Hi everyone, i’m trying to integrate computer vision into my application. What i need is sending an image to an api and get back a complete description. Is there any model available to do so? (I used gpt4-vision and it was awesome but now it is deprecated). Thanks a lot.
Welcome to the dev community!
You should be able to use gpt-4o as a direct drop-in replacement for gpt-4-vision-preview (I’m assuming thats what you were referring to).
You can find more details on the implementation in the vision documentation.
1 Like
Also try gpt-4o-mini and compare results. You may gain some speed and cost benefits if the output works for you.