intfloat /

e5-large-v2

5 DZD in / 1M tokens

e5-large-v2 is an open-source text embedding model developed by Microsoft Research. Based on a 335-million parameter BERT-large encoder architecture, it maps text into a dense 1024-dimensional vector space using weakly-supervised contrastive pre-training followed by supervised fine-tuning. It utilizes asymmetric prefix conditioning ("query: " and "passage: ") to optimize dense retrieval and semantic search, delivering strong zero-shot retrieval accuracy across diverse domains with predictable inference latency.