Voyage-3-large
used in
1
stack
Higher-capacity Voyage embedding model for retrieval-quality-sensitive RAG.
Larger, higher-quality embedding model in the Voyage AI (MongoDB) family, chosen when retrieval precision matters more than embedding cost — for example enterprise knowledge agents over large, mixed-domain corpora.
Strengths
- Higher retrieval quality than voyage-3 on demanding corpora
- API-based; no embedding infrastructure to host
Tradeoffs
- More expensive per token than voyage-3
- API-only; document text leaves your environment to be embedded