Today, we are thrilled to announce the general availability of the Claude Platform on AWS. The Claude Platform on AWS is a groundbreaking service that offers customers direct access to Anthropic’s native Claude Platform experience via their AWS account. This eliminates the need for separate credentials, contracts, or billing relationships. Notably, AWS is the first cloud provider to deliver access to the native Claude Platform experience.
In this article, we delve into how the Claude Platform operates on AWS and guide you on starting with it today.
Experience with the Claude Platform via AWS
With the Claude Platform on AWS, users interact with the same APIs, features, and console experience as available directly through Anthropic. This includes the Messages API, Agents managed by Claude (beta), the advise tool (beta), web search, web recover, MCP connector (beta), Agent skills (beta), code execution, and the File API (beta). For a comprehensive list of features, refer to the Claude platform documentation.
You can access the Claude Platform on AWS through familiar AWS features:
- Authentication: Utilize your existing AWS IAM credentials to access the Claude Platform, removing the need to manage separate accounts or API keys.
- Billing: Usage is billed via the AWS Marketplace on a consumption basis, allowing you to track and manage AI spending alongside other AWS services.
- Audit: Activity is captured in AWS CloudTrail, enabling you to monitor, audit, and investigate AI usage like any other AWS service.
The Claude Platform on AWS is operated by Anthropic, with underlying requests and data processed outside AWS security boundaries. This makes it ideal for teams without specific regional data residency requirements and complements the Claude models on Amazon Bedrock, offering flexibility in accessing Claude based on your needs.
Figure 1: Log in to the AWS Management Console and open the Claude platform on the AWS console
Getting started with Claude Platform on AWS
You can activate the Claude Platform on AWS via the AWS Marketplace. For detailed instructions, see Set up your account. Once activated, accessing your first API call involves three steps: create a workspace, authenticate, and call the API.
Step 1: Create a workspace
A workspace allows you to separate projects, environments, or teams while maintaining centralized billing and administration. It also serves as the primary AWS Identity and Access Management (IAM) resource for the Claude Platform on AWS. Access to specific workspaces is granted or denied through IAM policies using the workspace ARN. See IAM policies for sample policies.
Open the Claude console from the Claude platform on the AWS console and create a workspace.
Figure 2: You can find your workspace ID in the Claude platform on the AWS console.
Step 2: Authenticate
The Claude Platform on AWS supports two authentication methods: IAM with AWS Signature Version 4 and API keys. Temporary IAM credentials are recommended for configurations requiring higher security, while API keys can be used for exploring the Claude Platform on AWS.
To quickly test your configuration, generate an API key in the Claude Platform console on AWS:
Figure 3: You can generate an API key in the Claude platform on the AWS console
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
export ANTHROPIC_BASE_URL=https://aws-external-anthropic..api.aws
# Your workspace ID (search in Claude Platform on AWS Console → Workspaces)
export ANTHROPIC_WORKSPACE_ID=
Step 3: Make your first API call
You can now install the Anthropic client SDK and perform API calls:
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)
See Starter notebooks for more code examples.
Claude Platform on AWS in practice
Once your configuration is complete, you can point Claude Code, Claude Cowork, or any other API client to your workspace using the following environment variables or configuration:
export ANTHROPIC_API_KEY=
export ANTHROPIC_BASE_URL=https://aws-external-anthropic..api.aws
# For Claude Cowork, define the "anthropic-workspace-id" in your inference configuration.
# For Claude Code, use the following:
export ANTHROPIC_CUSTOM_HEADERS='{"anthropic-workspace-id":"}'
# For exporting the Anthropic SDK
export ANTHROPIC_WORKSPACE_ID=
Once connected, your customers can use features like web search, MCP connectors, agent skills, code execution, and file uploads through the Claude Platform on AWS.
Figure 4a: Claude Cowork connected to the Claude platform on AWS
Figure 4b: Claude Code connected to the Claude platform on AWS
You can monitor usage in the Claude console, including breakdowns by workspace, AWS IAM principal, and time period.
Figure 5: Usage analysis in the Claude console
In your AWS environment, AWS CloudTrail captures requests to the Claude Platform on AWS, whether they come from the Anthropic SDK, Claude Code, or Cowork. Workspace operations are logged as management events by default, and data event logging can be enabled to capture inference activity. For details on event types and logging configuration, see Monitoring and Logging. Because usage is billed through the AWS Marketplace, you can monitor costs in AWS Cost Explorer alongside other cloud services. You can also distribute expenses using resource tags.
| |
Figure 6: Examples of AWS CloudTrail (left) and AWS Cost Explorer (right) events for the Claude platform on AWS
Conclusion
The Claude Platform on AWS allows teams to leverage all native APIs and features of Anthropic through the same AWS account they already utilize. The Claude Platform on AWS is available in various regions including US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), South America (São Paulo), Europe (Dublin), Europe (London), Europe (Frankfurt), Europe (Milan), Europe (Zurich), Europe (Paris), Europe (Stockholm), Asia Pacific (Tokyo), Asia Pacific (Seoul), Asia Pacific (Melbourne), Asia-Pacific (Jakarta), and Asia-Pacific (Sydney). To begin, open the Claude platform on the AWS console or explore the documentation.
Try the Claude Platform on AWS today and provide feedback to AWS re:Post or through your usual AWS Support contacts.
About the authors
Daniel Mitchell
Daniel Mitchell is a Sr GenAI Specialist Solutions Architect at AWS and the SA Lead for Amazon Bedrock Knowledge Bases. He assists businesses worldwide in designing and deploying generative AI solutions using models and capabilities from Amazon Bedrock and Anthropic to create scalable, production-ready applications.
Sofiane Hamiti
Sofiane Hamiti is a technology leader with over 12 years of experience in building AI solutions and leading high-performing teams to maximize customer outcomes. He is passionate about empowering diverse talents to make a global impact and achieve their professional aspirations.
Eugénio Single
Eugénio Single is a Senior Product Marketing Manager for Amazon Bedrock at AWS. With years of experience in generative AI, he helps clients navigate the evolving landscape of core models and generative AI to adopt solutions that deliver measurable value.
Antonio Rodriguez
Antonio Rodriguez is a leading technology leader in generative AI at Amazon Web Services. He helps businesses of all sizes solve challenges, embrace innovation, and create new business opportunities with Amazon Bedrock. Outside of work, he enjoys spending time with his family and playing sports with his friends.
Ryan Ray
Ryan Ray is a Senior Partner Solutions Architect and AI Technical Lead at AWS, serving as the Global Technical Lead for Anthropic at AWS. He works at the intersection of cloud architecture and artificial intelligence, helping organizations adopt and scale Anthropic technologies on AWS.
For more information, visit the source link: Here
“`
