cohere
rerank-v4.0-fast
High performance, lowest latency reranker. AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Supports 100+ languages with a context length of 32,768 tokens.
Provider:
cohere
Model type:
rerank
Location:
US
Context Window
32768
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
2
Input tokens per million
$
0
Output tokens per million
