Gemini 1.0 Pro Vision

The Gemini 1.0 Pro Vision model was an early version of Google's powerful image understanding AI, optimized for tasks like object detection, image classification, and visual reasoning. While it has been deprecated, this model can still be a useful tool for certain applications.

Supports a 12,288 token context window. Handles Text, Image inputs and outputs.

Capable of generating structured output formats.