Recently, OpenAI has officially released its new and latest GPT-4.1 and GPT-4.1 mini AI models for ChatGPT. After these AI models, the company has now launched the research preview of Codex, a cloud-based software engineering agent that can work on many tasks in parallel, powered by Codex-1.
We’re launching a research preview of Codex: a cloud-based software engineering agent that can work on many tasks in parallel.
Rolling out to Pro, Enterprise, and Team users in ChatGPT starting today.https://t.co/HqiAtgydwh
— OpenAI (@OpenAI) May 16, 2025
More about Codex
Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering. Codex can perform tasks for you, such as writing features, answering questions about your codebase, fixing bugs, and proposing pull requests for review. Codex can read and edit files, as well as run commands including test harnesses, linters, and type checkers.
Codex is being rolled out to ChatGPT Pro, Enterprise, and Team users, and support for Plus and Edu is coming soon.
How does Codex work?
You can access Codex through the sidebar in ChatGPT and assign it new coding tasks by typing a prompt and clicking “Code”. If you want to ask Codex a question about your codebase, click “Ask”. Task completion typically takes between 1 and 30 minutes, depending on complexity. Codex also provides verifiable evidence of its actions through citations of terminal logs and test outputs, allowing you to trace each step taken during task completion.
You can review the results, request further reviews, open a GitHub pull request, or directly integrate the changes into your local environment. It will remain essential for users to manually review and validate all agent-generated code before integration and execution.
To balance safety and utility, Codex was trained to identify and precisely refuse requests aimed at the development of malicious software, while clearly distinguishing and supporting legitimate tasks. During task execution, internet access is disabled, limiting the agent’s interaction solely to the code explicitly provided via GitHub repositories and pre-installed dependencies configured by the user via a setup script. The agent cannot access external websites, APIs, or other services.
It is revealed that technical teams at OpenAI have started using Codex as part of their daily toolkit. The company has also been working with a small group of testers to better understand how Codex performs across diverse codebases, development processes, and teams. Also, do note that as a research preview, Codex currently lacks features like image inputs for frontend work and the ability to course-correct the agent while it’s working.
Codex: Availability
Codex, as mentioned above, is being rolled out to ChatGPT Pro, Enterprise, and Team users globally, with support for Plus and Edu coming soon. Users will have generous access at no additional cost for the coming weeks, after which the company will roll out rate-limited access and flexible pricing options that let you purchase additional usage on demand.
Apart from Codex, OpenAI is also releasing a smaller version of Codex-1, a version of o4-mini designed specifically for use in Codex CLI. It’s available now as the default mode in Codex CLI and in the API as codex-mini-latest. While connecting your developer account to Codex CLI has been made easier, you can now sign in with your ChatGPT account and select the API organization you want to use.
