cohere-rerank-v4.0-pro

by Cohere

Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.

API Pricing

Input$0.07 / 1M tokens

Specifications

Modalitiestext, image

FAQ

What is cohere-rerank-v4.0-pro?

Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.

How much does cohere-rerank-v4.0-pro cost?

On AIHubMix, cohere-rerank-v4.0-pro costs $0.07 per million input tokens.

What modalities does cohere-rerank-v4.0-pro support?

cohere-rerank-v4.0-pro accepts text and image input.

How do I call cohere-rerank-v4.0-pro via API?

cohere-rerank-v4.0-pro is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to cohere-rerank-v4.0-pro — no other code changes needed.

Who develops cohere-rerank-v4.0-pro?

cohere-rerank-v4.0-pro is developed by Cohere. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Cohere

north-mini-code-free

by Cohere

Developed by Cohere, north-mini-code-free is the debut model of the North family and…

256,000 tokens context

command-a-plus-05-2026

by Cohere

Cohere's stronger command model for multilingual agents and enterprise workflows

$2.5/1M in · $10/1M out
128,000 tokens context

cohere-rerank-v4.0-fast

by Cohere

Rerank 4 is the most advanced set of reranker models available today, purpose-built to…

$0.07/1M in

embed-v-4-0

by Cohere

Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of…

$0.12/1M in
128,000 tokens context

cohere-command-a

by Cohere

Command A is Cohere most performant model to date, excelling at tool use, agents…

$2.5/1M in · $10/1M out

command-a-03-2025

by Cohere

Command A is Cohere most performant model to date, excelling at tool use, agents…

$2.5/1M in · $10/1M out

Use cohere-rerank-v4.0-pro via the AIHubMix unified API — one interface for every major LLM.