BGE-M3 (Embeddings)
bge-m3
🇨🇭 Switzerland
BGE-M3 embeddings: turns a text into a vector of 1,024 numbers to search by meaning rather than by words, in more than 100 languages, also mixed. Input tokens only.
At a glance
| Publisher | BAAI |
|---|---|
| Architecture | Embeddings, 568 million parameters, vectors of 1,024 numbers |
| Licence | MIT |
| Runs in | 🇨🇭 Switzerland |
| Status | Loaded: the first request answers without a start-up wait. Live state on Status. |
| Price | CHF 0.02 input · CHF 0.00 output, per million tokens, excluding VAT. All prices |
Use it
Turns text into vectors: see Embeddings and rerank.
Limits
- A request goes only to the zones your key allows; if the model has no machine there now, a
503names the zones. It is never sent elsewhere.