1 個回答
- 最新
- 最多得票
- 最多評論
0
When you deploy a SageMaker model, it deploys it behind a SageMaker endpoint for real-time inference. You are charged by the second for on-demand ML hosting. Check the model deployment section of each region on the SageMaker Pricing page. In some use cases, you can save on inference cost by hosting several models behind the same endpoint (check this blog post).
已回答 4 年前
相關內容
- 已提問 6 個月前
- 已提問 1 年前
- AWS 官方已更新 2 年前
- AWS 官方已更新 1 年前