AWS launches Claude Platform on AWS, bringing Anthropic's native APIs and features directly to AWS accounts
AWS announced general availability of Claude Platform on AWS, enabling direct access to Anthropic's native APIs, tools, and console through existing AWS accounts. The service includes the Messages API, Claude Managed Agents, web search, MCP connector, and code execution, authenticated via AWS IAM and billed through AWS Marketplace.
AWS launches Claude Platform on AWS, bringing Anthropic's native APIs and features directly to AWS accounts
AWS announced general availability of Claude Platform on AWS, a new service that provides direct access to Anthropic's native Claude Platform experience through AWS accounts. AWS is the first cloud provider to offer this native integration.
What's included
Claude Platform on AWS provides the same APIs, features, and console experience available directly from Anthropic. This includes:
- Messages API
- Claude Managed Agents (beta)
- Advisor tool (beta)
- Web search and web fetch
- MCP connector (beta)
- Agent Skills (beta)
- Code execution
- Files API (beta)
The service integrates with existing AWS infrastructure through IAM authentication, eliminating the need for separate Anthropic accounts or API keys. Usage is billed through AWS Marketplace on a consumption basis and logged via AWS CloudTrail.
Architecture and data handling
According to AWS, Claude Platform on AWS is operated by Anthropic, with requests and data processed outside the AWS security boundary. This distinguishes it from Claude models available through Amazon Bedrock, which remain within AWS infrastructure. AWS states the service is "well suited for teams without specific Regional data residency requirements."
Authentication and setup
The service supports two authentication methods: IAM with AWS Signature Version 4 (recommended for higher security) and API keys (recommended for exploration). Users create workspaces to separate projects, environments, or teams while maintaining centralized billing and administration.
Setup requires three steps: creating a workspace through the Claude Console, authenticating via IAM or API key, and making API calls using the Anthropic Client SDKs. The service uses regional endpoints in the format https://aws-external-anthropic.<REGION>.api.aws.
Integration with Claude applications
Claude Code and Claude Cowork can connect to Claude Platform on AWS by configuring environment variables for the API key, base URL, and workspace ID. Users can monitor usage in the Claude Console with breakdowns by workspace, AWS IAM principal, and time period. AWS Cost Explorer provides cost tracking alongside other AWS services.
Availability
Claude Platform on AWS is available in 19 AWS regions: 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).
What this means
This launch gives AWS customers a streamlined path to Anthropic's full feature set without managing separate vendor relationships. Organizations already invested in AWS infrastructure gain unified authentication, billing, and audit trails for AI workloads. However, the architecture places data processing outside AWS boundaries, making it unsuitable for workloads with strict regional data residency requirements. For those use cases, Claude models on Amazon Bedrock remain the appropriate choice. The move positions AWS as the first cloud provider to offer native access to Anthropic's platform, potentially influencing how other cloud providers structure their AI partnerships.
Related Articles
Anthropic SDK v0.121.0 Adds Session Budgets, Mid-Conversation Tool Changes, and GitHub Skills Auto-Loading
Anthropic released version 0.121.0 of its Python SDK on August 7, 2026, introducing a new beta for mid-conversation tool changes, session budgets, an advisor tool, pinned inference location, and skills auto-loading from GitHub. The update also removes retired Claude Opus 4.1 models from the API.
GitHub Adds Agent App Activity Data to Copilot Usage Metrics API
GitHub has updated its Copilot usage metrics API to include activity data from agent apps such as Claude and Codex operating within GitHub workflows. The change gives organizations visibility into third-party agent usage alongside native Copilot metrics.
Anthropic Cuts False Positives in Fable 5's Biology Filter by 85%, Keeps Virology and Toxicology Blocked
Anthropic has cut false positives in Fable 5's biology safety classifier by roughly 85%, letting users ask about lab results, symptoms, and medical questions without being rerouted to the weaker Opus 5 model. Dual-use topics like virology, toxicology, and molecular design remain restricted, with Anthropic citing the difficulty of containing biological threats once released.
AWS Adds Temporal Policies to Bedrock AgentCore to Stop AI Agents From Exploiting Multi-Step Actions
Amazon Bedrock AgentCore now supports temporal policies—stateful authorization rules that evaluate an AI agent's entire session history, not just individual tool calls. The feature runs at the AgentCore Gateway, outside agent code, so it cannot be bypassed by prompt manipulation or agent bugs.
Comments
Loading...