embed-v4.0 logo

MODELS

embed-v4.0

by Cohere

modelsource:cohere.comembedding-modelmultimodaltext-embeddingsimage-embeddingsragenterprise-searchcohere

Overview

Cohere’s multimodal embedding model for text, images, and mixed documents, with 128K context and configurable embedding dimensions for enterprise search/RAG.

Details

embed-v4.0 is Cohere’s multimodal embedding model for creating embeddings from text, images, and mixed documents. The supplied Cohere launch page and model documentation describe it as supporting a 128K context window and configurable embedding dimensions, positioning it for enterprise search and retrieval-augmented generation workflows where content may include both language and visual document inputs.

When to Use

Use embed-v4.0 when you need embeddings for text, images, or mixed documents from a Cohere model. Consider it for enterprise search or RAG workflows that benefit from long-context embedding support and configurable embedding dimensions.

Getting Started

  1. Read Cohere’s embed-v4.0 launch page for the product overview.
  2. Review Cohere’s model documentation page for model-specific usage details.
  3. Run a small evaluation on representative text, image, or mixed-document data before production use.

Key Features

  • Multimodal embedding support for text, images, and mixed documents.
  • 128K context window as described by Cohere.
  • Configurable embedding dimensions.
  • Positioned for enterprise search and RAG use cases.

Capabilities

  • text embeddings
  • image embeddings
  • mixed-document embeddings
  • enterprise search/RAG retrieval

Last updated Aug 3, 2026