OpenAI GPT-5.1-Codex-Max Coding Model Arrives With Better Support for Windows

GPT-5.1-Codex-Max is OpenAI’s latest frontier agentic coding model, and it’s faster and more intelligent and efficient than previous models. It’s also the first to be trained to operate in Windows.

“We’re introducing GPT‑5.1-Codex-Max, our new frontier agentic coding model, available in Codex today,” the OpenAI announcement explains. “GPT‑5.1-Codex-Max is built on an update to our foundational reasoning model, which is trained on agentic tasks across software engineering, math, research, and more. GPT‑5.1-Codex-Max is faster, more intelligent, and more token-efficient at every stage of the development cycle–and a new step towards becoming a reliable coding partner.”

GPT-5.1-Codex-Max is notable for several reasons. It’s the first OpenAI coding model built for long-running, detailed work across multiple context windows, using a process called compaction to coherently work with over millions of tokens while completing a single task. It was trained on real-world software engineering tasks, including GitHub pull request creation, code review, frontend coding and Q&A, and it outperforms OpenAI’s previous models, of course.

But the big deal to me is that GPT-5.1-Codex-Max is the first Codex model that OpenAI trained to operate in Windows. This means it will be a better collaborator for developers using Windows and the Codex command line environment (CLI), but also that Windows users are finally getting Agent mode too. With this update, Codex can read files, write files, and run commands with fewer approvals.

GPT-5.1-Codex-Max launches today in Codex for ChatGPT Plus, Pro, Business, Edu, and Enterprise users, and API access is coming soon, OpenAI says.

You can learn more on the OpenAI website.