Last updated: 16/04/2025

CohereOfficial Docs

Embed English v3.0

embed-english-v3.0

active

Embed English v3.0

Embed is the leading multimodal embedding model, acting as an intelligent retrieval engine for semantic search and retrieval-augmented generation (RAG) systems.

Supports a 512 token context window. Handles Text, Image inputs and outputs.

Additional Information

Notes

You can create up to 96 text embeddings per API call. You can create 1 image embedding per API call.

Capabilities

Image

Input Pricing

$0.0001 /image

Embeddings

Embeddings Pricing

$0.10/1k tokens

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop