Amazon Bedrock adds structured outputs for all Anthropic Claude models
Overview
Amazon Bedrock now supports structured outputs for all Anthropic Claude models on the bedrock-runtime and bedrock-mantle endpoints, where each model is available, according to an AWS Machine Learning Blog post.
Structured outputs use constrained decoding to enforce a JSON schema during token generation, so responses are valid JSON with required fields present and no retry logic is needed.
AWS says the feature also works with cross-Region inference and batch inference on the bedrock-runtime endpoint, and that compiled grammars are cached for 24 hours. The post describes structured outputs for Claude on Amazon Bedrock as generally available.
Written by AI from the articles below · updated Oct 19, 7:37 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- AWS Machine Learning BlogOfficialAmazon Bedrock adds structured outputs for all Anthropic Claude models
AIAmazon Bedrock now supports structured outputs for all Anthropic Claude models on the bedrock-runtime and bedrock-mantle endpoints, where the model is available. Structured outputs use constrained decoding to enforce a JSON schema during token generation, so responses are valid JSON with required fields present and no retry logic is needed. The feature also works with batch inference and cross-Region inference on the bedrock-runtime endpoint, and compiled grammars are cached for 24 hours.
Heat Trend
Not enough continuous observations to show a trend yet.