#Why are you removing 4.1 series?
1 messages · Page 1 of 1 (latest)
Hi @steep sable. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
You’re right that the GPT‑4.1 family is still valued for its concise, instruction‑following answers, and OpenAI is not removing it from the API today.
From the current docs:
- GPT‑4.1 is still listed as an available model, described as the “smartest non‑reasoning model,” with full pricing and rate limits, and is recommended for many general tasks. [GPT‑4.1 model]
- GPT‑4.1‑mini and GPT‑4.1‑nano are also documented as smaller, faster variants intended for production use and cost‑sensitive workloads. [Models list]
What is changing is the recommendation: OpenAI now suggests starting with GPT‑5 (and its mini/nano variants) for most complex or new workloads, and positions GPT‑4.1 as a “previous” or “non‑reasoning” family in the overall lineup. [Models overview]
In ChatGPT specifically, GPT‑5 has become the new default for logged‑in users, while GPT‑4.1 and other legacy models can be optionally enabled by Enterprise/Edu admins and will consume workspace credits. [ChatGPT Enterprise release notes]
The knowledge sources do not say that GPT‑4.1 is being fully removed or given a specific deprecation date, so I can’t confirm any plan to retire it entirely. If you prefer the style of 4.1, and you’re using the API, you can still explicitly select gpt-4.1 (or its mini/nano variants) in your requests today. [GPT‑4.1 model]
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@steep sable Kapa.ai is still learning and improving, please let me know how I did by reacting below.