What's New in Codex for Developers

A short refresher on the latest Codex for Developers updates

What this course covers

The course runs across 7 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

GPT-5.5 removed from Codex — What's different: GPT-5.5 stopped working in Codex for people signed in with ChatGPT on October 14, 2026; API-key sessions are not affected. Why it matters for your work: Saved settings, custom agents or scheduled tasks that still pick GPT-5.5 need a new model or they will not run as expected. Try it (about 2 minutes): Open the model picker and choose GPT-6.1 Sol instead, then check any saved settings or scheduled tasks that named GPT-5.5. No access? Here's what you'd see: When signed in with ChatGPT, GPT-5.5 is unavailable in Codex, and GPT-6.1 Sol appears in the model picker. Renamed or removed: GPT-5.5 removed from Codex (ChatGPT sign-in); use GPT-6.1 Sol
GPT-6.1 Sol is the new main Codex model — What's different: OpenAI added GPT-6.1 Sol to Codex, a model that comes close to its top model on hard work at a lower cost, and made it the default model in the Codex CLI. Why it matters for your work: It is now the recommended choice for long coding and document jobs, so your tasks may run better without you changing anything. Try it (about 2 minutes): Open the model picker in the Codex app (or type /model in the CLI) and check that GPT-6.1 Sol is selected, then run a small task with it. No access? Here's what you'd see: GPT-6.1 Sol appears in the Codex app model picker and is selected as the default model in the Codex CLI.
Import your setup from Claude Code, Cowork or Cursor — What's different: The desktop app can import instructions, settings, skills, plugins, projects and recent work from Claude Code, Claude Cowork and Cursor, and the CLI can do the same with /import. Why it matters for your work: If you or your team used another AI agent, you can bring your work and setup over instead of starting from scratch. Try it (about 2 minutes): In the desktop app, open Settings > Import, pick the tool you used before, and import one project; turn on automatic updates if you want it kept in sync.
GPT-5.4 and GPT-5.4 mini removed from Codex — What's different: GPT-5.4 and GPT-5.4 mini were removed from Codex for people signed in with ChatGPT on August 31, 2026; API-key sessions keep them. Why it matters for your work: Anything still set to these models, such as a saved default or a scheduled task, has to point to a current model. Try it (about 2 minutes): Open the model picker and select a current model such as GPT-6.1 Sol, then check scheduled tasks and custom agents for the old names. No access? Here's what you'd see: Users signed in with ChatGPT no longer see GPT-5.4 and GPT-5.4 mini in the Codex model picker.
Steer the CLI while it is still answering — What's different: In the Codex CLI you can now send a follow-up while Codex is still responding, and it changes course right away. Why it matters for your work: You can fix a wrong direction early instead of waiting for a long answer to finish and starting over. Try it (about 2 minutes): Give the CLI a multi-step task, and while it is answering type a short correction such as 'use the other file' and press Enter. Needs: Codex CLI.
Also new — - Search and change CLI settings with /config: The Codex CLI now features a searchable /config panel to change settings instantly. - GPT-6 Luna for quick, high-volume tasks: GPT-6 Luna has been added as a lighter model for quick, high-volume tasks. - Codex cloud now works with GitLab (beta): Codex cloud now supports GitLab integration for starting tasks and reviewing merge requests. - The --full-auto flag is gone from codex exec: The --full-auto flag has been removed from codex exec in the CLI. - Retirement of the 'untrusted' approval setting: The untrusted approval setting has been retired and is no longer available. - Codex Cloud environments now require publishing and support desktop reopening: Codex Cloud environments now require publishing and can be reopened in the desktop app. - GitHub pull request review transitioned to Codex Cloud (Legacy): GitHub pull request reviews have transitioned to Codex Cloud (Legacy) ahead of scheduled deprecation. - New memory system is on by default in the CLI: Fresh Codex CLI profiles now use the newer memory system by default. - Worktrees are on by default in the CLI: Worktree support is now enabled by default in the Codex CLI. - AGENTS.md only loads in projects you trust: Codex now requires projects to be trusted before loading their AGENTS.md instructions. - and 5 more: Select and search the CLI transcript by keyboard; Built-in Google Cloud Vertex AI provider; codex mcp-server command removed; Clearer explanations when a request is blocked; Change reasoning effort mid-conversation
Try one on your own work — Pick the one main change from this course that is most useful to your job. Try it in your own Codex on a real task, then paste or describe what you got. The coach gives short, specific feedback. No access to the app or plan it needs? Describe how you would use it on a real task this week. That counts too. There is no score and no pass or fail: finishing this completes the course.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

The material is pitched at intermediate level, and takes roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: Codex track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

Codex for Developers: Core — A developer's working introduction to Codex, OpenAI's agentic coding tool. Learners delegate real tasks against a repository, manage context, review PR-style output, and keep human judgment in the loop. They finish using Codex daily with review discipline intact.
What's New in Codex — A short refresher on the latest Codex updates
Codex for Everyone: Core — The working level for non-technical builders: keeping your Codex-built tools alive and useful. Learners improve and fix their own tools, connect them safely to real files and data, and reuse what works. They finish knowing their limits - and exactly when to hand something to an engineer.
Codex for Everyone: Essentials — Data & Reporting Playbook — A focused playbook for turning a messy spreadsheet export into a simple, repeatable report with Codex, without writing code. Learners clean a copy of the file safely, have Codex build a one-page report, check the numbers against the source by hand, and set it up to re-run next week. About 45 minutes including the final.
Codex for Everyone: Essentials — Internal Tools Playbook — A focused playbook for building a small internal tool with Codex in the ChatGPT desktop app, without writing code. Learners pick a sensible first tool, plan it and let Codex build it on fake data, check every result by hand, and finish with a plain run guide plus a clear sense of when a tool needs an engineer. About 45 minutes including the final.

Frequently asked questions

How long does this course take?

It runs roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code what-s-new-in-codex-for-developers-8250f555.