Voyage AI
Retrieval-optimized embedding and reranking models
Voyage AI is profiled here as a RAG Framework tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Voyage AI builds embedding and reranking models for retrieval systems and was founded in 2023 by Stanford professor Tengyu Ma. MongoDB acquired the company in February 2025 and now develops Voyage models as the retrieval layer for Atlas and for standalone API customers. General-purpose models sit alongside domain-tuned variants for code, finance, and law, which raises retrieval accuracy in specialized corpora. Pricing follows a per-token model, and every new account starts with a free allowance large enough to index a sizable corpus.
Key Capabilities:
General and domain-specific text embeddings for code, finance, and law
Reranking models that reorder candidates for retrieval precision
Multimodal embeddings spanning text and images
Context-aware chunk embeddings that preserve document-level meaning
Flexible output dimensions and quantization for storage savings
REST API with a free token allowance and MongoDB Atlas integration
Alternative tools
- Docling
Open-source document conversion built for RAG pipelines
- Unstructured
Turn raw documents into LLM-ready structured data
- Chroma
Developer-first embedding database that runs anywhere
- Qdrant
Rust-based vector search engine with rich filtering
- Weaviate
Open-source vector database with native hybrid search
- Pinecone
Managed vector database for production retrieval workloads