Introducing the Claude Platform on AWS: Anthropic’s native platform (via your AWS account)

Machine Learning


Today, we are excited to announce the general availability of the Claude Platform on AWS. Claude Platform on AWS is a new service that gives customers direct access to Anthropic’s native Claude Platform experience through their AWS account. No separate credentials, contracts, or billing relationships are required. AWS is the first cloud provider to offer access to a native Claude Platform experience.

This post explains how AWS’s Claude Platform works and how you can start using it today.

Experience the Claude Platform through AWS

With AWS’s Claude Platform, you can use the same APIs, features, and console experience available directly through Anthropic. This includes: Message API, Agent managed by Claude (beta), advisor tool (beta), web search and web fetch, MCP connector (beta), agent skills (beta), Execute the code, File API (beta). See for a complete list of features. of Claude platform documentation.

Access Claude Platform on AWS through familiar AWS features.

  • certification: Use your existing AWS IAM credentials to access Claude Platform. There’s no need to manage separate accounts or API keys.
  • make a claim: Usage is billed on a pay-as-you-go basis through AWS Marketplace, so you can track and manage your AI spending alongside other AWS services.
  • audit: Activity is captured in AWS CloudTrail, so you can monitor, audit, and investigate your AI usage in the same way as with other AWS services.

The Claude Platform on AWS is operated by Anthropic, and the underlying requests and data are processed outside the AWS security perimeter. This makes it suitable for teams without specific regional data residency requirements and complements Amazon Bedrock’s Claude model, allowing you to access Claude with an approach that fits your needs.

Figure 1: Sign in to the AWS Management Console and Claude platform on AWS console

Get started with Claude Platform on AWS

The Claude Platform can be activated on AWS through AWS Marketplace. For detailed instructions, see Account Setup. After your account is activated, making your first API call requires three steps: creating a workspace, authenticating, and calling the API.

Step 1: Create a workspace

Workspaces allow you to separate projects, environments, or teams while maintaining centralized billing and management. It also serves as the primary AWS Identity and Access Management (IAM) resource for the Claude Platform on AWS. Allow or deny access to specific workspaces through IAM policies using workspace ARNs. For example policies, see IAM Policies.

Open the Claude console from within the Claude platform on the AWS console and create a workspace.

Figure 2: The workspace ID is located here: on the Claude platform AWS console.

Step 2: Authenticate

The Claude Platform on AWS supports two authentication methods: IAM using AWS Signature Version 4 and API keys. We recommend using temporary IAM credentials for setups that require a higher level of security, and using API keys to explore Claude Platform on AWS.

To quickly test your setup, you can generate an API key in the AWS Console’s Cloud Platform.

Figure 3: You can generate an API key in the AWS console’s Cloud Platform

Set your API key, base URL, and workspace ID as environment variables.

# Your API key  
export ANTHROPIC_API_KEY= 

# Your regional endpoint for Claude Platform on AWS 
export ANTHROPIC_BASE_URL=https://aws-external-anthropic..api.aws 

# Your workspace ID (find in Claude Platform on AWS Console → Workspaces) 
export ANTHROPIC_WORKSPACE_ID= 

Step 3: Make your first API call

You can do it now install of Anthropic Client SDK and make API call:

from anthropic import Anthropic 
import os 
 
client = Anthropic( 
   default_headers={"anthropic-workspace-id": os.environ["ANTHROPIC_WORKSPACE_ID"]}, 
) 
 
message = client.messages.create( 
   model="claude-sonnet-4-6", 
   max_tokens=1024, 
   messages=[{"role": "user", "content": "Hello!"}], 
) 
 
print(message) 

look introductory notebook for even more code example.

Practicing the Claude platform on AWS

Once setup is complete, you can specify Claude Code, Claude Cowork, or other API clients in your workspace using the following environment variables or configurations:

export ANTHROPIC_API_KEY= 

export ANTHROPIC_BASE_URL=https://aws-external-anthropic..api.aws 

 # For Claude Cowork, set the “anthropic-workspace-id" in your inference configuration. For Claude Code use the following:  
export ANTHROPIC_CUSTOM_HEADERS='{"anthropic-workspace-id":""}' 

 # For the Anthropic SDK 
export ANTHROPIC_WORKSPACE_ID= 

Once connected, clients can use features such as web search, MCP connectors, agent skills, code execution, and file uploads through the Claude Platform on AWS.

Figure 4a: Claude Cowork connected to Claude Platform on AWS

Figure 4b: Claude code connected to Claude platform on AWS

You can monitor usage in the Cloud console, including workspaces, AWS IAM principals, and time period breakdowns.

Figure 5: Claude Console usage analysis

In an AWS environment, AWS CloudTrail captures requests from Anthropic SDK, Claude Code, or Cowork to the Claude Platform on AWS. Workspace operations are logged as administrative events by default, and you can enable data event logging to capture inference activity. For more information about event types and logging configuration, see Monitoring and Logging. Your usage is billed through AWS Marketplace, so you can monitor your costs with AWS Cost Explorer alongside your other cloud services. You can also allocate spending using resource tags.

Figure 6: Example of AWS CloudTrail events (left) and AWS Cost Explorer (right) for Claude Platform on AWS

conclusion

Claude Platform on AWS gives your team access to Anthropic’s full native APIs and capabilities through the same AWS accounts they already use. The Claude Platform on AWS is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), South America (São Paulo), EU (Dublin), EU (London), EU (Frankfurt), EU (Milan), EU (Zurich), EU (Paris), EU (Stockholm), Asia Pacific (Tokyo), Asia Pacific (Seoul), and Asia Pacific. (Melbourne), Asia Pacific (Jakarta), Asia Pacific (Sydney). To get started, open Claude Platform in the AWS console or read our documentation.

Try the Claude Platform on AWS today and send your feedback to AWS re:Post or to your regular AWS Support contact.


About the author

dani mitchell

dani mitchell He is a Senior GenAI Specialist Solutions Architect at AWS and an SA Lead for the Amazon Bedrock Knowledge Bases. He helps companies around the world design and deploy generative AI solutions that use models and capabilities from Amazon Bedrock and Anthropic to build scalable, production-ready applications.

Sofian Hamiti

Sofian Hamiti 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 talent to increase their global impact and achieve their career aspirations.

Eugenio Soltero

Eugenio Soltero is a Senior Product Marketing Manager for Amazon Bedrock on AWS. With years of experience in generative AI, we help customers navigate the evolving landscape of underlying models and generative AI, and deploy solutions that deliver measurable value.

antonio rodriguez

antonio rodriguez Principal Generative AI Technology Leader at Amazon Web Services. He helps companies of all sizes use Amazon Bedrock to solve challenges, embrace innovation, and create new business opportunities. Outside of work, I love spending time with my family and playing sports with friends.

Ayan Ray

Ayan Ray He is a Principal Partner Solutions Architect and AI Tech Lead at AWS and serves as the Worldwide Tech Lead for Anthropic on AWS. He works at the intersection of cloud architecture and artificial intelligence, helping organizations adopt and scale Anthropic’s technology on AWS.



Source link