AI Model Wiki

    Skip to main content

    In short

    Cohere Command R+ 2 is a 104B parameter model designed for high-throughput enterprise applications, specifically excelling in Retrieval-Augmented Generation and tool-use automation. It offers a cost-effective, open-weights alternative to proprietary models for businesses requiring verifiable outputs and data sovereignty.

    Frequently asked

    What is the context window size for Cohere Command R+ 2?
    The model features a 128k token context window, allowing it to handle massive datasets and long documents effectively.
    Which languages does Cohere Command R+ 2 support?
    It is optimized for 10 key global languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Chinese.
    How much does Cohere Command R+ 2 cost to use via API?
    API pricing is $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a free limited tier available for non-commercial testing.
    Can Cohere Command R+ 2 be self-hosted?
    Yes, it is an open-weights model available for deployment on private clouds like AWS, Azure, and GCP, though self-hosting requires significant hardware due to its 104B parameters.
    What are the primary use cases for this model?
    It is engineered for enterprise knowledge management, customer support automation, legal document analysis, and financial research, with a specific focus on RAG and tool-use workflows.