Image segmentation using Gemini 2.5

Google's Gemini 2.5 Flash model now offers image segmentation capabilities at a remarkably low cost. The new feature can generate segmentation masks for objects in images, in addition to 2D bounding boxes. Using the non-thinking mode of Gemini 2.5 Flash, image segmentation can be performed for as little as 1/100th of a cent per image. This advancement brings powerful computer vision capabilities to a wider range of applications due to its affordability and accessibility through the Gemini API.