Command Light

Command Light is Cohere’s smallest and fastest model from the original Command family, released alongside Embed v3 in November 2023. It has around 6 billion parameters and a 4,096 token context window, and Cohere designed it for applications that need low latency and lower cost rather than top-tier reasoning. It was priced at $0.30 per million input tokens and $0.60 per million output tokens through the Cohere API. Cohere deprecated Command Light in September 2025 along with several other early Command models, and now points users toward Command R, Command R+, or Command A, calling Command A the strongest performer across the board. It remains documented here as a legacy option that some existing integrations may still reference.