Cohere Embed v4

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