---
id: "google/gemini-embedding-2"
also: ["google/gemini-embedding-2", "vercel/google/gemini-embedding-2"]
cheapest_list_usd_per_m: "0.2 in, 0.0 out, at google-ai-studio on openrouter"
cheapest_effective_usd_per_m: "0.2 in, 0.0 out, at google on vercel"
context: 8192
max_output: 7372
input: ["text", "image", "file", "audio", "video"]
output: ["embeddings"]
released: "2026-05-20"
api: ["/api/v1/embeddings"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 5
gateways: "openrouter (4), vercel (1)"
no_training: 4
trains: 0
retains_prompts: 1
---
# Google: Gemini Embedding 2

Google’s first fully multimodal Embedding model that is capable of mapping text, image, video, audio, and PDFs and their interleaved combinations thereof into a single, unified vector space. Built on the Gemini architecture, it supports 100+ languages.