Voyage 4 Lite
Available nowA lighter retrieval model for search experiences where speed and cost matter.
What it does
Voyage 4 Lite is the Voyage 4 family’s option optimized for latency and cost. It turns text into searchable vectors for general-purpose and multilingual retrieval, with the aim of serving a lighter search workload.
It retains a 32,000-token source context and the family’s selectable output dimensions. Voyage documents compatibility between the general Voyage 4 models, making Lite an option to evaluate when indexing large collections or responding to many everyday queries.
Language coverage
Voyage describes the current general retrieval family as multilingual. The model guide does not publish a complete named-language guarantee; treat it as a broad candidate and evaluate your collection.
Official language coverage ↗Where it helps
Interactive discovery
Retrieve relevant information in a search box people use repeatedly.
Large collections
Evaluate a lower-priced Voyage option when many texts need indexing.
Everyday support
Find common answers without always choosing the largest retrieval model.
When to choose it
Try it when a responsive experience and predictable indexing cost are key. Use a representative evaluation set to check whether it finds the important results before moving to Voyage 4 or Large.
The provider’s efficiency positioning is not a measured latency guarantee for this service; network and index performance also affect the user experience.
Official sources
Paraphrased from the provider’s documentation and original model information. Selection advice is our editorial guidance.
Voyage AI · Model guide ↗Reviewed October 3, 2026