E5 Multi-Lingual Large Embeddings 0.6B · deepinfra

The Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:” or “passage:”, as the model was explicitly trained with this format.

BasismodellAlle Modelle dieser BasisAlle Modelle des Anbieterszum Anbieter

Alle intfloat E5-Modelle bei allen Anbietern

Eingabe, $/1M $0.01

Ausgabe, $/1M —

Kontext 512

Akzeptiert —

Zuletzt geprüft 04.11.2026 12:00:14 UTC

Quelle —