Code Generation – C4: Container, Code, Cloud & Context

Searching in

Start typing to search

Find posts, pages, and products across your site.

No results found

Try different keywords or check your spelling.

Navigate · Select · Close

GPT-6 in Codex: Choosing Between Astra, Sol and Luna

Posted on September 26, 2026 by Nithin Mohan TK 28 min read

GPT-6 Astra, Sol and Luna with their list prices and the Codex configuration setting that assigns each one: review model, default model and subagent model

GPT-6 Astra, Sol and Luna are all in Codex and differ in price by a factor of a hundred. What has been published about them, what an agent session costs under the new caching and long-context rules, and what Codex CLI actually sends when each kind of work is given its own model.

GPT-5.2-Codex: 400K Context, Image Input and Microsoft Foundry

Posted on February 1, 2026 by Nithin Mohan TK 21 min read

A 400,000-token context window divided into instructions, repository files, the question and image, and room for reasoning and the answer, with three rules for prompt order

What OpenAI, Microsoft and GitHub have published about GPT-5.2-Codex, with sources, and what the 400,000-token window means in practice: how much code fits, what a session costs, and how prompt order decides whether caching applies.