BAAI
BAAI: bge-base-en-v1.5
baai/bge-base-en-v1.5
The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features improved similarity-score distribution and stronger retrieval performance out of the box.
Input
$0.005
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
512
tokens
Embeddings output · Token reference fields do not establish an output-unit price.
Limits
Context
512
tokens
Max output
460
90% of the context window
Parameters
109,482,752
Model facts
Author
BAAI
Tokenizer
Other
Modality
Text -> Embeddings
License
MIT
Created
Nov 18, 2025
Hugging Face
BAAI/bge-base-en-v1.5
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Embeddings