DigestAI news desk

Cut through the AI noise.

Enterprise & Industry7 min read

AWS adds India-based inference for Kimi K3 on Bedrock

AWS announced on November 3 that its Bedrock platform now supports in-country inference for Kimi K3, a multimodal open-weight model from Moonshot AI. This allows customers with strict data residency requirements to process workloads within India’s AWS Mumbai and Hyderabad Regions, avoiding cross-border data transfers. Ultrahuman, a health and wellness app, reports 80% lower LLM costs and 85%…

1 source primary source

Key points

  • AWS Bedrock now offers Kimi K3 inference in India’s Mumbai and Hyderabad Regions for data residency compliance
  • Ultrahuman cuts LLM costs by 80% and speeds up chats by 85% using Kimi K3 in-country
  • Kimi K3 supports OCR, multilingual document processing, and structured output via JSON schemas

The feature enables cross-Region inference profiles, where requests originate from any AWS Region but are processed in eligible destination Regions. AWS handles encryption and routing securely, without requiring public internet exposure or VPC setup. Kimi K3 supports OCR, multilingual document understanding (including Indic languages and Hinglish), structured output via JSON schemas, and advanced features like tool calling. AWS provides code samples for document processing pipelines, prompt optimization, and caching to reduce costs and latency. Pricing includes a 50% discount for the flex tier and explicit caching modes for static prompts.

Full story from AWS Machine Learning Blog · by Naomi Teng primary sourceOpen source ↗

Introducing India-based inference for Kimi K3 on Amazon Bedrock

AWS Machine Learning Blog · 3 November 2026

Loading the full article…

This text was published by AWS Machine Learning Blog and written by Naomi Teng. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
AWSMoonshot AIUltrahumanKimi K3Aditya Patawari

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories