Cohere Rerank API for Production RAG

Why Cohere Rerank?

• ✅ 40% accuracy improvement over bi-encoders
• ✅ 100+ languages supported
• ✅ Hosted API (no model hosting)
• ✅ Fast (< 200ms for 100 docs)

Quick Start

DEVELOPERpython
import cohere

co = cohere.Client('YOUR_API_KEY')

def rerank_with_cohere(query, documents):
    results = co.rerank(
        model='rerank-english-v3.0',  # or 'rerank-multilingual-v3.0'
        query=query,
        documents=documents,
        top_n=10
    )
    
    return [doc['text'] for doc in results.results]

# Use it
retrieved_docs = vector_search(query, k=100)
reranked = rerank_with_cohere(query, retrieved_docs)

Models (November 2025)

rerank-english-v3.0

• English only
• $1 per 1000 searches
• Best accuracy

rerank-multilingual-v3.0

• 100+ languages
• $1 per 1000 searches
• Excellent for global apps

With Metadata

DEVELOPERpython
results = co.rerank(
    query=query,
    documents=[
        {"text": doc, "metadata": {"source": "wiki", "date": "2025"}}
        for doc in documents
    ],
    top_n=10,
    return_documents=True
)

for r in results.results:
    print(f"Score: {r.relevance_score}")
    print(f"Text: {r.document['text']}")
    print(f"Metadata: {r.document['metadata']}")

Cost Optimization

DEVELOPERpython
# Only rerank if initial score is low
def smart_rerank(query, initial_results, threshold=0.7):
    # If top result has high confidence, skip reranking
    if initial_results[0]['score'] > threshold:
        return initial_results[:10]
    
    # Otherwise, rerank
    return rerank_with_cohere(query, [r['text'] for r in initial_results])

Cohere Rerank is the easiest way to dramatically improve RAG accuracy. Just plug it in after retrieval.