by Cohere
Command R+ by Cohere is an enterprise-focused large language model optimized for retrieval-augmented generation (RAG), complex multi-step reasoning, and multilingual tasks. With a 128K token context window, strong citation capabilities, and competitive pricing, it's a leading choice for business AI applications.
Command R+ excels at grounded generation — provide documents and request citations:
Based on the following documents, answer the question and cite
which document each claim comes from.
<documents>
[Document 1: ...]
[Document 2: ...]
</documents>
Question: What were the key factors in Q3 revenue growth?
Request specific formats for reliable, parseable responses:
Extract entities from this text and return as JSON:
{ "people": [], "organizations": [], "locations": [], "dates": [] }
For complex tasks, break them into steps and let the model reason through each one.
| Parameter | Description |
|---|---|
| temperature | Randomness 0-2 (default 0.3 for factual tasks) |
| max_tokens | Maximum response length |
| top_p | Nucleus sampling threshold |
| system | System prompt for role/behavior |
| tools | Function definitions for tool use |
Quick tips from the community about what works with Command R+ right now.
Sign in to share a tip.
No tips yet. Add a tip for this model.