Announcing Amazon SageMaker Inference for custom Amazon Nova models
Amazon SageMaker ยท 2026-02-16
Actions
Technical Details
| Regions | us-east-1, us-west-2 |
|---|---|
| Cost Impact | Decrease |
What This Means
For DevOps Teams
Configure and deploy custom Nova models using Amazon SageMaker Inference, leveraging optimized GPU utilization and auto-scaling to reduce costs and improve performance.
For Platform Teams
Integrate Amazon SageMaker Inference for custom Nova models into your AI infrastructure to simplify architecture, reduce operational toil, and enable advanced AI capabilities.
For Executives
Evaluate deploying Amazon SageMaker Inference for custom Nova models to optimize inference costs and enhance AI capabilities, leading to improved operational efficiency and competitive advantage.
Source
Related Amazon SageMaker Updates
- NVIDIA Nemotron 3 Nano 30B MoE model is now available in Amazon SageMaker JumpStart (2026-02-11)
- Amazon SageMaker HyperPod now supports node actions from the console (2026-02-10)
- Cartesia Sonic 3 text-to-speech model is now available on Amazon SageMaker JumpStart (2026-02-04)
- Apache Spark lineage now available in Amazon SageMaker Unified Studio for IDC based domains (2026-02-04)
- DeepSeek OCR, MiniMax M2.1, and Qwen3-VL-8B-Instruct models are now available on SageMaker JumpStart (2026-02-02)