← back to the directory
Model Inference & Serving

Command R

1Cohere's 2RAG-optimized 3enterprise 4conversational 5language 6model

the six Ws · specification

W1 Who

Cohere developed Command R as an enterprise-focused large language model.

W2 What

Command R is a generative LLM optimized for retrieval-augmented generation, tool use, and long-context reasoning.

W3 Where

Available via Cohere's API and as open weights on Hugging Face under CohereLabs.

W4 When

Released March 2024, with Command R+ following the same month and later updates through 2024.

W5 Why

Built to power production RAG and agentic workflows with strong multilingual and citation support.

W6 With

Runs via the Cohere API, or self-hosted through Hugging Face transformers with the open-weight checkpoint.

W7 Watch

Open weights (CohereLabs/c4ai-command-r) under CC-BY-NC with an acceptable-use addendum; watch Cohere's terms, hosted API requires a Cohere API key.

alternatives

works with

RAGtool-uselong-contextenterprise-LLMretrieval-augmented

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.