This new parameter in the Responses API provides explanations of how models arrive at answers for tasks like complex coding and multi-step problem solving. The summaries support developer debugging, evaluation, and user transparency by detailing the model's approach.
Available across all AWS Regions supporting OpenAI GPT models, including in-region and cross-region inference, this feature helps users better understand model outputs and improves interpretability in AI applications.
Source & further reading
Amazon Bedrock now supports reasoning summaries for OpenAI models ↗Source published 2026-10-09. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.