Claude Sonnet 5.5 available on Amazon Bedrock and Claude Platform on AWS

Sonnet 5.5 improves on Sonnet 5 by producing more polished documents and visuals, such as one‑pager summaries, architecture diagrams, and slide decks. It also checks results against stated requirements and is suited for workloads that run continuously or at scale, including first‑response alerts, monitoring of agents, SQL generation, UI/UX testing, and fast coding agents in IDEs with a fixed spend cap. Across the enterprise it supports scoped analysis, short spreadsheet edits, and routine document tasks for large user populations.

To try the model, users can open the Amazon Bedrock console, go to Test Playground, and select Sonnet 5.5. Programmatically, the model can be called via the Anthropic Messages API against bedrock‑runtime through the Anthropic SDK, or via the Invoke and Converse APIs on bedrock‑runtime using the AWS CLI or AWS SDK. Prerequisites include an active AWS account with Amazon Bedrock access, AWS CLI installed and configured, Python 3.10+, Boto3 installed, and IAM permissions bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream. Usage, performance, and costs can be monitored through Amazon CloudWatch and AWS Cost Explorer.