Voyage 4

Voyage 4 is a text embedding model developed by Voyage AI, a company focused on building embedding and reranking models for retrieval-augmented generation (RAG) and semantic search applications. It accepts text input and produces dense vector representations that capture semantic meaning, enabling downstream tasks such as document retrieval, clustering, and similarity comparison. The model supports a context window of 32,000 tokens, allowing it to encode long documents in a single pass without chunking.

Voyage 4 is well-suited for developers building search pipelines, recommendation systems, or any application that requires comparing or ranking text by meaning rather than keyword overlap. Voyage AI models are commonly used alongside large language models to retrieve relevant context before generation. The model is available through Voyage AI's API and is accessible on MindStudio without requiring separate API key management.