Skip to content
AI Atlas
ModelActivefamily · Embed

embed-english-light-v3.0

Coheredocs.cohere.com/docs/models

A smaller, faster version of embed-english-v3.0. Almost as capable, but a lot faster. English only.

Updated 13 min ago · first seen 11 Sept 2026

model_01M294H97GSFTQFYY9PR2CTFT4

Context
512 tokens
T1 · 13 min ago

Specification

Family
Embed

Source:Cohere — docs & blogT1observed 13 min agohigh

Context window
512 tokens

Source:Cohere — docs & blogT1observed 13 min agohigh

Modalities
text, image

Source:Cohere — docs & blogT1observed 13 min agohigh

Input modalities
text, image

Source:Cohere — docs & blogT1observed 13 min agohigh

Output modalities
embedding

Source:Cohere — docs & blogT1observed 13 min agohigh

API model id
embed-english-light-v3.0

Source:Cohere — docs & blogT1observed 13 min agohigh

Official page

Source:Cohere — docs & blogT1observed 13 min agohigh

Embedding dimensions
384

Source:Cohere — docs & blogT1observed 13 min agohigh

Endpoints
Embed, Embed Jobs

Source:Cohere — docs & blogT1observed 13 min agohigh

Oci model id
cohere.embed-english-light-image-v3.0 (for images), cohere.embed-english-light-v3.0 (for text)

Source:Cohere — docs & blogT1observed 13 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

12

Source tiers

T112

Freshest observation

13 min ago

Conflicts

None