Skip to main content
llm.info

Cohere Rerank 4 Fast

Cohere

The latency-optimised variant of Cohere's Rerank 4 family, targeting low-latency and high-throughput reranking where the Pro tier's peak relevance is not required. It shares the generation's 32,000-token context window and multilingual coverage, and is billed per search query.

Strengths

  • Tuned for low-latency, high-throughput reranking
  • Same 32,000-token context window as the Pro tier
  • Multilingual coverage across English and non-English documents
  • Billed per search query rather than per token

Caveats

  • Proprietary - Cohere API only
  • Trades peak relevance for latency - use Rerank 4 Pro for the hardest queries
  • Requires a first-stage retriever to produce the candidate set
  • Cohere does not publish a release date or per-query price on its model documentation
Vendor
Cohere
Context Window
32,000 tokens
License
Proprietary
Modalities
text

Capabilities

Vision
Audio
Video
Tool Use

Pricing

Billed per search query rather than per token. See Cohere pricing for current rates.

Reviews

Comments