Voyage AI
★ 4/5 · Other
Voyage AI provides high-accuracy embedding and reranking models via API, used by developers to improve retrieval quality in RAG and semantic search systems.
Pros
- Industry-leading embedding models (voyage-4, voyage-4-large, voyage-multimodal-3.5) with proven performance
- generous free tier includes 200M tokens monthly
- 33% batch processing discount available
- multimodal support for text, images, and video
Cons
- Pay-per-use pricing model can become expensive at scale ($0.06/M tokens for voyage-4, $0.12/M for voyage-4-large)
- specialized for embeddings/reranking, not general LLM chat
- file storage costs $0.05/GB/month
Cost
$0.02-0.12/M tokens depending on model; free 200M tokens/month; batch processing $0.04/M (voyage-4); file storage $0.05/GB/month
Verdict
Essential for teams building RAG systems, semantic search, or reranking pipelines that need production-grade embeddings with cost-effective per-token pricing.
Visit Voyage AI