Voyage Rerank 3 and Rerank 3 Lite are now available on AI Gateway

Voyage AI by MongoDB's Rerank 3 and Rerank 3 Lite are now available on Vercel's AI Gateway, callable as `voyage/rerank-3` and `voyage/rerank-3-lite`. Both reranking models reorder search results by relevance before documents are passed to a language model, handle up to 32K tokens per query-document pair, and follow instructions in the query to guide ranking, with Rerank 3 focused on accuracy and Rerank 3 Lite optimized for latency and cost. The series improves retrieval quality across domains, with the largest gains reported on long documents and code.

Rerank 3 https://vercel.com/ai-gateway/models/rerank-3 and Rerank 3 Lite https://vercel.com/ai-gateway/models/rerank-3-lite from Voyage AI by MongoDB are now available on AI Gateway. The models reorder search results by relevance before passing documents to a language model. The series improves retrieval quality across domains, with the largest gains on long documents and code. Rerank 3 focuses on accuracy, while Rerank 3 Lite is optimized for latency and cost. Both handle up to 32K tokens per query-document pair and follow instructions in the query to guide ranking. To use Rerank 3, set the model to voyage/rerank-3 : For Rerank 3 Lite, change the model to voyage/rerank-3-lite . Try Voyage Rerank 3 in the AI Gateway model playground https://vercel.com/ai-gateway/models/rerank-3 , or explore the model catalog https://vercel.com/ai-gateway/models . AI Gateway provides one API for calling models, tracking usage and cost, and configuring routing, retries, and failover. You can use an AI Gateway API key https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys or bring your own provider key https://vercel.com/docs/ai-gateway/authentication-and-byok/byok .