News
Models
Products
keyboard_arrow_down
Reader
Convert any URL to Markdown for better grounding LLMs.
Embeddings
World-class multimodal multilingual embeddings.
Reranker
World-class reranker for maximizing search relevancy.
DeepSearch
Search, read and reason until best answer found.
More
keyboard_arrow_down
Classifier
Zero-shot and few-shot classification for image and text.
Segmenter
Cut long text into chunks and do tokenization.

MCP Server
Add mcp.jina.ai as your MCP server to access our API in LLMs
open_in_new
API Docs
Auto codegen for your copilot IDE or LLM
open_in_new


Company
keyboard_arrow_down
About us
Contact sales
Intern program
Terms & Conditions
Download logo
open_in_new



Log in
login

News

Accelerate search AI, one token at a time.

rss_feedRSS
folder_special
Featured
Light blue background with stylized text in the center, composed of small dots or squares, evoking a modern and minimalistic
Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval
New 0.6B-parameter listwise reranker that considers the query and all candidate documents in a single context window.
Jina AI
October 03, 2025 • 7 minutes read
Jina Code Embeddings: SOTA Code Retrieval at 0.5B and 1.5B
Code generation LLMs → code embeddings: 0.5B/1.5B models achieve SOTA performance across 25 code retrieval benchmarks.
Jina AI
September 04, 2025 • 6 minutes read
Green "Code Embeddings" text displayed in a LED dot style on a black background, evoking a futuristic and technological atmos
Jina Embeddings v4: Universal Embeddings for Multimodal Multilingual Retrieval
Jina Embeddings v4 is a 3.8 billion parameter universal embedding model for multimodal and multilingual retrieval that supports both single-vector and multi-vector embedding outputs.
Jina AI
June 25, 2025 • 12 minutes read
Word "Embeddings" followed by a numeric or symbol representation, displayed in multiple colors on a technology-themed, colorf
school
Academic Publications
arXiv
October 01, 2025
jina-reranker-v3: Last but Not Late Interaction for Document Reranking
NeurIPS 2025
August 31, 2025
Efficient Code Embeddings from Code Generation Models
EMNLP 2025
June 24, 2025
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
ICLR 2025
March 04, 2025
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
ACL 2025
December 17, 2024
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
ICLR 2025
December 12, 2024
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
ECIR 2025
September 18, 2024
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
SIGIR 2025
September 07, 2024
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
EMNLP 2024
August 30, 2024
Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
WWW 2025
June 21, 2024
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
ICML 2024
May 30, 2024
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
arXiv
February 26, 2024
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
arXiv
October 30, 2023
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
EMNLP 2023
July 20, 2023
Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
14 publications in total.
folder_special
Featured
school
Academic
All
Press release
Tech blog
Event
Opinion
chevron_leftchevron_right

October 03, 2025 • 7 minutes read
Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval
New 0.6B-parameter listwise reranker that considers the query and all candidate documents in a single context window.
Jina AI
Light blue background with stylized text in the center, composed of small dots or squares, evoking a modern and minimalistic
October 01, 2025
jina-reranker-v3: Last but Not Late Interaction for Document Reranking
jina-reranker-v3 is a 0.6B parameter multilingual document reranker that introduces a novel last but not late interaction. Unlike late interaction models such as ColBERT that perform separate encoding followed by multi-vector matching, our approach conducts causal self-attention between query and documents within the same context window, enabling rich cross-document interactions before extracting contextual embeddings from the last token of each document. This compact architecture achieves state-of-the-art BEIR performance with 61.94 nDCG@10 while being significant smaller than generative listwise rerankers.
jina-reranker-v3: Last but Not Late Interaction for Document Reranking
arXiv
September 30, 2025 • 8 minutes read
Embeddings Are AI’s Red-Headed Stepchild
Embedding models aren't the most glamorous aspect of the AI industry, but image generators and chatbots couldn't exist without them.
Scott Martens
Humorous office cartoon depicting a team gathered around robots; signs labeled "embeddings", "tools", "reasoning", and "lol"
September 09, 2025 • 11 minutes read
Multimodal Embeddings in Llama.cpp and GGUF
We brought multimodal embeddings to llama.cpp and GGUF, and uncovered a few surprising issues along the way.
Andrei Ungureanu
Alex C-G
Cartoon llama in the center of a white background, emitting laser-like beams from its eyes. The illustration creates a playfu
September 04, 2025 • 6 minutes read
Jina Code Embeddings: SOTA Code Retrieval at 0.5B and 1.5B
Code generation LLMs → code embeddings: 0.5B/1.5B models achieve SOTA performance across 25 code retrieval benchmarks.
Jina AI
Green "Code Embeddings" text displayed in a LED dot style on a black background, evoking a futuristic and technological atmos
August 31, 2025
Efficient Code Embeddings from Code Generation Models
jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction.
Efficient Code Embeddings from Code Generation Models
NeurIPS 2025
August 29, 2025 • 9 minutes read
Agentic Workflow with Jina Remote MCP Server
Jina MCP streamlines agent development by connecting our APIs to any LLM, reducing custom code and improving reliability of the workflow.
Alex C-G
Digital map of Europe formed with binary code in shades of blue, grey, and white, with red, yellow, and blue highlights in so
August 13, 2025 • 15 minutes read
Optimizing GGUFs for Decoder-Only Embedding Models
4000 tokens/sec for a 3B-parameter embedding model on L4 GPU is probably as fast as you'll get with llama.cpp. Or is it?
Han Xiao
Text "DGUF for Embedding Models" written in yellow on a dark background, conveying a sleek, minimalistic, digital design.
August 11, 2025 • 8 minutes read
What We Learned at SIGIR 2025
Sharing what we saw and learned at SIGIR 2025, feat. CLIP-AdaM, RE-AdaptIR and evaluations for LLM-based retrieval systems.
Michael Günther
Bo Wang
Scott Martens
Conference scene in a large auditorium with a "SIGIR 2025" banner on the projected screen, a speaker on stage, and attendees
July 31, 2025 • 12 minutes read
How Image Resolution Impacts Visual Document Retrieval
Image resolution is crucial for embedding visually rich documents. Too small and models miss key details; too large and they can't connect the parts.
Maximilian Werk
Michael Günther
Scott Martens
Abstract composition with a dark background featuring a flower-like design, radiant eye-like feature, rainbow-colored curved
Offices
location_on
Sunnyvale, CA
710 Lakeway Dr, Ste 200, Sunnyvale, CA 94085, USA
location_on
Berlin, Germany (HQ)
Prinzessinnenstraße 19-20, 10969 Berlin, Germany
Search Foundation
Reader
Embeddings
Reranker
DeepSearch
Classifier
Segmenter
Get Jina API key
Rate Limit
API Status
Company
About us
Contact sales
News
Intern program
Download logo
open_in_new
Terms
Security
Terms & Conditions
Privacy
Manage Cookies
email
Jina AI © 2020-2025.