Text Embedding 3 Small is OpenAI's cost-effective embedding model converting text into 1536-dimensional vectors for semantic search, RAG, and clustering with improved multilingual performance.
Provider
OpenAI
Credits per 1k words
0.05
Max input tokens
8,192
Dimensions
256
384
512
768
1024
1536
MTEB retrieval score
50.64
Supported languages
ar
cs
da
de
el
en
es
fi
fr
hi
hu
id
it
ja
ko
nl
no
pl
pt
ro
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.
