Amazon Bedrock adds structured outputs for all Anthropic Claude models

Amazon 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.