Cohere Embed V4

EMBEDDER

Cohere Embed V4 is a multimodal embedding model that converts text, images, and complex business documents into vectors for RAG and semantic search with 128K context and multilingual support for 100+ languages.

Provider

Cohere

Credits per 1k words

0.27

Max input tokens

4,096

Dimensions

256
512
1024
1536

MTEB retrieval score

Per-modality rates

The text rate above bills text chunks per ~1k English words. Non-text chunks (image, video, audio) bill at these separate rates with their own units.

ModalityCreditsUnits
image2.40credit_per_record

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
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.

text
image