Skip to content
AI Atlas
ModelActivefamily · Gemini

Gemini Embedding 2

Google

Our first multimodal embedding model, mapping text, images, video, audio, and PDFs into a unified embedding space for advanced semantic search and RAG systems.

quality67

Updated 50 min ago · first seen 11 Sept 2026

model_01M293VBSGZDM1M18A67JX98P6

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · API model id

1 claims · 1 propertiesShow all properties

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
gemini-embedding-2-previewcurrentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →