Skip to content

Models

BGE-M3 (Embeddings)

bge-m3 🇨🇭 Switzerland

Embedding BGE-M3: trasforma un testo in un vettore di 1.024 numeri per cercare per significato invece che per parole, in più di 100 lingue, anche mescolate. Solo token in ingresso.

At a glance

PublisherBAAI
ArchitectureEmbeddings, 568 million parameters, vectors of 1,024 numbers
LicenceMIT
Runs in🇨🇭 Switzerland
StatusLoaded: the first request answers without a start-up wait. Live state on Status.
PriceCHF 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 503 names the zones. It is never sent elsewhere.

Search the docs

Type to search…