Cohere-rerank-v3-english
Cohere-rerank-v3-english
Version: 1
CohereLast updated August 2025

Key capabilities

About this model

Rerank should be used as a ranker after initial retrieval (i.e. an initial search system finds the top-100 most relevant documents for a larger corpus of documents).

Key model capabilities

  • Context window of the model is 4096 tokens
  • The max query length is 2048 tokens

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

Cohere Rerank English is the market's leading reranking model used for semantic search and retrieval-augmented generation (RAG).

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

Rerank English has SOTA performance on benchmarks in Code Retreival, Semi-structured Data Retreival, and Long Context.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Rerank supports JSON objects as documents where users can specify at query time the fields (keys) that semantic search should be applied over.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

 {
  "id": "571e6744-3074-457f-8935-08646a3352fb",
  "results": [
   {
    "document": {
     "Content": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district. The President of the USA and many major national government offices are in the territory. This makes it the political center of the United States of America.",
     "Title": "Details about Washington D.C"
    },
    "index": 0,
    "relevance_score": 0.98347044
   },
   {
    "document": {
     "Content": "Carson City is the capital city of the American state of Nevada. ",
     "Title": "Facts about Carson City"
    },
    "index": 1,
    "relevance_score": 0.07172112
   },
   {
    "document": {
     "Content": "Micronesia, officially the Federated States of Micronesia, is an island nation in the Pacific Ocean, northeast of Papua New Guinea. The country is a sovereign state in free association with the United States. The capital city of Federated States of Micronesia is Palikir.",
     "Title": "Micronesia"
    },
    "index": 3,
    "relevance_score": 0.05281402
   },
   {
    "document": {
     "Content": "North Dakota is a state in the United States. 672,591 people lived in North Dakota in the year 2010. The capital and seat of government is Bismarck.",
     "Title": "North Dakota"
    },
    "index": 2,
    "relevance_score": 0.03138043
   }
  ]
 }

Model architecture

The provider has not supplied this information.

Long context

Context window of the model is 4096 tokens

Optimizing model performance

The provider has not supplied this information.

Additional assets

We evaluated Rerank English on various configurations with BM25 (lexical search) as the initial retrieval step as well as Embeddings as the initial retrieval step BM25 with Rerank v3.0 General Retreival Evaluation Results and Embeddings with Rerank v3.0 General Retreival Evaluation Results For full details of this model, release blog post

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

Responsible AI considerations

Safety techniques

The provider has not supplied this information.

Safety evaluations

The provider has not supplied this information.

Known limitations

The provider has not supplied this information.

Acceptable use

Acceptable use policy

The provider has not supplied this information.

Quality and performance evaluations

Source: Cohere Rerank English has SOTA performance on benchmarks in Code Retreival, Semi-structured Data Retreival, and Long Context. We evaluated Rerank English on various configurations with BM25 (lexical search) as the initial retrieval step as well as Embeddings as the initial retrieval step BM25 with Rerank v3.0 General Retreival Evaluation Results and Embeddings with Rerank v3.0 General Retreival Evaluation Results

Benchmarking methodology

Source: Cohere The provider has not supplied this information.

Public data summary

Source: Cohere The provider has not supplied this information.
Model Specifications
Context Length4096
LicenseCustom
Last UpdatedAugust 2025
Input TypeText
Output TypeText
ProviderCohere
Languages1 Language