I have a question for Open AI. If the fine tuned availability will be ceased after January 2027, will this means creating API keys will be stopped too?
Also what if I want to fine tune my project on something specific in my profession to get most accurate results, as was done, what to do now? models are always generalized and not ever enough in getting accurate answers in all professions.
This is what I want to know. I use a fine tuned version of 4.1 for character creation. I have to fine tune because a prompt and RAG isn’t enough for a solid/consistent personality.
Hope somebody @OpenAI_Support answers that.
You mean to ask: will your API key still be able to list and run your fine-tuning AI model? That answer is provided:
Jan 6, 2027 Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated.
Above, OpenAI means when the base model of your fine-tuning model is shut off, not when it is deprecated. Deprecated means that it has a limited lifespan and will become obsolete, and you should start planning your migration, not that it has already ceased to operate. The fine-tuning endpoint, for example, is currently deprecated, not shut off.
Hi and welcome to the community!
Regarding this question:
According to the official deprecations page, fine-tuned models remain accessible until the underlying base model is deprecated.
Inference on fine-tuned models will only be turned off once the underlying base model is deprecated.
Based on experience, this is usually a period of three months or longer.
Same. Have you explore another alternative?