---
type: "post"
id: "structured-outputs-for-anthropic-claude-models-on-amazon-c9a274"
slug: "structured-outputs-for-anthropic-claude-models-on-amazon-c9a274"
title: "Structured outputs for Anthropic Claude models on Amazon Bedrock"
description: "**Thesis:** Schema-constrained generation makes output validity part of the inference interface, but moves some integration complexity into schema lifecycle and runtime behavior."
retrieval_nugget: "**Thesis:** Schema-constrained generation makes output validity part of the inference interface, but moves some integration complexity into schema lifecycle and runtime behavior."
published_at: "2026-10-20"
updated_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "published_at"
topics: ["claude","anthropic"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/structured-outputs-for-anthropic-claude-models-on-amazon-bedrock"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:structured-outputs-for-anthropic-claude-models-on-amazon-c9a274"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:81cb005c44ed1e5d47c4f8da8cbad53ff1762daebd99cdf5d0c0c944d89b49bd","reviewed_at":"2026-10-20T08:05:15.041Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Schema-constrained generation makes output validity part of the inference interface, but moves some integration complexity into schema lifecycle and runtime behavior.","observed_facts":[{"text":"AWS says structured outputs are supported for all Anthropic Claude models available on Amazon Bedrock, on both bedrock-runtime and bedrock-mantle.","source_urls":["https://aws.amazon.com/blogs/machine-learning/structured-outputs-for-anthropic-claude-models-on-amazon-bedrock"]},{"text":"The feature provides JSON Schema output formatting and strict tool use, and uses constrained decoding to prevent schema-violating tokens.","source_urls":["https://aws.amazon.com/blogs/machine-learning/structured-outputs-for-anthropic-claude-models-on-amazon-bedrock"]},{"text":"Bedrock validates schemas against a supported subset of JSON Schema Draft 2020-12, compiles new schemas into grammar artifacts, and caches them for 24 hours.","source_urls":["https://aws.amazon.com/blogs/machine-learning/structured-outputs-for-anthropic-claude-models-on-amazon-bedrock"]}],"mechanism":"Bedrock validates and compiles supported schemas into grammar artifacts, constrains generation to the grammar, and caches artifacts for 24 hours; structure changes invalidate the cache and trigger recompilation.","why_now":"The announcement matters as Claude users can now apply schema-constrained generation through Bedrock’s two endpoints, not only handle output formatting in application code.","implications":["This can reduce parsing and retry work, while making schema compatibility and changes an explicit part of deployment planning.","Strict tool-parameter validation supplies a concrete schema enforcement point for Bedrock-based agent workflows."],"evidence_boundary":"These are AWS’s product claims; the source provides no independent benchmarks quantifying reliability, latency, or cost effects. The supported schema subset also means this should not be read as support for every JSON Schema feature.","watch_conditions":["Watch for documentation or measured reports clarifying schema-subset limitations, first-request compilation latency, and how real workloads fare when schemas change."],"related_records":[],"new_branch_reason":"No prior New Runtime analytical record was supplied, so this starts a distinct record on Bedrock’s schema-constrained generation capability."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/structured-outputs-for-anthropic-claude-models-on-amazon-c9a274/","markdown":"https://newruntime.com/posts/structured-outputs-for-anthropic-claude-models-on-amazon-c9a274.md","json":"https://newruntime.com/posts/structured-outputs-for-anthropic-claude-models-on-amazon-c9a274.json"}
related_patterns: ["model-answers-become-task-interfaces"]
---

# Structured outputs for Anthropic Claude models on Amazon Bedrock

## Retrieval answer

**Thesis:** Schema-constrained generation makes output validity part of the inference interface, but moves some integration complexity into schema lifecycle and runtime behavior.

**Thesis:** Schema-constrained generation makes output validity part of the inference interface, but moves some integration complexity into schema lifecycle and runtime behavior.

**Observed facts:** AWS says structured outputs are supported for all Anthropic Claude models available on Amazon Bedrock, on both bedrock-runtime and bedrock-mantle. It offers JSON Schema output formatting and strict tool use, with constrained decoding to prevent schema-violating tokens. Bedrock validates against a supported subset of JSON Schema Draft 2020-12, compiles new schemas into grammar artifacts, and caches them for 24 hours.

**Mechanism:** Bedrock validates and compiles supported schemas into grammar artifacts, constrains generation to the grammar, and caches artifacts for 24 hours; structure changes invalidate the cache and trigger recompilation. This turns schema handling into a runtime lifecycle concern: first use can add compilation delay, and a structural schema change requires fresh compilation.

**Why now:** The announcement matters as Claude users can now apply schema-constrained generation through Bedrock’s two endpoints, not only handle output formatting in application code. For builders, **First implication:** This can reduce parsing and retry work, while making schema compatibility and changes an explicit part of deployment planning.

**Evidence boundary:** These are AWS’s product claims; the source provides no independent benchmarks quantifying reliability, latency, or cost effects. The supported schema subset also means this should not be read as support for every JSON Schema feature.

**Watch condition:** Watch for documentation or measured reports clarifying schema-subset limitations, first-request compilation latency, and how real workloads fare when schemas change.

The mechanism has architectural relevance to agent integrations because tool parameters are now checked against schemas at the service boundary. This record is distinct because no prior New Runtime analytical record was supplied; the earlier public post about Claude Structured Outputs is historical context, not a record to extend.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)