Cohere develops the Cohere Embed Multilingual Light V 3.0, an open-source embedding model capable of generating embeddings from text inputs. It is genuinely best at creating multilingual embeddings, having been trained on nearly 1B English training pairs and nearly 0.5B Non-English training pairs from 100+ languages.
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.