Voyage Rerank 3 and Rerank 3 Lite are now available on AI Gateway
- Source
- vercel.com
- Author
- Zachary Chen
- Date

Context
A Vercel changelog entry says Voyage AI's Rerank 3 and Rerank 3 Lite are available through Vercel's AI Gateway. A reranker takes the documents a search has already found and reorders them by relevance to the query before they go to a , so the model sees the best material first. Rerank 3 is described as focused on accuracy, and Rerank 3 Lite as optimized for latency and cost.
Both handle up to 32K per query-document pair and follow instructions placed in the query to guide ranking. The changelog states that the series improves retrieval quality across domains, with the largest gains on long documents and code, but gives no measurements. AI Gateway itself is one API for calling models, tracking usage and cost, and configuring routing, retries and failover. For background, Voyage's earlier rerank-2.5 models also advertised instruction following and a 32K .
- LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…






