OpenAI Launches Codex: A Smarter AI Assistant for Software Engineers

OpenAI has officially introduced Codex, its most advanced AI coding assistant yet—designed to help developers tackle real-world software engineering challenges faster and more efficiently.

At the heart of Codex is Codex-1, a powerful model that writes cleaner and more accurate code than its predecessor, o3. What sets Codex apart is its ability to automatically test the code it generates—running those tests repeatedly until the results pass. That means fewer bugs and more reliable output, straight from your AI assistant.

Codex is more than just a code generator. It can work on tasks ranging from debugging and adding new features to answering coding questions, all within a timeframe of one to thirty minutes, depending on complexity. And while Codex gets to work, users can continue using their computer and browser without interruption.

Now available to ChatGPT Pro, Enterprise, and Team users, Codex is designed to handle multiple tasks at once, streamlining workflows without taking over the user’s system. OpenAI also plans to extend access to ChatGPT Plus and Edu users soon, with “generous” availability promised in the near future.

Alongside Codex, OpenAI is rolling out a major update to its open-source tool Codex CLI. The latest version uses the o4-mini model by default, offering enhanced support for development tasks. This model is also accessible through OpenAI’s API at a cost of $1.50 per million input tokens and $6 per million output tokens.

With these new capabilities, OpenAI continues to push AI deeper into the software engineering space—aiming to make AI-powered development faster, smarter, and more accessible to teams of all sizes.

Citeste mai mult