It can be cheaper to use a more expensive model (in terms of tokens/$) if it can be tuned with the same context you'd have to otherwise send with every prompt.
Right now, gpt-3.5-turbo cannot be tuned, so you must fit everything in the 4k limit. There are 4 other models that can be tuned.
https://platform.openai.com/docs/guides/fine-tuning
It can be cheaper to use a more expensive model (in terms of tokens/$) if it can be tuned with the same context you'd have to otherwise send with every prompt.
Right now, gpt-3.5-turbo cannot be tuned, so you must fit everything in the 4k limit. There are 4 other models that can be tuned.