Rerank Models by Cohere
4 models2024Up to 4k ctx
About
Rerank models sort text inputs by semantic relevance to a specified query. They are often used to sort search results returned from an existing search solution.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Rerank English V3 | Use when the workload needs 4k context. | 2024-04 | 4k context | Current |
| Rerank Multilingual V3 | Use when the workload needs 4k context. | 2024-04 | 4k context | Current |
| Rerank English V2 | Use when the workload needs 512 context. | 2024-04 | 512 context | Current |
| Rerank Multilingual V2 | Use when the workload needs 512 context. | 2024-04 | 512 context | Current |
Release Timeline
1 release group2024-04
4 current
Rerank English V2
Current512 context
Rerank English V3
Current4k context
Rerank Multilingual V2
Current512 context
Rerank Multilingual V3
Current4k context
Specifications(4 models)
| Model | Released | Context |
|---|---|---|
| Rerank English V3 | 2024-04 | 4k |
| Rerank Multilingual V3 | 2024-04 | 4k |
| Rerank English V2 | 2024-04 | 512 |
| Rerank Multilingual V2 | 2024-04 | 512 |
Available From(1 provider)
Frequently Asked Questions
- What is Rerank used for?
- Rerank models sort text inputs by semantic relevance to a specified query.
- How does Rerank compare to Command?
- Rerank by Cohere is strongest where you need its listed use cases, while Command by Cohere is the closest related family to check for multilingual. Rerank has 4 listed variants and reaches up to 4k 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 English V3 with 4k context.
