Hello,
I fine-tuned a “chatgpt-4o-mini” model on a large text dataset, when I tried to use the image recognition capapility of “chatgpt-4o-mini” model on the new model it gave me an error that this model not supporting the images.
1 Like
Welcome to the Forum!
Fine-tuning with images is currently only supported with gpt-4o-2024-08-06.
Vision fine-tuning capabilities are available today for all developers on paid usage tiers(opens in a new window). These capabilities are supported on the latest GPT-4o model snapshot,
gpt-4o-2024-08-06. Developers can extend existing fine-tuning training data for images using the same format as our Chat endpoints(opens in a new window).
Source: https://openai.com/index/introducing-vision-to-the-fine-tuning-api/
1 Like
Thank you for your reply. I didn’t train the model with images, but I intended to use it in my requests.
1 Like
Apologies for my misunderstanding. The same basically applies in that a fine-tuned gpt-4o-mini can currently only process text.
Thank you for your quick response. 
1 Like