Head to head

GPT-4.1 mini vs Command R (03-2024)

On a blended workload of one million input tokens and three million output tokens, Command R (03-2024) is 1.0× cheaper than GPT-4.1 mini.

GPT-4.1 miniCommand R (03-2024)
Provider OpenAI Cohere
Input / MTok $0.4 $0.5
Output / MTok $1.6 $1.5
Cache read / MTok $0.1
Context window 1,047,576
Blended 1M in + 3M out $5.20 $5.00
Status ga ga

GPT-4.1 mini detail   Command R (03-2024) detail