Rerank 3 is a reranking model from Voyage AI that scores and reorders candidate documents by relevance to a query. It has a 32K-token context length and supports instruction-following.
Rerank 3 Lite is a reranking model from Voyage AI that scores and reorders candidate documents by relevance to a query, optimized for latency-sensitive applications. It has a 32K-token context length and supports instruction-following.
Voyage 4 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 4 Large is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 4 Lite is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Multimodal 3.5 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Rerank 2.5 is Voyage AI's current quality-optimized generalist reranker with instruction-following and multilingual support.
Rerank 2.5 Lite is Voyage AI's current latency-optimized generalist reranker with instruction-following and multilingual support.
Voyage Code 4 is Voyage AI's current proprietary embedding model optimized for code retrieval and coding-agent workflows. It supports 256, 512, 1024 (default), and 2048-dimensional outputs.
Voyage Context 4 is Voyage AI's current contextualized chunk embedding model for general-purpose and multilingual retrieval. It supports 256, 512, 1024 (default), and 2048-dimensional outputs, with a 32,000-token per-chunk window and up to 120,000 total tokens when auto-chunking.
Rerank 1 is a reranking model from Voyage for improving retrieval quality by rescoring candidate results against a query. Use it to rescore retrieved passages, products, or documents before final ranking or generation.
Rerank 2 is a reranking model from Voyage for improving retrieval quality by rescoring candidate results against a query. Use it to rescore retrieved passages, products, or documents before final ranking or generation.
Rerank 2 Lite is a reranking model from Voyage for improving retrieval quality by rescoring candidate results against a query. Use it to rescore retrieved passages, products, or documents before final ranking or generation.
Rerank Lite 1 is a reranking model from Voyage for improving retrieval quality by rescoring candidate results against a query. Use it to rescore retrieved passages, products, or documents before final ranking or generation.
Voyage 01 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 02 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 3 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 3 Large is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 3 Lite is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 3.5 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage 3.5 Lite is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Code 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Code 3 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Context 3 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Finance 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Large 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Large 2 Instruct is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Law 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Lite 01 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Lite 01 Instruct is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Lite 02 Instruct is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Voyage Multilingual 2 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at multilingual retrieval and semantic similarity tasks.
Voyage Multimodal 3 is an embedding model from Voyage for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.