---
id: "google/gemini-embedding-2-preview"
also: ["google/gemini-embedding-2-preview"]
cheapest_list_usd_per_m: "0.2 in, 0.0 out, at google-ai-studio on openrouter"
cheapest_effective_usd_per_m: "0.2006 in, 0.0 out, at google-ai-studio on openrouter"
context: 8192
max_output: 7372
input: ["text", "image", "file", "audio", "video"]
output: ["embeddings"]
released: "2026-04-17"
api: ["/api/v1/embeddings"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 1
---
# Google: Gemini Embedding 2 Preview

Gemini Embedding 2 Preview 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...