Skip to main content
llm.info

Gemini Embedding

Google

Google's embedding model that maps text (and, in multimodal variants, images, video, audio, and PDFs) into a shared vector space, leading retrieval benchmarks (~67.7 MTEB retrieval). It supports Matryoshka dimensions up to 3,072 and integrates with the Gemini API and Vertex AI.

Strengths

  • Leads MTEB retrieval benchmarks (~67.7)
  • Shared multimodal vector space (text, image, and more)
  • Matryoshka dimensions up to 3,072
  • Gemini API and Vertex AI integration
  • Strong multilingual retrieval

Caveats

  • Proprietary - Google API only (no self-hosting)
  • Per-request input token limits
  • Usage-based pricing scales with volume
Vendor
Google
Context Window
2,048 tokens
License
Proprietary
Modalities
text
image

Capabilities

Vision
Audio
Video
Tool Use

Pricing

Usage-based via the Gemini API and Vertex AI (per 1M tokens); see Google pricing for current rates.

Reviews

Comments