Text Multilingual Embedding 002 converts text into vector representations optimized for cross-lingual semantic search, RAG, and clustering across numerous languages with 2048-token context.
Provider
Google
Credits per 1k words
0.07
Max input tokens
3,072
Dimensions
256
384
512
768
MTEB retrieval score
59.68
Supported languages
ar
bg
bn
cs
da
de
el
en
es
et
fi
fil
fr
hi
hr
hu
id
it
ja
ko
lt
lv
ms
nl
no
pl
pt
ro
ru
sk
sl
sv
sw
ta
te
th
tr
uk
vi
zh
Supported input media
Modalities this embedder accepts natively. Other media types are converted to text (OCR for images, transcription for audio/video) before embedding.
