← AI PulseJul 24, 2026

Wire · news · Single-source brief

OpenAI GPT-5.6 Sol, Terra, and Luna Now Available on Amazon Bedrock

OpenAI's GPT-5.6 Sol, Terra, and Luna models are now generally available on Amazon Bedrock, offering new options for inference and cost management.

By Illumora Editorial

Source · Jul 24, 2026, 3:40 PM · On Illumora · Jul 24, 2026, 3:47 PM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →AWS Machine Learning Blog — Get started with OpenAI GPT-5.6 Sol, Terra, and Luna on Amazon Bedrock | Amazon Web Services
Save

OpenAI's GPT-5.6 Sol, Terra, and Luna models have reached general availability on Amazon Bedrock. Users can now access these models for various applications, with guidance provided on model selection and operational aspects.

Key Points

  • OpenAI GPT-5.6 Sol, Terra, and Luna are generally available on Amazon Bedrock.
  • Users can select a specific model from this suite.
  • Inference can be run through the Responses API on the bedrock-mantle endpoint.
  • Prompt caching is available to help reduce operational costs.
  • The OpenAI Codex coding agent can be connected.
  • Guidance is provided for planning quotas and scaling.

Context

According to the AWS Machine Learning Blog, the general availability of these OpenAI models on Amazon Bedrock expands the range of foundational models accessible to developers. The announcement details how to integrate and manage these models within the Amazon Bedrock environment.

Why It Matters

This release provides builders with new OpenAI models on Amazon Bedrock, offering additional choices for developing and deploying AI-powered applications. The inclusion of features like prompt caching and guidance on scaling can influence operational efficiency and cost management.

What To Do

  • Review the documentation on selecting a model from the GPT-5.6 Sol, Terra, and Luna suite.
  • Explore running inference via the Responses API on the bedrock-mantle endpoint.
  • Investigate prompt caching strategies to optimize costs.
  • Note the instructions for connecting the OpenAI Codex coding agent.
  • Plan for quotas and scaling requirements when integrating these models.