---
type: "post"
id: "cohere-rerank-5-more-relevant-context-for-rag-bba6d4"
slug: "cohere-rerank-5-more-relevant-context-for-rag-bba6d4"
title: "Cohere Rerank 5 | More Relevant Context for RAG and Agents"
description: "Cohere has released Rerank 5, a new enterprise reranking model family with Pro and Fast tiers."
retrieval_nugget: "Cohere has released Rerank 5, a new enterprise reranking model family with Pro and Fast tiers."
published_at: "2026-10-21"
updated_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "published_at"
topics: ["retrieval","context-engineering","agent-context"]
entities: ["Cohere","Rerank 5","Rerank 5 Pro","Rerank 5 Fast","Context Focus","Cohere North","Microsoft Foundry","Amazon SageMaker"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Cohere has launched Rerank 5, adding a new retrieval model to the RAG and agent context pipeline discussed in the prior."
prior_refs: ["memory:25952e40-d6ae-8b12-ad53-3c1ad0832d40"]
source_url: "https://cohere.com/blog/rerank-5"
source_urls: ["https://cohere.com/blog/rerank-5"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:cohere-rerank-5-more-relevant-context-for-rag-bba6d4"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/cohere-rerank-5-more-relevant-context-for-rag-bba6d4/","markdown":"https://newruntime.com/posts/cohere-rerank-5-more-relevant-context-for-rag-bba6d4.md","json":"https://newruntime.com/posts/cohere-rerank-5-more-relevant-context-for-rag-bba6d4.json"}
---

# Cohere Rerank 5 | More Relevant Context for RAG and Agents

## Retrieval answer

Cohere has released Rerank 5, a new enterprise reranking model family with Pro and Fast tiers.

Cohere has released Rerank 5, a new enterprise reranking model family with Pro and Fast tiers. The company says both tiers are generally available through the Cohere API, Model Vault, Microsoft Foundry, Amazon SageMaker, and Cohere North.

The release adds Context Focus, an optional feature that returns relevant passages within documents in a single rerank call rather than only ranking documents or chunks. API pricing is $0.05 per million tokens for Rerank 5 Pro and $0.02 per million tokens for Rerank 5 Fast. Cohere says Fast reranks about 187 1,000-token documents per second on one NVIDIA A100 under its stated test conditions, or 2.9 times Pro's throughput.

Cohere reports that Pro ranked first on 39 of 46 composite datasets in its evaluation and scored 82.2 on BRIGHT. Those are vendor-reported benchmark results; the announcement does not establish performance, latency, cost reduction, or answer-quality gains in a particular deployment.

Source: https://cohere.com/blog/rerank-5

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Retrieval](https://newruntime.com/topics/retrieval.md): Explore the retrieval topic hub.
- topic hub: [Context Engineering](https://newruntime.com/topics/context-engineering.md): Explore the context-engineering topic hub.
- topic hub: [Agent Context](https://newruntime.com/topics/agent-context.md): Explore the agent-context topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)