Google · Embedding model

Gemini Embedding 2

google/gemini-embedding-2

Embedding

Released May 20, 2026

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...

Specifications

Input: text, image, file, audio, video
Output: vector per input (float array; base64 on request)
Batch: up to 512 inputs per call
Billing: per input token

Use it

POST /api/v1/embeddings · MCP embed · full reference

curl https://omnirail.org/api/v1/embeddings \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-embedding-2","input":["brass lever espresso machine","coffee grinder"]}'