Skip to content

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.

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

More models by Google

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
1M
2.1s
272tps
$1.50/M$9.00/M
Read:$0.15/M
Write:
$14.00/K
+ input costs
+4
google logo
vertex logo
05/19/2026
1M
0.8s
244tps
$0.25/M$1.50/M
Read:$0.03/M
Write:
$14.00/K
+ input costs
+4
google logo
vertex logo
03/03/2026
1M
4.6s
319tps
$2.00/M
$12.00/M
Read:
$0.2/M
Write:
$14.00/K
+ input costs
+4
google logo
vertex logo
02/19/2026
1M
0.8s
171tps
$0.50/M
$3.00/M
Read:
$0.05/M
Write:
$14.00/K
+ input costs
+4
google logo
vertex logo
12/17/2025
1M
0.3s
263tps
$0.10/M$0.40/M
Read:$0.01/M
Write:
$35.00/K
+ input costs
+4
google logo
vertex logo
06/17/2025
1M
1.6s
130tps
$1.25/M
$10.00/M
Read:
$0.13/M
Write:
$35.00/K
+ input costs
+4
google logo
vertex logo
03/20/2025