Command R+
Cohere's enterprise model purpose-built for RAG and production tool-calling pipelines
Context window
128K
Input / 1M tokens
$2.50
Output / 1M tokens
$10.00
Provider
Cohere
Command R+ is not trying to be the most capable model on every benchmark - it's purpose-built for enterprise RAG pipelines and reliable tool calling. Cohere's grounding approach significantly reduces hallucination on retrieval tasks compared to general-purpose models. It also natively supports 10 business languages and is available for self-hosting via Cohere's cloud or on-premise deployments.
Strengths
- ✓Purpose-built for RAG with citation grounding
- ✓Low hallucination rate on retrieval tasks
- ✓Reliable multi-step tool calling
- ✓Supports 10 business languages natively
- ✓Available for on-premise deployment
Best for developers who...
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| RAG (BEIR) | Top-5 | Competitive on standard RAG benchmarks |
| MMLU | ~75% | Not the primary benchmark focus |
Source: Cohere Command R+ launch post
Compare Command R+ with
Command R+ vs Claude Sonnet 4.6
Anthropic - 200K ctx
Command R+ vs Mistral Large
Mistral AI - 128K ctx
Command R+ vs Amazon Nova Pro
Amazon Web Services - 300K ctx