# Amazon — Amazon SageMaker Inference: 2026 year-to-date launches in review

- Company: Amazon (amazon.com)
- Announced: 2026-09-18T20:52:14+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://aws.amazon.com/blogs/machine-learning/amazon-sagemaker-inference-2026-year-to-date-launches-in-review/
- Record: https://forck.live/items/12245-amazon-sagemaker-inference-2026-year-to-date-launches-in-review
- Subject: Bedrock / Nova
- Pricing: There is no additional cost for generating recommendations.

Amazon SageMaker AI delivered 13 new capabilities year-to-date in 2026 across managed endpoints and HyperPod Inference, including inference recommendations and benchmarking, capacity-aware instance pools, OpenAI-compatible APIs, and container caching to address deployment, scaling, observability, and latency challenges in generative AI inference.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/amazon-sagemaker-inference-2026-year-to-date-launches-in-review/:

> Year-to-date in 2026, SageMaker AI delivered 13 new capabilities across these two paths and this post walks through these capabilities and benefits to enterprises, startups and public sector.

---

Record: https://forck.live/items/12245-amazon-sagemaker-inference-2026-year-to-date-launches-in-review
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md