OpenAI Codex OpenAI Codex

Start using Codex(opens in a new window)

Listen to article

_Update on May 16, 2025:_ _We launched Codex, a cloud-based software engineering agent that can work on many tasks in parallel.Learn more_⁠_._⁠⁠(opens in a new window)⁠⁠(opens in a new window)⁠⁠(opens in a new window)

_Update on April 16, 2025: We launched Codex CLI, our new open source local coding agent. To get started, please visithttps://github.com/openai/codex_⁠(opens in a new window)_._

_The OpenAI Codex models weredeprecated_⁠(opens in a new window)_in March 2023. To learn about our latest coding models, please visit ourdocs_⁠(opens in a new window)_._

* * *

Codex is the model that powersGitHub Copilot⁠(opens in a new window), which we built and launched in partnership with GitHub a month ago. Proficient in more than a dozen programming languages, Codex can now interpret simple commands in natural language and execute them on the user’s behalf—making it possible to build a natural language interface to existing applications. We are now inviting businesses and developers to build on top of OpenAI Codex through our API.

Spacegame

Play video

Five browser windows on a computer desktop screen showing repeated 'HELLOWORLD' text.

Datascience

Video carousel navigation

Play video

Play video

Play video

Play video

Video carousel navigation

* Go to slide 1

Creating a Space Game with OpenAI Codex

Tweet

OpenAI Codex is a descendant of GPT‑3; its training data contains both natural language and billions of lines of source code from publicly available sources, including code in public GitHub repositories. OpenAI Codex is most capable in Python, but it is also proficient in over a dozen languages including JavaScript, Go, Perl, PHP, Ruby, Swift and TypeScript, and even Shell. It has a memory of 14KB for Python code, compared to GPT‑3 which has only 4KB—so it can take into account over 3x as much contextual information while performing any task.

GPT‑3’s main skill is generating natural language in response to a natural language prompt, meaning the only way it affects the world is through the mind of the reader. OpenAI Codex has much of the natural language understanding of GPT‑3, but it produces working code—meaning you can issue commands in English to any piece of software with an API. OpenAI Codex empowers computers to better understand people’s intent, which can empower everyone to do more with computers.

Once a programmer knows what to build, the act of writing code can be thought of as (1) breaking a problem down into simpler problems, and (2) mapping those simple problems to existing code (libraries, APIs, or functions) that already exist. The latter activity is probably the least fun part of programming (and the highest barrier to entry), and it’s where OpenAI Codex excels most.

OpenAI Codex is a general-purpose programming model, meaning that it can be applied to essentially any programming task (though results may vary). We’ve successfully used it for transpilation, explaining code, and refactoring code. But we know we’ve only scratched the surface of what can be done.

We’re now making OpenAI Codex available in private beta via our API, and we are aiming to scale up as quickly as we can safely. During the initial period, OpenAI Codex will be offered for free. OpenAI will continue building on the safety groundwork we laid with GPT‑3—reviewing applications and incrementally scaling them up while working closely with developers to understand the effect of our technologies in the world.

OpenAI Codex is a descendant of GPT‑3; its training data contains both natural language and billions of lines of source code from publicly available sources, including code in public GitHub repositories. OpenAI Codex is most capable in Python, but it is also proficient in over a dozen languages including JavaScript, Go, Perl, PHP, Ruby, Swift and TypeScript, and even Shell. It has a memory of 14KB for Python code, compared to GPT‑3 which has only 4KB—so it can take into account over 3x as much contextual information while performing any task.

GPT‑3’s main skill is generating natural language in response to a natural language prompt, meaning the only way it affects the world is through the mind of the reader. OpenAI Codex has much of the natural language understanding of GPT‑3, but it produces working code—meaning you can issue commands in English to any piece of software with an API. OpenAI Codex empowers computers to better understand people’s intent, which can empower everyone to do more with computers.

Once a programmer knows what to build, the act of writing code can be thought of as (1) breaking a problem down into simpler problems, and (2) mapping those simple problems to existing code (libraries, APIs, or functions) that already exist. The latter activity is probably the least fun part of programming (and the highest barrier to entry), and it’s where OpenAI Codex excels most.

Authors

Wojciech Zaremba, Greg Brockman, OpenAI

Related articles

View all

Global news partnerships: Le Monde and Prisa Media Company Mar 13, 2024

Review completed & Altman, Brockman to continue to lead OpenAI Company Mar 8, 2024

OpenAI announces new members to board of directors Company Mar 8, 2024

Related articles

View all

Global news partnerships: Le Monde and Prisa Media Company Mar 13, 2024

Review completed & Altman, Brockman to continue to lead OpenAI Company Mar 8, 2024

OpenAI announces new members to board of directors Company Mar 8, 2024