Urgent.News

What's breaking now, across thousands of outlets.

AI

Introducing Anthropic models on Amazon Bedrock for in-region inference in Seoul and Singapore

Amazon Bedrock now supports Anthropic's Claude Opus 5 and Claude Sonnet 5 with in-region inference in Seoul, and Claude Sonnet 5 in Singapore. If you have local data processing requirements in South Korea or Singapore, you can now use these Anthropic models at scale, with inference processed entirely within the Region you call.

Amazon Bedrock now offers in-region inference for Anthropic's Claude Opus 5 and Claude Sonnet 5 models in Seoul and Singapore. This allows for strict data residency requirements, as inference is processed entirely within the specified AWS Region, without leaving it. This feature is ideal for industries like financial services, healthcare, and the public sector in South Korea and Singapore.

To use this feature, one can access the models through the bedrock-runtime endpoint, which supports Anthropic's Messages API, InvokeModel API, and Converse API. The Anthropic Messages API can be accessed either through the Amazon Bedrock console or programmatically using AWS SDK, Boto3, or the Anthropic SDK package. The Claude models can be invoked using the direct model ID, such as anthropic.claude-opus-5 or anthropic.claude-sonnet-5.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Also reported by 2 other outlets

Read the original at aws.amazon.com →

More in AI

5 Ways to Reduce Voice AI Costs Without Losing Quality

1. Cache Your Synthesized Audio One of the biggest drivers of cost in voice AI is the sheer number of API calls you make to a TTS provider.

  • Cache synthesized audio to avoid repeated API charges
  • Batch requests and use parallelism to reduce overhead
  • Optimize text length and pacing to cut audio costs

I tried to learn GitHub Actions twice: I failed the first time, but AI helped me succeed the second time

The first time I tried to deploy a static site using GitHub Actions, I gave up halfway through the tutorials. The second time, with the help of an AI agent, I had the site deployed in several hours…

  • Author failed first GitHub Actions attempt due to brief tutorials
  • AI agent helped author understand GitHub Actions deployment
  • AI setup GitHub Actions, leading to successful second attempt

More from Wednesday 30 September →