Skip to content
Dashboard

Gemini Embedding 2

Gemini Embedding 2 is Google's first natively multimodal embedding model, mapping text, images, video, audio, and documents into a single unified embedding space with support for interleaved multi-modal inputs and over 100 languages. Your use is subject to Google's Terms & Privacy Policies.

import { embed } from 'ai';
const result = await embed({
model: 'google/gemini-embedding-2',
value: 'Sunny day at the beach',
})
Read docs

Copy link to headingMore models by Google

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
0.4s
338tps
$0.30/M
$2.50/M
Read:$0.03/M
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
07/21/2026
1M
2.9s
184tps
$1.50/M
$7.50/M
Read:$0.15/M
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
07/21/2026
1M
1.6s
183tps
$1.50/M
$9/M
Read:$0.15/M
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
05/19/2026
1M
0.7s
237tps
$0.25/M
$1.50/M
Read:$0.03/M
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
05/07/2026
1M
4.8s
109tps
$2/M+1 more
$12/M+1 more
Read:
$0.2/M+1 more
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
02/19/2026
1M
0.6s
199tps
$0.50/M+1 more
$3/M+1 more
Read:
$0.05/M+1 more
Write:
$14/K+1 more
+ input costs
+3
google logo
vertex logo
12/17/2025