Gemini Embedding 2: natively multimodal embedding model
panarky
22 points
2 comments
March 10, 2026
Related Discussions
Found 5 related stories in 92.3ms across 8,303 title embeddings via pgvector HNSW
- Gemini API File Search is now multimodal gmays · 45 pts · May 10, 2026 · 66% similar
- Gemini Omni meetpateltech · 297 pts · May 19, 2026 · 65% similar
- Ask HN: Best Embedding Models? devstein · 11 pts · May 05, 2026 · 62% similar
- Gemini 3.5 Flash spectraldrift · 697 pts · May 19, 2026 · 62% similar
- Gemini 3.1 Flash-Lite: Built for intelligence at scale meetpateltech · 51 pts · March 03, 2026 · 59% similar
Discussion Highlights (2 comments)
jeanloolz
This is colossal. It can creates embeddings on pretty much any type of format, video, audio, documents. The context is still a bit small compared to what we are used to in text, but this seems major
jerrygoyal
what's the pricing and how does it compare to zembed-1 for text only embeddings?