Embedding Models/Jina Embeddings v5 Text Small

Jina Embeddings v5 Text Small by Jina AI — 1024D

677M-parameter multilingual text embedding model scoring 71.7 on MTEB English v2 and 67.7 on MMTEB. Highest performance among multilingual embedding models under 1B parameters. Built on Qwen3-0.6B-Base with distillation from Qwen3-Embedding-4B. Supports 119+ languages, 32K tokens, 1024-dim with Matryoshka truncation. Robust under truncation and binary quantization.

At a glance

Modalities

Dimensions

1K

Max tokens

33K

Parameters

677M

Price / 1M tokens

Type

Dense

Matryoshka dimensions

32641282565127681024

Output types

DenseLate Interaction

Language support

multilingual

Benchmarks

MTEB ENGLISH V2 71.70
MMTEB 67.70

Details

Release date 2026-02-18
License CC BY-NC 4.0
Model ID jina-embeddings-v5-text-small
Provider Jina AI

Tags

textretrievaltext-matchingclusteringclassificationmteb

What You Need to Know About Jina Embeddings v5 Text Small

Complete Specifications for Jina Embeddings v5 Text Small by Jina AI

Get detailed specifications for Jina Embeddings v5 Text Small, including output dimensionality of 1024 dimensions, maximum input token length, supported input modalities, and pricing per million tokens. This embedding model is designed for semantic search, text classification, clustering, and retrieval-augmented generation applications where understanding the relationship between texts is essential.

Pricing and Cost Efficiency for Jina Embeddings v5 Text Small

Review the pricing structure for Jina Embeddings v5 Text Small and compare it against other embedding models from Jina AI and competitors. Understanding embedding model costs is essential when scaling vector search and RAG applications to millions of documents. We provide transparent pricing to help you budget effectively.

Use Cases and Applications for Jina Embeddings v5 Text Small

Explore the ideal use cases for Jina Embeddings v5 Text Small. Whether you are building a semantic search engine, recommendation system, document classification pipeline, or multilingual retrieval system, understanding this model's capabilities and dimensionality will help you choose the right embedding strategy for your project.