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