Skip to main content
llm.info

Voyage-3-large

Voyage AI

Voyage AI's retrieval-optimized commercial embedding model, among the best for MTEB retrieval quality at production scale. It supports long context and Matryoshka (shortenable) dimensions, and is a common choice for high-accuracy RAG pipelines.

Strengths

  • Among the best MTEB retrieval quality at production scale
  • Retrieval-optimized for high-accuracy RAG
  • Long-context input support
  • Matryoshka (shortenable) dimensions
  • Backed by MongoDB integration

Caveats

  • Proprietary - API only (no self-hosting)
  • Usage-based pricing scales with volume
  • Best paired with Voyage rerankers for peak quality
Vendor
Voyage AI
Context Window
32,000 tokens
License
Proprietary
Modalities
text

Capabilities

Vision
Audio
Video
Tool Use

Pricing

Usage-based via the Voyage AI API (per 1M tokens); a generous free tier for evaluation. Now part of MongoDB.

Reviews

Comments