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.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Todos os modelos intfloat E5 em todos os provedores

Entrada, $/1M $0.01

Saída, $/1M —

Contexto 512

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —