Amazon Bedrock 在首尔和新加坡推出 Anthropic 模型区域内推理

Amazon Bedrock now supports the Anthropic Claude models: Claude Opus 5 and Claude Sonnet 5 in Seoul and Claude Sonnet 5 in Singapore with in-region inference on the bedrock-runtime endpoint. If you have local data processing requirements in South Korea or Singapore, for example, in financial services, healthcare, and the public sector, you can now use these Anthropic models at scale. Amazon Bedrock processes inference requests and data within the Region you call. The processing does not leave the Region.

In-region inference

To help you meet strict data residency requirements for your AI applications, Amazon Bedrock offers in-region inference. Your request is processed entirely within the single AWS Region you specify, and it does not leave that Region. Use this when you have a need for strict single-Region data processing.

Unlike cross-Region inference profiles, there is no routing layer. The request you send to the Seoul (ap-northeast-2) or Singapore (ap-southeast-1) Region is served by that Region alone. Your input prompts and output results stay within it for the full lifecycle of the request. In exchange, your throughput is bounded by that Region’s capacity. Requests are subject to per-Region service quotas. Billing follows standard on-demand pricing for the Region you call. Quota consumption, Amazon CloudWatch metrics, and AWS CloudTrail log entries are all scoped to that same Region. There is no source-versus-destination distinction to account for in your monitoring. In-region inference for Claude Sonnet 5 and Claude Opus 5 in Seoul and Claude Sonnet 5 in Singapore is available on the bedrock-runtime endpoint. For new applications, we recommend the bedrock-runtime endpoint. You invoke it with the direct model ID, for example, anthropic.claude-opus-5 or anthropic.claude-sonnet-5. It supports Anthropic’s Messages API and the Amazon Bedrock InvokeModel and Converse APIs, along with Amazon Bedrock features such as Amazon Bedrock Guardrails and intelligent prompt routing.

Access Claude models from the Amazon Bedrock console

You can access Claude models in the text playground in the Amazon Bedrock console, which requires no coding or SDK setup. You can send prompts, adjust inference parameters, and switch between variants to get a feel for each model before you integrate the API.

Open the Amazon Bedrock console in a Region that you want to use as a source; In the navigation pane, under Test, choose Playground; Choose Select model in the middle of the page; Search for anthropic.claude-opus-5, select On-Demand under Inference, and choose Apply; Enter a prompt and choose Run to generate a response

Figure 1: The Anthropic Opus 5 model selected in the Amazon Bedrock console playground with in-region inference

Call Claude models with the Anthropic Messages API and Amazon Bedrock InvokeModel and Converse API

You can access Anthropic’s Claude Opus 5 or Claude Sonnet 5 programmatically with Seoul in-region inference using the Anthropic Messages API on the bedrock-runtime through Anthropic SDK or keep using the Invoke and Converse API on bedrock-runtime through the AWS Command Line Interface (AWS CLI) and AWS SDK.

Prerequisites

Active AWS account with Amazon Bedrock access; AWS CLI installed and configured; Python 3.8+; Boto3 installed: pip install boto3; Anthropic SDK installed: pip install anthropic; The Amazon Bedrock Token Generator for Amazon Bedrock authentication installed: pip install aws_bedrock_token_generator

Here’s a quick example using the AWS SDK for Python (Boto3) with the InvokeModel API:

You can also use the Amazon Bedrock Converse API for a unified multi-model experience:

You can also use the Anthropic Messages API through the anthropic SDK package for a streamlined experience:

You can monitor usage, performance, and costs through CloudWatch and AWS Cost Explorer to scale your applications as demand grows.

Conclusion

With the launch of Anthropic’s Claude Opus 5 and Claude Sonnet 5 on Amazon Bedrock with in-region inference in Seoul, and Claude Sonnet 5 with in-region inference in Singapore, you can now build generative AI applications that have strict data residency requirements. This keeps inference within the Region you want. We are excited about this launch and look forward to seeing how you use these capabilities to accelerate innovation and deliver impactful AI-powered experiences across the Region. For the most current information about model availability in each Region, see Regional availability by models in the Amazon Bedrock User Guide.

About the authors

Aamna Najmi

Aamna is a Senior Specialist Solutions Architect for Generative AI focusing on Anthropic models and operationalizing and governing generative AI systems at scale on Amazon Bedrock. She helps ISVs solve their challenges, embrace innovation, and create new business opportunities with Amazon Bedrock.

Alfredo Castillo

Alfredo is a Senior Specialist Solutions Architect for Generative AI at AWS, focusing on Anthropic models go-to-market on Amazon Bedrock. He works with Financial Services customers to design and scale generative AI solutions across distributed systems and turn generative AI experiments into production workloads. Outside of work, he is passionate about family and endurance sports.

Eugenio Soltero

Eugenio is a Sr. Product Marketing Manager for Amazon Bedrock at AWS. With several years of experience in generative AI, he helps customers navigate the evolving landscape of foundation models and generative AI to adopt solutions that deliver measurable value.

Sofian Hamiti

Sofian is a technology leader with over 12 years of experience building AI solutions, and leading high-performing teams to maximize customer outcomes. He is passionate about empowering diverse talents to drive global impact and achieve their career aspirations.