Voyage AI Blog the company blog of Voyage AI: latest posts and feed
Voyage AI · Company blog · < 1 a month · last post Sep 30, 2026 · Active
Posts
10 on file since Aug 11, 2025Product and companySep 30 3w3 weeks agorerank-3 and rerank-3-lite: the next generation of Voyage rerankersTL;DR – We are excited to introduce the Rerank 3 series, the next generation of Voyage rerankers. rerank-3 and rerank-3-lite improve upon rerank-2.5 and rerank-2.5-lite across nearly all domains at the same price, with the largest gains on...AI and agentsAug 13 2mo2 months agovoyage-code-4: code retrieval built for coding agentsTL;DR – Introducing voyage-code-4, our next-generation code embedding model, purpose-built to improve performance and reduce costs for coding agents.AI and agentsJun 30 3mo3 months agovoyage-context-4: stop worrying about chunking with our best-performing modelTL;DR – voyage-context-4 is our next-generation contextualized chunk embedding model – it produces chunk embeddings that capture the full document context without any manual metadata or context augmentation, so you can stop thinking about...Reliability and performanceMar 3 7mo7 months agoBreaking the Dense Ceiling: How voyage-4-large Uses MoE to ScaleAuthor: Hong Liu Efficient scaling of embedding models has been a core focus of Voyage AI research: Rather than simply scaling up, we aim to improve the quality-cost trade-off, extending the Pareto frontier beyond what is possible with...AI and agentsJan 15 9mo9 months agovoyage-multimodal-3.5: a new multimodal retrieval frontier with video supportTL;DR – We’re excited to introduce voyage-multimodal-3.5, our next-generation multimodal embedding model built for retrieval over text, images, and videos.AI and agentsJan 15 9mo9 months agoThe Voyage 4 model family: shared embedding space with MoE architectureTL;DR – We’re excited to introduce the Voyage 4 series, a new generation of text embedding models featuring industry-first shared embedding spaces.Reliability and performanceJan 15 9mo9 months agoAnnouncing New Models and Expanded AvailabilityAt Voyage AI, we empower developers to build applications that rely on highly accurate AI-powered search and retrieval. We’re committed to building state-of-the-art models that maximize retrieval accuracy while offering unparalleled cost...Data engineeringDec 4, 2025 10mo10 months agoIntroducing the Batch API: Simpler and more efficient for large-scale workloadsTL;DR – We’re excited to introduce our Batch API, an asynchronous endpoint built to efficiently handle large volumes of requests.AI and agentsOct 22, 2025 1y1 year agoThe Case Against LLMs as RerankersAuthors: Apoorva Joshi, Zhenmei Shi, Akshay Goindani, Hong LiuResearch Leads: Zhenmei Shi, Akshay Goindani, Hong Liu Large language models are increasingly being used for a broad range of tasks, including reranking, but they may not be the...Product and companyAug 11, 2025 1y1 year agorerank-2.5 and rerank-2.5-lite: instruction-following rerankersTL;DR – We are excited to introduce the rerank-2.5 series, which significantly improves upon rerank-2’s performance while also introducing instruction-following capabilities for the first time. About this blog
Voyage AI's own blog on voyageai.com, found by the daily check.
Posts per week, last 26 weeks
< 1 a month over the last six months (or since the feed's oldest post)
History
Listed on Blogs Oct 7, 2026. No changes to its feed, status or cadence since.
Blogsby Ibis