OpenAI announced today that its latest and most powerful agent coding model, GPT-5.1-CodexMax, is now fully integrated into the response API, allowing developers to directly incorporate this top-tier coding intelligence into existing applications and production workflows.

This model was first introduced in Codex two weeks ago, and it has attracted attention for significant improvements in complex task decomposition, code generation quality, multi-step reasoning, and autonomous agent execution capabilities. Now, with the official release of the API, developers can immediately call this flagship model in a broader range of environments.

QQ20251205-100439.png

Notably, users who call CodexCLI using an API key have also been granted access to GPT-5.1-CodexMax. This means that whether building automated development tools, internal R&D assistance systems for enterprises, or intelligent programming products for end users, they can immediately leverage the full capabilities of this model.

OpenAI stated that this update aims to further lower the entry barrier for high-performance AI programming capabilities, enabling more products and services to offer a "ready-to-write, auto-correcting, self-executing" programming assistant experience.