Cohere's Embed English Light V 3.0 is an open-source embedding model capable of generating embeddings from text inputs, with a context window of 1,024 tokens. It is particularly suited for tasks that require high-quality English language embeddings, having been trained on nearly 1 billion English training pairs.
Input
Output
Context
1K
Max Output
1K
Parameters
-
Input Modalities
Output Modalities
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Automatically route workloads to the right model for every task, every time.