LLM ReferenceLLM Reference

Rerank Models by Cohere

6 models2024–2025Up to 32K ctx

About

Rerank is a family of 6 AI models by Cohere, released between 2024 and 2025.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

6 in view

Use when the workload needs ranking and 32K context.

2025-04ranking32K context

Use when the workload needs ranking and 32K context.

2025-04ranking32K context

Use when provider availability and model metadata match the workload.

2024-10

Use when the workload needs ranking and 4K context.

2024-08ranking4K context

Use when the workload needs ranking and 4K context.

2024-02ranking4K context

Use when the workload needs ranking and 4K context.

2024-02ranking4K context

Release Timeline

4 release groups
2025-04
2 current
Rerank v4.0 Fast
ranking32K context
Current
Rerank v4.0 Pro
ranking32K context
Current
2024-10
1 current
2024-08
1 current
Rerank v3.5
ranking4K context
Current
2024-02
2 current
Rerank English v3.0
ranking4K context
Current
Rerank Multilingual v3.0
ranking4K context
Current

Specifications(6 models)

Rerank model specifications comparison
ModelReleasedContext
Rerank v4.0 Pro2025-0432k
Rerank v4.0 Fast2025-0432k
Cohere Rerank 3.52024-10
Rerank v3.52024-084K
Rerank English v3.02024-024K
Rerank Multilingual v3.02024-024K

Available From(2 providers)

Frequently Asked Questions

What is Rerank used for?
Rerank is used for ranking and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
How does Rerank compare to Command?
Rerank by Cohere is strongest where you need ranking, while Command by Cohere is the closest related family to check for multilingual. Rerank has 6 listed variants and reaches up to 32K context, while Command reaches up to 256K context, so compare the specs and pricing tables before choosing a production model.
Which Rerank model should I use?
If price is the main constraint, use the pricing table first because Rerank does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Rerank v4.0 Pro with 32K context.

Models(6)