Skip to content
AI ConnectPowered by VELENTIS
AI-generated1 min

Amazon Bedrock Adds Structured Outputs for Anthropic Claude Models

Amazon Bedrock has introduced structured outputs for all Anthropic Claude models across bedrock-runtime and bedrock-mantle endpoints, delivering schema-compliant JSON directly.

This article was AI-generated and published automatically. Context, labelling and all sources at the end of the article.

(KI-generiertes Symbolbild: Gemini / AI Connect)

Amazon Bedrock has updated its service to support structured outputs across its entire roster of Anthropic Claude models. The capability is available to users calling either the bedrock-runtime or bedrock-mantle endpoints. Through this update, system calls return schema-compliant JSON that adheres directly to a defined structure.

The functionality is driven by a JSON Schema output format combined with strict tool use. This framework allows developers to obtain formatted responses without writing custom parsing scripts. Additionally, the system removes the requirement for secondary post-processing or programmatic retry logic to enforce the output format.

What this means for you

For engineering teams building on AWS, guaranteed schema adherence removes the need for brittle regex parsing and validation wrappers around model calls. Eliminating retry logic for malformed outputs directly cuts down both response latency and unnecessary token costs. It also makes Claude models more reliable when feeding data directly into downstream APIs and automated databases.

Evidence

Solidly sourced
46/100

  • Amazon Bedrock provides structured outputs for all Anthropic Claude models across bedrock-runtime and bedrock-mantle endpoints.

    single source
    Quote

    „Amazon Bedrock now supports structured outputs for all Anthropic Claude models on both the bedrock-runtime and bedrock-mantle endpoints.“

    AWS, Machine Learning

  • The feature delivers schema-compliant JSON conforming to a defined structure without requiring custom parsing, retry logic, or post-processing.

    single source
    Quote

    „Receive schema-compliant JSON that conforms to a defined structure, without custom parsing, retry logic, or post-processing“

    AWS, Machine Learning

  • The structured output feature operates through JSON Schema output format and strict tool use.

    single source
    Quote

    „using JSON Schema output format and strict tool use.“

    AWS, Machine Learning

Sources

The evidence score is computed, not hand-set: from confidence, the number of sources and the share of verified statements.

Source & transparency

As of: October 19, 2026

AI-generatedAI-generated: produced automatically from vetted sources with technical quality checks (source, quote and figure verification); no human sign-off of each item before publication

Sources
1
Verified statements
0 / 3
Evidence score
46Solidly sourced
Generative AIUse Cases

Want to put this into practice?

We connect you with suitable AI providers from the DACH region, free of charge and without obligation.

What's next?

What does AI really cost?

Honest price ranges for your project, independent, with nothing to sell you.

See prices

Get your team ready (AI Act)

The EU AI Act requires providers and deployers to take measures supporting AI literacy in the team — not a specific level. Baseline training for your team is in development.

Find the right training

Find the right provider

Describe your project. We connect you with suitable providers at a fair price.

Start the analysis
Back to AI Radar