Hi all,
I would like to figure out for my project on image understanding where image with high resolution really needs ‘closer look’ by 4o, and therefore ‘auto’ mode is a good balance between price and quality. To this end, I could not fathom the rules of ‘auto’ mode. Can anyone share the insights on how 4o decides to go low-res or high-res?
https://platform.openai.com/docs/guides/vision?lang=python
By controlling the detail parameter, which has three options, low , high , or auto , you have control over how the model processes the image and generates its textual understanding. By default, the model will use the auto setting which will look at the image input size and decide if it should use the low or high setting.