Jina Embeddings v3

Jina AI · 2024 · Embeddings · Germany / EU

A to Z

A · App: No
B · Built By: Jina AI
C · CEO & Politics: Han Xiao — No public partisan activity documented
D · Date: 2024
E · Expertise: Intermediate+
F · Free Tier: Yes
G · Generates: Text only
H · Deployment: Cloud + Local (open weights)
I · Inputs: Text
J · Jurisdiction: Germany / EU
K · Key Staffers: Saba Sturua (Lead author), Han Xiao (Senior author)
L · Languages: English-primary
M · Model Type: Embeddings
N · Safety Issues: None reported
O · Open Source: Yes — open weights
P · Pricing: Free for non-commercial use (open weights, CC BY-NC 4.0); paid Jina API
Q · AIDb Rating: [UNKNOWN]
R · What Makes It Special: Jina AI's jina-embeddings-v3 (September 2024), a 570M-parameter multilingual embedding model built on Jina-XLM-RoBERTa with an 8,192-token context and five task-specific LoRA adapters (retrieval, clustering, classification and text matching); Matryoshka training lets its 1,024-dimension vectors be cut to as few as 32, it covers 89 languages (strongest in 30), and Jina reports it beats OpenAI's and Cohere's latest proprietary embeddings on English MTEB tasks. Weights CC BY-NC 4.0.
S · Stock / Status: Private
T · Training Cutoff: [UNKNOWN]
U · Users: [UNKNOWN]
V · Voice Chat: No
W · Weights: Downloadable
X · X Handle: @JinaAI_
Y · Year Founded: [UNKNOWN]
Z · Bottom Line: Open-weights Embeddings from Jina AI, released 2024.

Data completeness 85% · Last verified 2026-05-12 · Primary source ↗

“Jina Embeddings v3.” AIDb — The AI Database. Verified 2026-05-12. https://theaidatabase.com/m/jina-embeddings-v3.html