Gemini Embedding 2
Rank #160
google
google/gemini-embedding-2
Usage data date 2026-07-26 · updated daily
Usage and specs
Daily rank#160
Daily tokens6B
Daily requests12M
Daily change
−53.0%
Context window8.2K
What is Gemini Embedding 2
Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.
Tools built on this model
Google Gemini
Most useful for people already working in Google services, with plan limits and data permissions worth checking first.
Google AI
Best for self-taught learners and developers who want to connect AI study with hands-on practice; not for learners needing systematic Chinese-language instruction.
Imagen
Best for researchers, engineers, and technology decision-makers tracking text-to-image progress; not for casual users who want to generate images right away.
Gemini
Best for users embedded in the Google ecosystem who need multimodal and automation power; not suitable for users in restricted regions or those who avoid Google services.
PaLM 2
Suited to AI developers, researchers, and enterprise teams in the Google ecosystem; not for everyday users seeking a ready-made consumer chatbot.