Indlæser kataloget…
BAAI's open-weight multilingual text-embedding model for retrieval, similarity search, classification and clustering.
| Inferensleverandør | Suverænitet | Kører i | Pris | Status | Fastgør |
|---|---|---|---|---|---|
| L3 | 0,10 € per 1 mio. ind-tokens | Online | |||
| L0 | 0,07 € per 1 mio. ind-tokens | Online |
11 anvendelsesområder klassificeret af redaktøren. Noten forklarer hvorfor.
Purpose-built multilingual embedding model with an 8192-token context window, suited to dense retrieval over long passages across languages.
Embedding outputs can feed lightweight classifiers or similarity-based labelling, but it has no native generative classification head, so it is a competent rather than primary choice.
No function-calling support is documented, and the model produces vectors rather than structured tool invocations.
No text-generation capability is documented, so it cannot draft long-form content.
Query rewriting requires generative output, which this embedding model does not provide.
As a bi-encoder embedding model rather than a cross-encoder reranker, it is materially less precise for second-stage reranking than dedicated reranking models.
Text-only embedding model with no vision input capability.
Useful only as the retrieval stage of a document Q&A pipeline; it has no generative capability to produce answers on its own.
Tal fra eksterne kilder, ikke vores egne vurderinger. Percentiler er målt mod embedding-modellerne på Stav.
curl https://api.stav.ai/v1/embeddings \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "baai/bge-multilingual-gemma2",
"input": ["Hello, world"]
}'→ X-Stav-Request-Id · X-Stav-Model · X-Stav-Provider → X-Stav-Sovereignty-Level — det niveau, forespørgslen blev betjent på