voyageai

Rerank 2.5 Lite is an instruction-following text reranker from Voyage AI by MongoDB, balancing ranking quality with lower latency. It is suited for high-throughput retrieval pipelines and accepts natural-language guidance for relevance scoring, including queries up to 8,000 tokens.

Rerank 2.5 is an instruction-following text reranker from Voyage AI by MongoDB, optimized for retrieval quality. It is suited for rescoring candidates in general-purpose and domain-specific search, and accepts natural-language guidance for relevance scoring, including queries up to 8,000 tokens.

Voyage Multimodal 3.5 is a multimodal embedding model from Voyage AI by MongoDB. It maps interleaved text and visual content into a shared embedding space for cross-modal retrieval over documents, screenshots, figures, tables, and other mixed-media collections, with Matryoshka embeddings at 2048, 1024, 512, and 256 dimensions.

Voyage 4 Lite is an efficiency-focused general-purpose embedding model from Voyage AI by MongoDB, optimized for low-latency and cost-sensitive retrieval. It supports Matryoshka embeddings at 2048, 1024, 512, and 256 dimensions, with multiple quantization options.

Voyage 4 is a general-purpose multilingual embedding model from Voyage AI by MongoDB. It is suited for retrieval, semantic search, and RAG applications, with Matryoshka embeddings at 2048, 1024, 512, and 256 dimensions and multiple quantization options.

Voyage 4 Large is a general-purpose multilingual embedding model from Voyage AI by MongoDB, optimized for retrieval quality. It supports Matryoshka embeddings at 2048, 1024, 512, and 256 dimensions, with multiple quantization options for balancing retrieval quality, storage, and serving efficiency.