AWS First Steps
LanguageEnglish
New feature

Structured outputs for Claude models available on Amazon Bedrock

Amazon Bedrock now supports structured outputs for all Anthropic Claude models across both the bedrock-runtime and bedrock-mantle endpoints, enabling schema-compliant JSON responses without custom parsing or post-processing.

Amazon Bedrock now supports structured outputs for all Anthropic Claude models via bedrock-runtime and bedrock-mantle endpoints, enabling schema-compliant JSON responses through boto3 and bedrock-runtime API or Messages API without custom parsing, retry logic, or post-processing. This automates reliable schema tasks like extracting fields from financial reports, parsing clinical notes into EHRs, enriching product catalogs, analyzing contracts, and routing support tickets intelligently. For details, see Amazon Bedrock documentation. Structured outputs are available where Claude models are offered; check regional availability for more information.

Why it matters

This update benefits developers and organizations that need to automate data extraction and document processing with AI models, as structured outputs enable reliable and consistent data formats.

Regions: Listed in the official documentation

Read the original AWS announcement

Related articles and terms

Generative AI Platform - Building an Enterprise AI Foundation with Amazon BedrockLearn how to build generative AI applications using Amazon Bedrock. This guide covers foundation model selection, RAG pattern implementation, safety guardrails, and SageMaker integration for designing enterprise-grade AI infrastructure.Amazon BedrockA fully managed generative AI service providing access to leading foundation models via APIUsing Claude on Amazon Bedrock - Model Selection, Prompt Design, and Cost OptimizationCompares the Anthropic Claude models available on Amazon Bedrock, provides model selection guidelines by use case, and covers prompt design best practices and cost optimization.The Layered Architecture of AWS AI/ML Services - Flexibility Through the Three Tiers of SageMaker, Bedrock, and API ServicesThis article organizes AWS AI/ML services into three layers - SageMaker (full control), Bedrock (managed generative AI), and Rekognition/Comprehend/etc. (API-based) - and explains AWS's flexibility through comparisons with GCP Vertex AI and Azure OpenAI Service, including custom silicon integration.Amazon Bedrock GuardrailsA safety mechanism that controls generative AI application inputs and outputs, performing harmful content filtering and personal information masking