Creating a GenU (Generative AI Use Cases JP) v5.4 environment with Claude Opus 4.6 support

I am Ishikawa from the Cloud Business Division Consulting Department. On Thursday, January 22, I presented at an event co-hosted with AWS Japan with the title Agentic AI System using GenU × AgentCore (MCP).

https://events.classmethod.jp/seminar/260122-hokkaido-seminar/

During the session, I focused on demos, showcasing customizations for the Japan region and live demonstrations of AgentCore, MCP, S3 Vectors, and more. Since we couldn't cover all the detailed settings within the event time, today I'll explain the steps to build that demo environment. Specifically, I'll focus on how to configure and set up the latest GenU 5.4 to use Claude Opus 4.6.

Why GenU v5.4, Why Claude Opus 4.6

If you're interested in utilizing generative AI for business but are concerned about "how to start" or "whether it's secure," you're not alone. GenU is a generative AI application developed primarily by volunteers at AWS Japan.

The latest GenU v5.4 is the ideal platform for experiencing the latest generative AI, featuring migration from MCP to AgentCore, enhanced support for private networks, and no-code agent development with Agent Builder.

https://aws.amazon.com/jp/builders-flash/202504/genu-development-guide/

Additionally, Claude Opus 4.6, released on February 5, 2026, is Anthropic's latest flagship model with improved coding capabilities, long text comprehension, and doubled output capacity.

I'd like to introduce this to everyone who wants to leverage Claude Opus 4.6 with the latest GenU 5.4 in the Tokyo region.

Prerequisites

• Deploy GenU in Tokyo region (ap-northeast-1) to achieve low latency
• Data residency not required
  • Use global inference profile ID

1. Getting the Source Code

https://github.com/aws-samples/generative-ai-use-cases

Clone the repository.

git clone https://github.com/aws-samples/generative-ai-use-cases.git

After cloning, run the ci command to install packages.

npm ci

2. Configuration Changes

Editing model.ts (Common)

Add the following to generative-ai-use-cases/packages/common/src/application/model.ts. This will make Claude Opus 4.6 selectable.

  'global.anthropic.claude-opus-4-6-v1': {
    flags: MODEL_FEATURE.TEXT_DOC_IMAGE_REASONING,
    displayName: 'Claude Opus 4.6',
  },

Editing model.ts (Chat)

Add the following to generative-ai-use-cases/packages/cdk/lambda/utils/models.ts. This will make Claude Opus 4.6 selectable. Note that defaultParams reuses the definition from Claude Opus 4.5.

  'global.anthropic.claude-opus-4-6-v1': {
    defaultParams: CLAUDE_OPUS_4_5_DEFAULT_PARAMS,
    usecaseParams: USECASE_DEFAULT_PARAMS,
    createConverseCommandInput: createConverseCommandInput,
    createConverseStreamCommandInput: createConverseStreamCommandInput,
    extractConverseOutput: extractConverseOutput,
    extractConverseStreamOutput: extractConverseStreamOutput,
  },

Editing cdk.json

Replace the region, modelRegion, and modelIds in generative-ai-use-cases/packages/cdk/cdk.json with the settings below to use global inference profile IDs.

    "region": "ap-northeast-1",
    "modelRegion": "ap-northeast-1",
    "modelIds": [
      "global.anthropic.claude-opus-4-6-v1",
      "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
      "global.anthropic.claude-haiku-4-5-20251001-v1:0",
      "global.anthropic.claude-opus-4-5-20251101-v1:0",
      "global.anthropic.claude-sonnet-4-20250514-v1:0",
      "global.amazon.nova-2-lite-v1:0"
    ],

With region settings region: ap-northeast-1 and modelRegion: ap-northeast-1 (both Tokyo region), all stacks except WAF will be deployed in the Tokyo region.

With region settings region: ap-northeast-1 and modelRegion: ap-northeast-1 (both Tokyo region), all stacks except WAF will be deployed in the Tokyo region, allowing low-latency access to applications. Additionally, six text generation models with global.*/apac.* prefixes (including Claude Opus 4.6) and three media models will be available.

3. Deployment

Run the bootstrap command

If you've never used CDK in the AWS account or region before, run the bootstrap command first (it's safe to run even if you're not sure).

npx -w packages/cdk cdk bootstrap

Deploy to the Tokyo region

Since we've already specified Tokyo region (ap-northeast-1) in region and modelRegion, deploy without region specification.

npm run cdk:deploy

Check the Web URL

After deployment, the Web URL (the part like https://d3pv66btvgugv1.cloudfront.net) will be displayed.

If you miss it, you can also check from the CloudFormation outputs.

4. Login

Click on the Web URL (the part like https://d3pv66btvgugv1.cloudfront.net) and you'll see the login screen. Enter your email address and password.

A verification code will be sent to the email address you specified. Enter it and click [Confirm] to complete registration.

After logging in, you will see the following top page.

New Claude models, including Claude Opus 4.6, are now available.

The execution result is as follows:

5. Disable Self-Signup (Required)

You should immediately disable the UI that allows anyone to create an account.

Edit parameter.ts

You can disable self-signup by overriding selfSignUpEnabled in envs in generative-ai-use-cases/packages/cdk/parameter.ts.

  '': {
    selfSignUpEnabled: false,
  },

After configuring, deploy again.

npm run cdk:deploy

When the "Create account" tab disappears, you've succeeded.

Note: Recommended Security Settings

In "5. Disable Self-Signup (Required)" we only set selfSignUpEnabled, but you can apply recommended security settings using the same procedure. We recommend using multiple layers of defense to strengthen security.

Note: If You Have Data Residency Requirements

Data residency requirements define rules about "in which country or region an organization's data should be physically stored and processed." If data cannot be taken out of Japan, configure Japanese domestic cross-region inference. However, relatively new Opus models like Claude 4.5 or 4.6 may often not be available.

If you have data residency requirements but want to choose relatively new models, use the following configuration:

    "region": "ap-northeast-1",
    "modelRegion": "ap-northeast-1",
    "modelIds": [
      "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
      "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
      "jp.amazon.nova-2-lite-v1:0"
    ],

Conclusion

I've introduced the procedure to add Claude Opus 4.6 to GenU v5.4 and deploy it in the Tokyo region. By just adding model definitions to model.ts and changing settings in cdk.json, you can quickly build an environment to try multiple models, including the latest Claude Opus 4.6. After deployment, don't forget to apply security settings like disabling self-signup and IP address restrictions. GenU continues to be actively developed, and future versions may include standard support for Claude Opus 4.6. Until then, I hope this article's procedure will help with your testing and business applications.