Search Foundation Models

Browse the full catalog. Select a model for full details.

Page-to-Markdown document parser in one pass at 570M active parameters

jina-reranker-v3.5

Domain-ready listwise reranker for multilingual and structured retrieval

jina-embeddings-v5-omni-nano

Compact multimodal embeddings for edge deployment

jina-embeddings-v5-omni-small

Multimodal embeddings for text, image, audio, video, and PDF

jina-embeddings-v5-text-nano

SOTA multilingual embeddings for edge deployment

jina-embeddings-v5-text-small

SOTA multilingual embeddings with task-specific adapters

Multilingual vision-language model for visual question answering

jina-reranker-v3

Listwise reranker for SOTA multilingual document retrieval

jina-code-embeddings-0.5b

Efficient code embeddings from code generation models

jina-code-embeddings-1.5b

Efficient code embeddings from code generation models

jina-embeddings-v4

Universal embedding model for multimodal and multilingual retrieval

jina-reranker-m0

Multilingual multimodal reranker model for ranking visual documents

Frontier small language model for converting raw HTML into markdown or JSON

Multilingual multimodal embeddings for texts and images

jina-embeddings-v3

Frontier multilingual embedding model with SOTA performance

jina-colbert-v2

The best multilingual ColBERT with top performance on embedding and reranking

reader-lm-0.5b

A small language model for converting raw HTML into markdown

reader-lm-1.5b

A small language model for converting raw HTML into markdown

jina-reranker-v2-base-multilingual

Cross-encoder reranker with multilingual, function calling and code search support.

Multimodal embedding models for images and English text

jina-reranker-v1-tiny-en

The fastest reranker model, best suited for ranking a large number of documents reliably

jina-reranker-v1-turbo-en

The best combination of fast inference speed and accurate relevance scores

jina-reranker-v1-base-en

Our first reranker model maximizing search and RAG relevance

jina-colbert-v1-en

Improved ColBERT with 8K-token length for embedding and reranking tasks

jina-embeddings-v2-base-es

Spanish-English bilingual embeddings with SOTA performance

🇺🇸 🇪🇸

jina-embeddings-v2-base-code

Optimized for code and docstring search

jina-embeddings-v2-base-de

German-English bilingual embeddings with SOTA performance

🇺🇸 🇩🇪

jina-embeddings-v2-base-zh

Chinese-English bilingual embeddings with SOTA performance

🇺🇸 🇨🇳

jina-embeddings-v2-base-en

On par with OpenAI's text-embedding-ada-002

jina-embedding-b-en-v1

The first version of the Jina Embedding model, the OG.

Our Search Foundation Models

We've been moving the needle in search models since day one. Take a look at our model evolution below—hover or click to discover each milestone.

Use it via

2026Q3

2026Q2

2026Q1

2025Q4

2025Q3

2025Q2

2025Q1

2024Q4

2024Q3

2024Q2

2024Q1

2023Q4

2023Q2

jina-embedding-b-en-v1

jina-embeddings-v2-base-en

jina-embeddings-v2-base-zh

🇺🇸 🇨🇳

jina-embeddings-v2-base-de

🇺🇸 🇩🇪

jina-embeddings-v2-base-code

jina-embeddings-v2-base-es

🇺🇸 🇪🇸

jina-colbert-v1-en

jina-reranker-v1-base-en

jina-reranker-v1-tiny-en

jina-reranker-v1-turbo-en

jina-reranker-v2-base-multilingual

reader-lm-0.5b

reader-lm-1.5b

jina-colbert-v2

jina-embeddings-v3

jina-reranker-m0

jina-embeddings-v4

jina-code-embeddings-0.5b

jina-code-embeddings-1.5b

jina-reranker-v3

jina-embeddings-v5-text-nano

jina-embeddings-v5-text-small

jina-embeddings-v5-omni-nano

jina-embeddings-v5-omni-small

jina-reranker-v3.5