Using Cohere Embed v4.0 on Cohere API

Implementation guide · Cohere Embed · Cohere

Serverless

Cohere API exposes Cohere Embed v4.0 through model ID embed-v4.0. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cohere API and generate an API key.
  2. 2
    Use the Cohere API SDK or REST API to call embed-v4.0 — see the documentation for request format.
API PortalDocumentationPricing

Code Examples

See Cohere API documentation for integration details.

Pricing on Cohere API

Capabilities

Multimodal

About Cohere Embed v4.0

Latest multimodal embedding model supporting text, images, and mixed content (e.g., PDFs). Embed v4.0 offers variable embedding dimensions (256, 512, 1024, 1536 default) and supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance). Ideal for semantic search, classification, and clustering across multimodal data.

Full model details →

Model Specs

Released2025-04-01
Context128k
ArchitectureEncoder Only

More Models on Cohere API

Cohere Embed English v3.0Cohere Embed English Light v3.0Cohere Embed Multilingual v3.0Cohere Embed Multilingual Light v3.0
All models on Cohere API →

Also available on(2)

Microsoft Foundry$0.12/1MVercel AI Gateway$0.12/1M
Compare all providers →

Provider

Cohere API

Cohere

Toronto, Ontario, Canada