GPT-5.5 leaves Codex on 14 October: the hidden risk of hard-coded AI models

OpenAI retires GPT-5.5 from ChatGPT and Codex on 14 October 2026, while the API stays available. AI coding tool users and AI software teams searching for a fix should check where models are hard-coded.

OpenAI will retire GPT-5.5 from ChatGPT, ChatGPT Work and Codex on 14 October 2026, across all plan types. Searches for the retirement date and migration steps are rising as teams realise their workflows name the model explicitly.

What is and is not affected

The retirement covers ChatGPT sign-in access. It does not apply to the OpenAI API, and Codex sessions that authenticate with an API key keep working. Teams using the sign-in route are pointed to a newer model in the current range. Reporting on the replacement’s exact name varies, so check OpenAI’s own notice rather than relying on third-party summaries.

The practical risk is not the retirement itself. It is that the model name is written into places nobody remembers: saved workspace defaults, scheduled tasks, scripts, custom agents and CLI commands. When the date passes, those fail, sometimes silently, sometimes by quietly falling back to a different model with different behaviour and cost.

The pattern behind it

Vendors now ship and retire models in months, not years. Any product or internal automation that hard-codes a model version has a built-in expiry date.

What good looks like

So what

If your business runs customer-facing features or internal workflows on an AI model, ask your developer where the model name is set and who is watching deprecation notices. It is a one-hour audit that prevents an outage. BuildApps builds AI products with model switching and evaluation designed in from the start, as part of AI-assisted development. To review an existing AI feature, start a project.

← All research

More research.

MAI Code 2 and MAI Code 2 Flash arrive in GitHub Copilot, including a model for free-plan users

GitHub has added Microsoft's MAI Code 2 and MAI Code 2 Flash to Copilot across editors, the CLI, the cloud agent and mobile, with administrators able to control access through model policy.

Read ›

GitHub Copilot team customizations are generally available: set default agent plugins for a whole team

GitHub has made team customizations generally available, so team maintainers and organisation owners can set approved Copilot agent plugins as defaults for every member of a team.

Read ›

Claude Code 2.1.330: scheduled tasks run for 30 days, risky rm commands ask first, and enterprise sign-in arrives

Claude Code 2.1.330 extends scheduled tasks and /loop from 7 to 30 days, makes more destructive rm commands ask for approval, and adds sign-in for organisations managed in Anthropic's Enterprise Admin Console.

Read ›

OpenAI's GPT-6.2 Astra and Sol are generally available in GitHub Copilot, with a code review focus

GitHub made OpenAI's GPT-6.2 Astra and GPT-6.2 Sol generally available in Copilot for agentic coding and code review. GitHub reports early tests catching more real issues.

Read ›

Copilot code review adds adaptive effort and secret detection in public preview

GitHub's Copilot code review can now choose Lite, Balanced or Max effort per pull request and flag exposed secrets, both in public preview. Azure DevOps support is generally available.

Read ›

Claude Code 2.1.329: /code-review now covers the whole branch, and saved scheduled tasks need rescheduling

Claude Code 2.1.329 makes /code-review review the whole branch against the default branch and adds fixes for Code Mode and sign-in. Saved scheduled tasks mostly need setting up again.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work