Skip to content
Log In
Sign Up
Dashboard

Voyage 4

Voyage 4 is a mid-sized model in Voyage AI's Voyage 4 family. Voyage AI reports it approaches voyage-3-large retrieval quality with a context window of 32K tokens, Matryoshka dimensions (2048, 1024, 512, 256), and multiple quantization options. All Voyage 4 models share one embedding space, so you can mix models for asymmetric retrieval.

index.ts
import { embed } from 'ai';


const result = await embed({
  model: 'voyage/voyage-4',
  value: 'Sunny day at the beach',
})
OverviewAboutProvidersSimilarFAQ

About Voyage 4

Voyage 4 sits at the center of Voyage AI's Voyage 4 lineup, released N/A. It supports a context window of 32K tokens and occupies the middle ground between the MoE flagship voyage-4-large and the budget-oriented voyage-4-lite.

All Voyage 4 models share one embedding space. You can embed documents with voyage-4-large and run queries through Voyage 4 without maintaining separate vector indices. This asymmetric pattern lets you optimize cost per query while keeping document embeddings at flagship quality.

Voyage 4 supports Matryoshka dimensions (2048, 1024, 512, 256) and quantization-aware training across float32, int8, and binary formats. These compression options apply the same way across all Voyage 4 models, so you can tune storage costs independently of which model you choose for embedding.