Cohere Rerank 4 Pro
Cohere Rerank 4 Pro is a reranking model from Cohere designed to improve search result relevance with a 4096-token context window.
CohereSemantic reranking for retrieval pipelines
Cohere Rerank 4 Pro (rerank-v4.0-pro) is a reranking model developed by Cohere, built to re-score and reorder candidate documents or passages retrieved by a first-stage retrieval system. It operates on a 4096-token context window and is designed to be used as a second-stage component in retrieval-augmented generation (RAG) pipelines, search systems, and information retrieval workflows. Rather than generating text, it assigns relevance scores to a list of documents given a query, allowing downstream systems to surface the most pertinent results.
Rerank 4 Pro is the professional-tier variant in Cohere's Rerank 4 model family, intended for production use cases that require high-quality relevance scoring across large document sets. It is well suited for enterprise search, question-answering systems, and any application where the ordering of retrieved content directly affects output quality. The model is available as a first-party offering through Cohere's API and is accessible on MindStudio without requiring separate API key management.
What Cohere Rerank 4 Pro supports
Document Reranking
Scores and reorders a list of candidate documents by relevance to a given query, improving the precision of first-stage retrieval results.
4096-Token Context
Processes queries and documents within a 4096-token context window, supporting moderately long passages in a single reranking call.
RAG Pipeline Integration
Functions as a second-stage component in retrieval-augmented generation workflows, re-scoring chunks before they are passed to a language model.
Relevance Scoring
Returns a numerical relevance score for each document-query pair, enabling flexible thresholding and filtering in downstream applications.
Multilingual Support
Cohere's Rerank 4 family supports reranking across multiple languages, making it usable in non-English retrieval pipelines.
Ready to build with Cohere Rerank 4 Pro?
Get Started FreeCommon questions about Cohere Rerank 4 Pro
What is the context window for Cohere Rerank 4 Pro?
Cohere Rerank 4 Pro has a context window of 4096 tokens, which applies to the combined length of the query and each candidate document passage processed in a reranking call.
How is a reranking model different from a language model?
A reranking model does not generate text. Instead, it takes a query and a list of documents as input and returns a relevance score for each document, allowing you to reorder results by how well they match the query.
What is Cohere Rerank 4 Pro best used for?
It is best used as a second-stage component in search and retrieval-augmented generation (RAG) pipelines, where a fast first-stage retriever returns a broad set of candidates and the reranker narrows them down to the most relevant results.
What is the pricing for Cohere Rerank 4 Pro?
Pricing information is not published in the available metadata. You should consult Cohere's official pricing page or contact Cohere directly for current rates.
Does Cohere Rerank 4 Pro support image or video inputs?
No. Based on the available metadata, Cohere Rerank 4 Pro does not support image or video inputs. It is a text-based reranking model.
What is the knowledge cutoff or release date for this model?
The metadata indicates a release date of 2026. No specific training data knowledge cutoff date is published in the available information.
Explore similar models
CohereCohere Rerank 4 Fast
Cohere Rerank 4 Fast is a reranking model from Cohere designed to score and reorder search results with a 4096 token context window.
CohereCohere Rerank 3.5
Cohere Rerank 3.5 is a reranking model from Cohere that reorders search results by semantic relevance with a 4096 token context window.
CohereCohere Embed 4
Cohere Embed 4 is an embedding model from Cohere with a 128,000-token context window, released in April 2025.
NvidiaLlama Nemotron Rerank VL 1B v2
Llama Nemotron Rerank VL 1B v2 is a vision-language reranking model from Nvidia with a 10,240-token context window.
Voyage AIVoyage Rerank 2.5
Voyage Rerank 2.5 is a reranking model from Voyage AI designed to improve document retrieval relevance with a 32,000-token context window.
QwenQwen3 Reranker 0.6B
Qwen3 Reranker 0.6B is a lightweight reranking model from Qwen designed to reorder retrieved documents with a 32,768-token context window.
Start building with Cohere Rerank 4 Pro
No API keys required. Create AI-powered workflows with Cohere Rerank 4 Pro in minutes — free.