Skip to content

Gemini Embedding 2

Embeddings
google/gemini-embedding-2

3072 dimensions · Apr 2026 · 1 upstreams

Gemini Embedding 2 is Google's first multimodal embedding model, mapping text, images, video, audio, and PDFs into one 3,072-dimension vector space for cross-modal semantic search, document retrieval, and recommendations over 100+ languages. Upstream accepts 8,192 input tokens and MRL-truncates to 128–3,072 dimensions. AnyRouter exposes the text path only — the OpenAI-compatible /embeddings body is a text `input`, so the extra upstream modalities are deliberately not declared here.

Bring your own keyAnyRouter has no platform route for Gemini Embedding 2. Requests use your key and bill your provider account. AnyRouter adds no fee.
max input
8K
dimensions
3072
input / 1M (list)
$0.20
routes
1

Upstreams

1
  1. 1OpenRouterYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Embed a sentence

Details

Owner
Google
Kind
Embeddings
Released
Apr 2026
Context
8K
Data policy
Provider retention
Endpoint
/api/v1/embeddings

Quick start

curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-embedding-2",
    "input": "The quick brown fox jumps over the lazy dog"
  }'