Using Cohere Rerank v4.0 Fast on Cohere API

Implementation guide · Cohere Rerank · Cohere

Serverless

Cohere API exposes Cohere Rerank v4.0 Fast through model ID rerank-v4.0-fast. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-01. Next refresh: weekly.

Quick Start

1
Create an account at Cohere API and generate an API key.
2
Use the Cohere API SDK or REST API to call rerank-v4.0-fast — see the documentation for request format.

API Portal Documentation Pricing

Code Examples

See Cohere API documentation for integration details.

Pricing on Cohere API

Capabilities

No model capability flags are currently sourced.

About Cohere Rerank v4.0 Fast

Fast variant reranking model optimized for low latency and high throughput. Multilingual support for reranking English and non-English documents and semi-structured data (JSON). Provides good quality at faster inference speeds than the pro variant.

Full model details →

Model Specs

Released2025-04-01

Context32k

ArchitectureEncoder Only

Cohere

Toronto, Ontario, Canada