Gemini Embedding 2

Name: Gemini Embedding 2
Author: Google

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

Live

Open / InstallLast updated August 5, 2026

Description

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space. Supports a context window of 8,192 tokens. Input priced at $0.2 per million tokens. Weights are not publicly released; access is via the provider API.

Author

Google

Platform

api

Pricing model

paid

Capabilities

Text embeddings
8,192 token context
File attachments
Image input
Audio input

Benchmarks

No benchmark results have been added yet.