Using Cohere Rerank 5 Fast on Cohere API

Implementation guide · Cohere Rerank · Cohere

Serverless

Cohere API exposes Cohere Rerank 5 Fast through model ID rerank-v5.0-fast. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-21. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cohere API and generate an API key.
  2. 2
    Use the Cohere API SDK or REST API to call rerank-v5.0-fast — see the documentation for request format.
  3. 3
    You'll be billed $0.02/1M input. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Cohere API documentation for integration details.

Pricing on Cohere API

TypePrice (per 1M)
Input tokens$0.02

Capabilities

No model capability flags are currently sourced.

About Cohere Rerank 5 Fast

Cohere Rerank 5 Fast is Cohere's low-latency, high-throughput reranking model, released October 21, 2026 with the Rerank 5 generation. It is multilingual, reranks English and non-English documents and semi-structured JSON within a 32,768-token query-plus-document window, and adds Context Focus, which returns the most relevant passages inside each document as scored character spans, plus calibrated relevance scores. Cohere says it outperforms its previous-generation Rerank 4 Pro. The Cohere API serves it as rerank-v5.0-fast.

Full model details →

Model Specs

Released2026-10-21
Parameters500M
Context32K

More Models on Cohere API

Cohere Rerank v4.0 ProCohere Rerank v4.0 FastCohere Rerank v3.5Cohere Rerank English v3.0Cohere Rerank Multilingual v3.0Cohere Rerank 5 Pro
All models on Cohere API →

Provider

Cohere API

Cohere

Toronto, Ontario, Canada