Fine tuning gpt-4o-mini with text removes multimodal capabilities

API Bugs
1

I have fine-tuned gpt-4o-mini with a text dataset, and when I tried to request it with an image it threw the error

BadRequestError: Error code: 400 - {‘error’: {‘message’: ‘Invalid content type. image_url is only supported by certain models.’, ‘type’: ‘invalid_request_error’, ‘param’: ‘messages.[0].content.[1].type’, ‘code’: None}}

2

This is not a bug so much as it is the current state of things. It is unclear how fine-tuning a model affects the vision capabilities, so all fine-tunes are for the moment text/text only.