ModelOpenAI

OpenAI releases guide for GPT-6 Astra, Sol and Luna

Original title: A model guide for the GPT-6 family

Plain language

What it is: OpenAI published a guide for its new GPT-6 model family, which includes GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna. The guide helps users choose the right model and manage costs for different tasks.
How it works: Users can match their tasks to a model based on intelligence and price, adjust reasoning levels, and use features like prompt caching to save money. The models can also interact directly with websites and desktop apps.
Where it is available: The guide applies to developers and businesses building applications using OpenAI's API and Codex.
Example: Hex uses GPT-6 Astra to turn sales performance questions into written findings and interactive dashboards.

What it is: OpenAI released a practical guide for deploying and optimizing the GPT-6 model family, detailing GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna.
How it works: It explains how to manage context and costs using prompt caching and compaction, adjust reasoning effort levels, and control execution speed. It also covers long-running tasks using mid-turn steering, asynchronous tool calling, and multi-agent delegation.
Where it is available: These features and models are available through the OpenAI API and Codex.
Example: Cognition uses GPT-6 Astra inside Devin to run software tests and generate reports that separate passed checks from untested areas.

The headline and explanation on this page are based on OpenAI's post. The full details are in the original.

A model guide for the GPT-6 family