---
id: "baai/bge-m3"
also: ["baai/bge-m3-20251117", "BAAI/bge-m3"]
cheapest_list_usd_per_m: "0.01 in, 0.0 out, at deepinfra/fp32 on openrouter"
cheapest_effective_usd_per_m: "0.0094 in, 0.0 out, at deepinfra/fp32 on openrouter"
context: 8194
max_output: 7374
input: ["text"]
output: ["embeddings"]
released: "2025-11-18"
api: ["/api/v1/embeddings"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 0
---
# 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.