OpenAI text-embedding-3
AI Model
Embedding
Current
The vectors under most RAG systems.
You're looking at an AI model record: who built it, what it can do, and the hardware and data behind it.
Embedding models turn text into vectors for search and retrieval — the invisible workhorses of RAG. OpenAI's text-embedding-3 family (January 2024) with Matryoshka-style shortening is the most widely deployed commercial line; open alternatives from the MTEB leaderboard trail closely.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Developed by
Sources
Record reviewed as of 2026-01-15 — see Methodology.