Rocket - Start building, Now!
Mini toolsGemini Embedding 2
By Google
Model family: Gemini
Gemini Embedding 2 (gemini-embedding-2-preview) produces embeddings for text, images, video, audio, and PDFs in one unified space for cross-modal retrieval and classification. Google describes support that includes up to 8192 input tokens for text, up to 6 images per request, up to 120 seconds of video, native audio embedding without transcription, and PDF embedding up to 6 pages, plus interleaved multimodal inputs in a single request and MRL-based output dimension scaling down from 3072.
New
Multimodal
Gen 3
Overview
Gemini Embedding 2 is Google’s first natively multimodal embedding model that maps text, images, video, audio, and documents into a single shared embedding space.
About Google
At Google, we think that AI can meaningfully improve people's lives and that the biggest impact will come when everyone can access it.
Industry:
Technology, Information and Internet
Company Size:
182.000-190.000
Location:
Mountain View, CA, US
Website:
ai.google
Tools using Gemini Embedding 2
-
Tealgreen🙏 396 karmaMar 29, 2025@GeminiThey nailed it. It’s better than 3.7 at coding.
Last updated: March 11, 2026
