Right now, we’re excited to announce the overall availability of Claude Platform on AWS. Claude Platform on AWS is a brand new service that offers prospects direct entry to Anthropic’s native Claude Platform expertise by way of their AWS account, with no separate credentials, contracts, or billing relationships required. AWS is the primary cloud supplier to supply entry to the native Claude Platform expertise.
On this publish, we discover how Claude Platform on AWS works and how one can begin utilizing it as we speak.
Claude Platform expertise by way of AWS
With Claude Platform on AWS, you’re employed with the identical APIs, options, and console expertise accessible by way of Anthropic instantly. This consists of the Messages API, Claude Managed Brokers (beta), advisor software (beta), internet search and web fetch, MCP connector (beta), Agent Abilities (beta), code execution, information API (beta). For the complete listing of capabilities, see the Claude Platform documentation.
You entry Claude Platform on AWS by way of acquainted AWS options:
- Authentication: You employ present AWS IAM credentials to entry Claude Platform. No separate accounts or API keys to handle.
- Billing: Utilization is billed by way of AWS Market on a consumption foundation, so you’ll be able to observe and handle AI spending alongside your different AWS companies.
- Audit: Exercise is captured in AWS CloudTrail, so you’ll be able to monitor, audit, and examine AI utilization the identical method you do for some other AWS companies.
Claude Platform on AWS is operated by Anthropic, and the underlying requests and information are processed exterior the AWS safety boundary. This makes it properly suited to groups with out particular Regional information residency necessities, and enhances Claude fashions on Amazon Bedrock, so you’ll be able to entry Claude by way of the strategy that matches your wants.
Determine 1: Register to the AWS Administration Console and open the Claude Platform on AWS Console
Getting began with Claude Platform on AWS
You’ll be able to activate Claude Platform on AWS by way of the AWS Market. For step-by-step directions, see Arrange your account. After your account is activated, attending to your first API name takes three steps: create a workspace, authenticate, and name the API.
Step 1: Create a workspace
With a workspace, you’ll be able to separate tasks, environments, or groups whereas sustaining centralized billing and administration. It additionally serves as the first AWS Identification and Entry Administration (IAM) useful resource for Claude Platform on AWS. You grant or deny entry to particular workspaces by way of IAM insurance policies utilizing the workspace ARN. See IAM insurance policies for coverage examples.
Open the Claude Console from inside the Claude Platform on AWS Console and create a workspace.
Determine 2: You will discover your workspace ID within the Claude Platform on AWS Console.
Step 2: Authenticate
Claude Platform on AWS helps two authentication strategies: IAM with AWS Signature Model 4, and API keys. We advocate utilizing momentary IAM credentials for setups that require the next degree of safety, and API keys for exploring Claude Platform on AWS.
To rapidly take a look at your setup, you’ll be able to generate an API key within the Claude Platform on AWS Console:
Determine 3: You’ll be able to generate an API key within the Claude Platform on AWS Console
Set your API key, base URL, and Workspace ID as atmosphere 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 (discover in Claude Platform on AWS Console → Workspaces)
export ANTHROPIC_WORKSPACE_ID=
Step 3: Make your first API name
Now you can set up the Anthropic Shopper SDKs and make API calls:
from anthropic import Anthropic
import os
shopper = Anthropic(
default_headers={“anthropic-workspace-id”: os.environ[“ANTHROPIC_WORKSPACE_ID”]},
)
message = shopper.messages.create(
mannequin=”claude-sonnet-4-6″,
max_tokens=1024,
messages=[{“role”: “user”, “content”: “Hello!”}],
)
print(message)
See Getting Began notebooks for extra code examples.
Claude Platform on AWS in observe
Together with your setup full, you’ll be able to level Claude Code, Claude Cowork, or some other API shopper at your workspace utilizing the next atmosphere variables or configuration:
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 next:
export ANTHROPIC_CUSTOM_HEADERS='{“anthropic-workspace-id”:””}’
# For the Anthropic SDK
export ANTHROPIC_WORKSPACE_ID=
After you’re related, your shoppers can use capabilities like internet search, MCP connectors, agent expertise, code execution, and file uploads by way of Claude Platform on AWS.
Determine 4a: Claude Cowork related to Claude Platform on AWS
Determine 4b: Claude Code related to Claude Platform on AWS
You’ll be able to monitor utilization within the Claude Console, together with breakdowns by workspace, AWS IAM principal, and time interval.
Determine 5: Utilization analytics within the Claude Console
In your AWS atmosphere, AWS CloudTrail captures requests to Claude Platform on AWS, whether or not from the Anthropic SDK, Claude Code, or Cowork. Workspace operations are logged as administration occasions by default, and you may allow information occasion logging to seize inference exercise. For particulars on occasion sorts and logging configuration, see Monitoring and logging. As a result of utilization is billed by way of AWS Market, you’ll be able to monitor prices in AWS Value Explorer alongside your different cloud companies. You may also allocate spending utilizing useful resource tags.
Determine 6: Instance AWS CloudTrail occasions (left) and AWS Value Explorer (proper) for Claude Platform on AWS
Conclusion
With Claude Platform on AWS, your groups get Anthropic’s full native APIs and options by way of the identical AWS account you already use. Claude Platform on AWS is on the market in 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 Parcific (Melborune), Asia, Pacific (Jakarta), Asia Pacific (Sydney), and Asia Pacific (Melbourne). To get began, open the Claude Platform on AWS Console or discover the documentation.
Give Claude Platform on AWS a strive as we speak and ship suggestions to AWS re:Put up or by way of your typical AWS Assist contacts.
Concerning the authors
Dani Mitchell
Dani Mitchell is a Sr GenAI Specialist Options Architect at AWS and the SA lead for Amazon Bedrock Data Bases. He helps enterprises the world over design and deploy generative AI options utilizing Amazon Bedrock and Anthropic’s fashions and capabilities to construct scalable, production-ready purposes.
Sofian Hamiti
Sofian Hamiti is a know-how chief with over 12 years of expertise constructing AI options, and main high-performing groups to maximise buyer outcomes. He’s obsessed with empowering various skills to drive world affect and obtain their profession aspirations.
Eugenio Soltero
Eugenio Soltero is a Sr. Product Advertising Supervisor for Amazon Bedrock at AWS. With a number of years of expertise in generative AI, he helps prospects navigate the evolving panorama of basis fashions and generative ai to undertake options that ship measurable worth.
Antonio Rodriguez
Antonio Rodriguez is a Principal Generative AI Tech Chief at Amazon Internet Providers. He helps firms of all sizes resolve their challenges, embrace innovation, and create new enterprise alternatives with Amazon Bedrock. Aside from work, he likes to spend time together with his household and play sports activities together with his buddies.
Ayan Ray
Ayan Ray is a Principal Associate Options Architect and AI Tech Lead at AWS, serving because the Worldwide Tech Lead for Anthropic at AWS. He works on the intersection of cloud structure and Synthetic Intelligence, serving to organizations undertake and scale Anthropic’s applied sciences on AWS.
