Voyage Rerank 2.5 Lite
Voyage Rerank 2.5 Lite is a reranking model from Voyage AI designed to reorder retrieved documents within a 32,000 token context window.
Voyage AILightweight reranking with 32K token context
Voyage Rerank 2.5 Lite is a reranking model developed by Voyage AI, a company specializing in embedding and retrieval models. It is designed to take a query and a set of candidate documents returned by an initial retrieval step and reorder them by relevance, improving the quality of results passed to downstream tasks. The model supports a context window of 32,000 tokens, allowing it to process longer documents during the reranking stage.
This model is the lighter variant in Voyage AI's rerank-2.5 family, making it suited for use cases where lower latency or reduced computational cost is a priority without fully abandoning reranking quality. It fits into retrieval-augmented generation (RAG) pipelines as a post-retrieval step between a vector search and a language model. Developers working with large document corpora who need a cost-efficient reranking layer will find it a practical option.
What Voyage Rerank 2.5 Lite supports
Document Reranking
Reorders a set of retrieved candidate documents by relevance to a query, improving precision before passing results to a downstream model or application.
Long Context Support
Accepts inputs up to 32,000 tokens, enabling reranking of longer documents without requiring chunking at the reranking stage.
RAG Pipeline Integration
Functions as a post-retrieval reranking layer in retrieval-augmented generation pipelines, sitting between vector search and the language model.
Relevance Scoring
Produces relevance scores for each query-document pair, allowing developers to filter or rank results programmatically based on a numeric signal.
Ready to build with Voyage Rerank 2.5 Lite?
Get Started FreeCommon questions about Voyage Rerank 2.5 Lite
What is the context window for Voyage Rerank 2.5 Lite?
Voyage Rerank 2.5 Lite supports a context window of 32,000 tokens, which applies to the combined length of the query and each candidate document being reranked.
How does Voyage Rerank 2.5 Lite differ from the full rerank-2.5 model?
Voyage Rerank 2.5 Lite is the lighter variant in the rerank-2.5 family. It is designed to offer lower latency and reduced computational cost compared to the full rerank-2.5 model, making it suitable for cost-sensitive or latency-sensitive applications.
What is this model used for?
It is used to reorder documents retrieved by a first-stage retrieval system — such as a vector database — so that the most relevant results are ranked highest before being passed to a language model or returned to a user.
Is pricing available for Voyage Rerank 2.5 Lite?
Pricing information is not included in the available metadata. You can check Voyage AI's official documentation or pricing page for current rates.
Does Voyage Rerank 2.5 Lite support image or multimodal inputs?
Based on available metadata, Voyage Rerank 2.5 Lite does not indicate support for image or video inputs. It is a text-based reranking model.
Explore similar models
Voyage AIVoyage Rerank 2.5
Voyage Rerank 2.5 is a reranking model from Voyage AI designed to improve document retrieval relevance with a 32,000-token context window.
Voyage AIVoyage 4
Voyage 4 is an embedding model from Voyage AI designed for semantic search and retrieval with a 32,000-token context window.
Voyage AIVoyage 4 Large
Voyage 4 Large is an embedding model from Voyage AI with a 32,000 token context window for semantic search and retrieval.
NvidiaLlama Nemotron Rerank VL 1B v2
Llama Nemotron Rerank VL 1B v2 is a vision-language reranking model from Nvidia with a 10,240-token context window.
CohereCohere Rerank 4 Fast
Cohere Rerank 4 Fast is a reranking model from Cohere designed to score and reorder search results with a 4096 token context window.
QwenQwen3 Reranker 0.6B
Qwen3 Reranker 0.6B is a lightweight reranking model from Qwen designed to reorder retrieved documents with a 32,768-token context window.
Start building with Voyage Rerank 2.5 Lite
No API keys required. Create AI-powered workflows with Voyage Rerank 2.5 Lite in minutes — free.