release
Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
Builders relying on specific model behaviors or performance profiles in ChatGPT need to update their workflows before the deadline to avoid disruption, especially if they depend on features unique to the retiring models.
What happened
OpenAI has announced the retirement of GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini from ChatGPT, effective February 13, 2026. This follows a prior announcement regarding the retirement of GPT-5 variants (Instant, Thinking, and Pro). According to the OpenAI Blog, these changes affect only the ChatGPT interface; the API will see no modifications at this time. For developers and solopreneurs building AI workflows on ChatGPT, this means the specific model capabilities tied to these versions will no longer be available through the chat interface after the cutoff. Users relying on the distinct behavior of GPT-4o, GPT-4.1, or o4-mini for tasks like reasoning or cost efficiency may need to migrate to alternative models within ChatGPT—likely GPT-5 or its successors—or adjust their prompts and expectations. The retirement underscores OpenAI’s ongoing model consolidation strategy, pushing users toward newer architectures. While API users are unaffected, those who prototype or deploy ChatGPT-based solutions should plan workflows accordingly to avoid sudden changes. This move may also signal a shift in which models are prioritized for future features and availability.
Key takeaways
- OpenAI will remove GPT-4o, GPT-4.1, GPT-4.1 mini, and o4-mini from ChatGPT on February 13, 2026.
- The retirement coincides with the previously announced shutdown of GPT-5 (Instant, Thinking, and Pro) in ChatGPT.
- No changes are planned for the API; these models remain accessible via API after the date.
- Users of ChatGPT must switch to other models for continued access past the retirement date.
Why it matters
Builders relying on specific model behaviors or performance profiles in ChatGPT need to update their workflows before the deadline to avoid disruption, especially if they depend on features unique to the retiring models.
This is an original editorial digest by AI Workflow Pro. Full reporting at the source:
Read the original on OpenAI BlogMore AI news
All news →





Join the AI Workflow Pro Community