Jina AI releases jina-embeddings-v4 (3.8B)

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

jina-embeddings-v4 (3.8B) released — unifies text and images, supports late interaction

Why it matters

Points toward a single model handling both multimodality and late interaction

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

Paperarxiv.orghttps://arxiv.org/abs/2506.18902

Added in Week 35, 2026 · See that week

On the map — ⑰ Embeddings line

  1. Previous stopEmbed v4
  2. This recordjina-embeddings-v4
  3. Next stopAmazon makes Nova Multimodal Embeddings generally available on Bedrock
See it on the map

Same week

The term context engineering becomes establishedOfficialGoogle officially releases Gemma 3nOfficialPartial summary judgment in Kadrey v. MetaOfficialNVIDIA introduces NVFP4Official

Nearby on the same axis

Milvus 2.6 releasedOfficialAlibaba Qwen releases the Qwen3 Embedding and Reranker series (0.6B–8B)OfficialGoogle makes gemini-embedding-001 generally available (GA)OfficialLanceDB announces a $30 million Series A and launches its Multimodal LakehouseOfficial