Amazon Bedrock Enables Million-Token Context Windows with GPT-5.6 Models

OpenAI's GPT-5.6 Sol, Terra, and Luna models now handle up to one million tokens per input on Amazon Bedrock, supporting comprehensive document and codebase processing.

By Isabel Turner · Editorial pseudonym · 2026-08-03 · 1 min read

AI-ASSISTED REPORTING · RETROSPECTIVE ARCHIVE

Retrospective edition: 2026-08-03. Source published: 2026-08-03. Added to this archive: 2026-11-03. This briefing was prepared later from the linked announcement; it was not published on this website on the historical edition date.

With a 1 million token context window, GPT-5.6 models can analyze full code repositories, lengthy legal documents, and maintain entire conversation histories in one request, reducing information loss from chunking. This expanded context allows broader reasoning and more coherent responses for complex workflows and code reviews.

Available in multiple AWS US regions, customers can access these models via Amazon Bedrock's Console or API. The platform applies prompt caching with discounts for repeated context, enhancing efficiency for long-context requests.

Source & further reading

OpenAI GPT-5.6 Sol, Terra, and Luna now support 1 million token context windows on Amazon Bedrock ↗

Source published 2026-08-03. 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.