Google Vertex AIOfficial Docs

Gemini 1.0 Pro Vision

gemini-1.0-pro-vision

## Gemini 1.0 Pro Vision The original Gemini 1.0 Pro Vision model was optimized for image understanding, providing a powerful multimodal AI solution for a variety of applications. This model supports a 12,288 token context window and handles inputs and outputs across Text, Image, Video, Audio, Transcription, and Text-to-Speech capabilities. Gemini 1.0 Pro Vision was deprecated on July 12, 2024, so users are encouraged to migrate to a newer Gemini version for the latest features and performance. Supports a 12,288 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.