Cohere · Rerank
Rerank V4.0 Fast
Newer version: Rerank V5.0 Fast. Our catalogue has no release date for Rerank V4.0 Fast. We compared the version names in our catalogue.
Cohere Rerank 4.0 Fast is Cohere's low-latency multilingual cross-encoder reranker. It reorders documents by semantic relevance to a query for search and retrieval-augmented generation, tuned for high-throughput workloads across 100+ languages with a 32K context window.
Evidence and sources
Model architecture, as its sources state it
Maker HQ: US (according to Cohere's own website)
Sources: Cohere API data, LiteLLM data, Models.dev data, EURouter dataPrimary data from Cohere API
from LiteLLM: deprecation date
from Models.dev: weights availability
from EURouter: description
Tags from its sources:proprietaryrerankmultilingual
Advantages and trade-offs
Compared with 10 representative rerank models
Advantages
Trade-offs
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersText
Text
Also known as: azure_ai/cohere-rerank-v4.0-fast, cohere-rerank-4.0-fast, cohere/rerank-v4-fast, rerank-v4-fast
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works