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.

• Context window: 8,192 tokens
• Input: text
• Output: embeddings
• Pricing: $0.01/M input tokens

View on OpenRouter. Model data sourced from OpenRouter.