Cohere Rerank v4.0 Fast
Version: 2
Direct from Azure models
Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:- Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
- Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all as part of one Azure AI Foundry platform.
- Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Azure AI Foundry; reducing integration effort.
- Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.
Key capabilities
About this model
Cohere's Rerank v4.0 Fast endpoint enables businesses to significantly improve search and retrieval-augmented generation systems. As input, it takes a query and a list of potentially relevant documents. Rerank v4.0 Fast then returns the documents as a list sorted by semantic similarity to the provided query. As an intelligent cross-encoding AI model, Rerank v4.0 Fast is able to understand the meaning behind enterprise data and user questions. Rerank v4.0 Fast can be implemented with just a few lines of code, delivers leading performance across over 100 languages, and is uniquely capable of understanding complex information which requires reasoning. These attributes make Rerank v4.0 Fast particularly well suited for global organizations within Finance, Healthcare, Energy, Government, and Manufacturing.Rerank v4.0 Fast can be added to existing systems, whether keyword or semantic, to improve performance.
Key model capabilities
Use cases
See Responsible AI for additional considerations for responsible use.Key use cases
While this model is generally useful, business tend to use it to enhance Agentic AI and Retrieval-Augmented Generation (RAG) Systems and improve Enterprise Search Systems. This capability is particularly helpful for businesses operating within specialized industries such as finance, government, energy, manufacturing, and healthcare.Out of scope use cases
The provider has not supplied this information.Pricing
Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here. Pricing for managed compute offer is based on GPU surcharge See pricing details here.Technical specs
Training cut-off date
The provider has not supplied this information.Training time
The provider has not supplied this information.Input formats
Image and TextOutput formats
Image and TextSupported languages
Rerank V4.0 Fast also offers industry-leading multilingual capabilities. It can search across data in 100+ languages, with state-of-the-art accuracy on the following 10 global business languages: Arabic, Chinese, French, German, Hindi, Japanese, Korean, Portuguese, Russian, and Spanish.Sample JSON response
The provider has not supplied this information.Model architecture
The provider has not supplied this information.Long context
The provider has not supplied this information.Optimizing model performance
The provider has not supplied this information.Additional assets
The provider has not supplied this information.Training disclosure
Training, testing and validation
The provider has not supplied this information.Distribution
Distribution channels
Follow this article to deploy the Cohere model with pay-as-you-go.More information
Rerank improves search systems by sorting documents based on their semantic similarity to a query.Responsible AI considerations
Safety techniques
The provider has not supplied this information.Safety evaluations
The provider has not supplied this information.Known limitations
The provider has not supplied this information.Acceptable use
Acceptable use policy
The provider has not supplied this information.Quality and performance evaluations
Source: Cohere The provider has not supplied this information.Benchmarking methodology
Source: Cohere The provider has not supplied this information.Public data summary
Source: Cohere The provider has not supplied this information.Model Specifications
Context Length4096
LicenseCustom
Last UpdatedDecember 2025
Input TypeText,Image
Output TypeText,Image
ProviderCohere
Languages14 Languages