Baai
Models published by Baai, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
BAAI's BGE-Large is an open multilingual text embedding model returning a 1,024-dimension dense vector over a 512-token window, across 100+ languages. MIT-licensed. AnyRouter exposes the text path via /embeddings on the user's own paired device running Ollama.
BGE Base EN v1.5 is an open-weight English text embedding model that maps sentences and paragraphs to 768-dimensional vectors for retrieval and semantic search. It takes up to 512 tokens of input.
BGE Multilingual Gemma 2 is BAAI's open-weight compact multilingual text embedding model built on Gemma 2. It is trained across 100+ languages, takes an 8,192-token input window, and returns a 3,584-dimension dense vector.
BGE-M3 is BAAI's open-weight multilingual text embedding model for dense, sparse, and multi-vector retrieval. It covers 100+ languages with an 8,192-token input window and returns a 1,024-dimension dense vector.