# Cohere Embed v4

> Multilingual, multimodal enterprise embedding model supporting over 100 programming languages and primary business languages with advanced quantization for cost optimization.

- **URL:** https://cohere.com/embeddings
- **Category:** Machine Learning Models
- **Tags:** Embeddings, multilingual, Multimodal
- **Updated:** 2026-03-10 11:58
- **Canonical page:** https://vectordb.ever.works/items/cohere-embed-v4

## Details

## Overview

Cohere embed-v4.0 is a multilingual, multimodal embedding model designed for enterprises to incorporate advanced search and retrieval applications, converting text and images into semantic search vectors.

## Features

- Supports over 100 programming languages
- Primary business language support: Arabic, Japanese, Korean, French, and more
- Multimodal capabilities with Base64 image input
- Byte and binary quantization support
- Matryoshka Representation Learning (MRL) for flexible dimensions
- Significant storage cost savings

## Technical Specifications

- Text and image input support
- Advanced quantization techniques
- Flexible embedding dimensions
- Enterprise-grade security and compliance

## Use Cases

- Multilingual semantic search
- Code search across programming languages
- Multimodal document retrieval
- Enterprise knowledge bases
- Cross-language information retrieval

## Pricing

Enterprise pricing with volume discounts available

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/cohere-embed-v4._