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.
6 October 2026
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
- Model names live in one configuration file, not scattered through code.
- There is an automated test that runs a sample of real tasks against any new model before it is switched on.
- Someone owns a calendar of vendor deprecation dates.
- Where possible, the product can switch between two vendors without a rewrite.
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.