January 2026 Summaries

The Voyage 4 series introduces a pioneering set of text embedding models that feature industry-first shared embedding spaces, including models like voyage-4-large, voyage-4, voyage-4-lite, and voyage-4-nano. These models allow for interchangeable use of embeddings, providing flexibility for users to optimize for accuracy, latency, and cost by combining different models for query and document embedding. The flagship model, voyage-4-large, employs a mixture-of-experts architecture, achieving state-of-the-art retrieval accuracy with costs significantly lower than dense models. The series supports dimensional embeddings and employs Matryoshka learning and quantization to maintain high retrieval accuracy while reducing database costs. Evaluations using the Retrieval Embedding Benchmark demonstrate that voyage-4-large outperforms other models like Gemini Embedding 001 and Cohere Embed v4, with asymmetric retrieval enhancing quality when smaller models retrieve documents embedded by voyage-4-large. The models are accessible through the Voyage API and MongoDB Atlas, with voyage-4-nano available on Hugging Face for local development.

Voyage-multimodal-3.5 is a new advanced multimodal embedding model designed for improved retrieval of text, images, and videos, building on its predecessor, voyage-multimodal-3. It introduces explicit video frame support and maintains a unified transformer encoder architecture that processes both visual and textual inputs together, avoiding the modality gap seen in CLIP-based models. This model achieves higher retrieval accuracy compared to Cohere Embed v4 and Google Multimodal Embedding 001 across various datasets, including visual document and video retrieval tasks, while also performing competitively on standard text retrieval. It features Matryoshka embeddings for flexible dimensionality and offers multiple quantization options to minimize quality loss. The model is available with token-based pricing and offers free usage up to certain limits, providing tools for embedding videos effectively and improving retrieval pipelines.

Voyage AI announces advancements in AI-powered search and retrieval with the introduction of the Voyage 4 model series and voyage-multimodal-3.5, alongside expanded platform availability. The Voyage 4 series features a shared embedding space for seamless model transitions without re-indexing, includes the open-weights voyage-4-nano model, and offers improved retrieval accuracy with models like voyage-4-large leading on the RTEB leaderboard. The voyage-multimodal-3.5 model extends capabilities to video retrieval, supporting semantic searches over video content with natural language queries and introducing Matryoshka embeddings for flexible dimensionality. These models are now available on platforms such as MongoDB Atlas, GCP, AWS, and Azure, enhancing accessibility for developers to optimize retrieval accuracy and cost efficiency in their applications.