← All models

baai

BAAI: bge-m3

The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.

8,194 context
Modalities:text->embeddings
Released:11/17/2025

The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.

Weekly tokens

19.6B

Tokens generated this week (network-wide)

Usage by period

Today14.1K tokens
This week159.9K tokens
This month179.5K tokens
Trending159.9K tokens