cohere-rerank-v5-pro · Cohere
cohere-rerank-v5-pro is Cohere's enterprise search and retrieval-augmented generation (RAG) reranking model. It can reorder retrieval results based on query relevance, supports multiple languages, and provides stable relevance scoring to help filter out irrelevant content. Its Context Focus feature can also extract the most relevant passages from documents, reducing the language model's token consumption and response latency.
cohere-rerank-v5-pro is Cohere's enterprise search and retrieval-augmented generation (RAG) reranking model. It can reorder retrieval results based on query relevance, supports multiple languages, and provides stable relevance scoring to help filter out irrelevant content. Its Context Focus feature can also extract the most relevant passages from documents, reducing the language model's token consumption and response latency.
On AIHubMix, Cohere Rerank V5 Pro costs $0.05 per million input tokens and $0.05 per million output tokens.
Cohere Rerank V5 Pro accepts text input.
Cohere Rerank V5 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-v5-pro — no other code changes needed.
Cohere Rerank V5 Pro is developed by Cohere. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Cohere Rerank V5 Pro was released in October 2026 by Cohere.
cohere-rerank-v5-fast is Cohere's enterprise search and retrieval-augmented generation…
Developed by Cohere, north-mini-code-free is the debut model of the North family and…
Cohere's stronger command model for multilingual agents and enterprise workflows
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Rerank 4 is the most advanced set of reranker models available today, purpose-built to…
Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of…
Use Cohere Rerank V5 Pro via the AIHubMix unified API — one interface for every major LLM.