
No ratings yet
Be the first to review this model
Cohere's most performant Command model, delivering 150% of the throughput of its predecessor on only two GPUs with a 256K context window. Features a reasoning variant for complex agentic tasks and supports 23 languages. The strongest option for enterprise RAG, tool use, and grounded generation workflows.
Released
March 15, 2025
Parameters
111B
Context
256K
Pricing
Paid
Last updated: March 15, 2026
Benchmark scores may vary based on evaluation methodology and conditions.