Titan Text Embeddings V2 converts text into numerical vectors optimized for RAG, search, and classification with flexible embedding sizes (256, 512, 1024), multilingual support for 100+ languages.
Provider
Amazon
Credits per 1k words
0.05
Max input tokens
8,000
Dimensions
256
512
1024
MTEB retrieval score
—
Supported languages
ar
de
en
es
fr
hi
it
ja
ko
nl
pl
pt
ru
sv
th
tr
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.
