- 类型
- 对比表 2 列 · 浅色 · AI
- 布局
- Two-column section with introductory content on the left and extensive instance-and-price tables alongside it.
- UX 模式
- Present dedicated inference as production-ready and autoscalCompare instance families, capacity, and hourly ratesLet users estimate costs before deployment
- UI 模式
- Eyebrow and prominent section headingShort explanatory paragraphLearn more link styled as an actionDense pricing tables grouped by hardware type
- 说明
- Inference Endpoints describes dedicated, secure model deployment from the HF Hub, starting at $0.033 per hour. Detailed tables enumerate instance families, resource sizes, and hourly prices to support infrastructure selection.
- 页面上的标题
- Dedicated inference, starting at $0.033/hour.
