Voyage Rerank 2.5 Lite
Voyage Rerank 2.5 Lite is Voyage AI's generalist reranker balanced for latency and quality. It supports a context window of 32K tokens, instruction-following, and multilingual reranking. It improves accuracy by 7.16% over Cohere Rerank v3.5 across 93 retrieval datasets. Your use subject to Voyage AI's Terms & Privacy Policies.
import { rerank } from 'ai';
const result = await rerank({ model: 'voyage/rerank-2.5-lite', query: 'What is the capital of France?', documents: [ 'Paris is the capital of France.', 'Berlin is the capital of Germany.', 'Madrid is the capital of Spain.', ],})About Voyage Rerank 2.5 Lite
Voyage Rerank 2.5 Lite is Voyage AI's generalist reranker released August 11, 2025, optimized for both latency and quality. It reorders candidate documents returned by a first-stage retriever, with a context window of 32K tokens, multilingual support, and the same instruction-following capability as rerank-2.5.
Across 93 retrieval datasets, Voyage Rerank 2.5 Lite improves accuracy by 7.16% over Cohere Rerank v3.5 when paired with four first-stage retrieval methods: BM25 lexical search, OpenAI text-embedding-3-large, voyage-3-large, and voyage-3.5. Averaged across those first-stage methods, Voyage Rerank 2.5 Lite outperforms Cohere Rerank v3.5, Qwen3-Reranker-8B, and rerank-2-lite by 1.93%, 1.01%, and 2.70% respectively on NDCG@10. It performs better than Qwen3-Reranker-8B, the strongest open-source reranker in the comparison, despite being over an order of magnitude smaller.
On the Massive Instructed Retrieval (MAIR) benchmark, Voyage Rerank 2.5 Lite outperforms Cohere Rerank v3.5 by 10.36%. Instruction-following lets you steer relevance scores using natural language without changing your retrieval index. The context window of 32K tokens matches rerank-2.5, so long query-document pairs fit a single rerank call.