Voyage AI

Model

Embedding and reranking models for search and RAG

Price: 200M free tokens, then pay per use
Access: API key

About

Voyage AI offers embedding and reranking models for semantic search and retrieval-augmented generation, including code, legal and finance variants. It is for teams building search or RAG. Each account gets 200M free tokens on the current models.

What you can do with it

Embed documents and queries for semantic search
Rerank retrieved documents by relevance to a query
Embed code, legal or finance text with domain-specific models

Get started

Create a secret key in the Voyage dashboard
Set VOYAGE_API_KEY in your environment

Example

curl https://api.voyageai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VOYAGE_API_KEY" \
  -d '{
    "input": "Sample text",
    "model": "voyage-4-large",
    "input_type": "document"
  }'

Details

Hosting: Hosted service, Self-hosted
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript
MCP server: None