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.
Recent activity on bge-base-en-v1.5
Total usage per day on OpenRouter
Prompt
11.8M
Completion
0
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.