Google Vertex AIOfficial Docs

Gemini Embedding Experimental

gemini-embedding-exp

## Gemini Embedding Experimental The Gemini Embedding Experimental model provides a powerful distributed representation of text, enabling advanced natural language processing capabilities. With a context window of up to 8192 tokens, this model can handle a wide range of text-based inputs and outputs, 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.