Compare embedding models for search, RAG, clustering, and semantic similarity workloads.
Embedding models produce vectors and are billed differently from chat models. Use this page for RAG and search planning.
intfloat/multilingual-e5-large-instructsentence-transformers/all-minilm-l12-v2sentence-transformers/all-minilm-l6-v2sentence-transformers/all-mpnet-base-v2sentence-transformers/paraphrase-minilm-l6-v2