Google Vertex AIOfficial Docs

Gemini Embedding Experimental 03-07

gemini-embedding-exp-03-07

## Gemini Embedding Experimental 03-07 The Gemini Embedding Experimental 03-07 model provides a powerful distributed representation of text, enabling a wide range of multimodal applications. With support for a 8192 token context window, this model can handle diverse inputs including text, image, video, audio, transcription, and text-to-speech. Supports a 8192 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.