanFold on Tenstorrent silicon predicts 1M+ protein structures powering Anthropic design contest — DavidBennett__ · 2026-11-21
- DeepSeek-V4.1-Flash on one Apple M5 Ultra 512GB: steady 101 tok/s decode up to 256K context — HankYeomans · 2026-11-21
- Keysight Q4 orders jump 53% to $2.34B as AI testing demand still outruns supply — BenBajarin · 2026-11-21
- Micron CEO: customer demand over next five years exceeds what we could commit — Beth_Kindig · 2026-11-21
- 2026 WebAI Summit Posts 25 Talks, 8 Per Week, Keynoted by Google's Jason Mayes — jason_mayes · 2026-11-21
- Tenstorrent hits 5,300 tokens/sec/user decoding gpt-oss-120b on just 8 Galaxy units — DavidBennett__ · 2026-11-21