Embeddings & Vector SearchVoyage AI (MongoDB)Voyage AI

Voyage AI releases voyage-context-4

voyage-context-4 released — embeds documents longer than 32K as context-preserving chunks without chunking; price per 1 million tokens cut from $0.18 to $0.12

Why it matters

An attempt to absorb chunking, a RAG preprocessing step, into the embedding model itself

Source — Primary sources first; secondary reports are labelled “Press”

Officialblog.voyageai.comhttps://blog.voyageai.com/2026/06/29/voyage-context-4/

Added in Week 35, 2026 · See that week

Same week

OpenClaw publishes a batch of high-severity security advisoriesOfficialFigure 03 deployed in sequencing at Spartanburg Hall 52OfficialDiagnosing and Mitigating Context Rot in Long-horizon Search publishedPaper

Nearby on the same axis

Elastic publishes vector search benchmarksOfficialResearchers release NeoMMEPaperResearchers release COREPaperGoogle makes Gemini Embedding 2 generally available (GA)Official