Command R+
Cohere's enterprise flagship, purpose-built for retrieval-augmented generation, grounded citations, and multi-step tool use. Weights are published under a research-only license.
At a glance
Released
Jul 9, 2026
Provider
Cohere
Context window
128,000 tokens
Max output
16,000 tokens
Modalities
Text → text
Knowledge cutoff
March 2026
API model ID
command-r-plusLicense
Open weights (CC-BY-NC, research)
Pricing
Standard
Input$2.50 / 1M
Output$10 / 1M
* Rates are from a third-party aggregator — verify before relying on them. A typical 1,500-token prompt with a 650-token answer costs ≈ $0.010 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withCommand R+ (08-2024) (August 2024)
- More accurate citations and grounding than the 2024 release
- Improved multi-step tool use for enterprise agents
- Higher price than the mid-tier Command R
Best use cases
Enterprise RAG
Answers over private knowledge bases with inline source citations.
Tool-using agents
Plans and executes multi-step workflows across business systems.
Regulated industries
Grounded, auditable outputs suit compliance-sensitive teams.
Strengths & limitations
Strengths
- Best-in-class RAG grounding
- Strong tool use
- Enterprise focus
Limitations
- Research-only license for the weights
- Priciest in the Command line
How to test it
- No-code: open the Cohere dashboard and run a prompt in the playground.
- API: create a key in the Cohere dashboard and call the API (example below).
curl https://api.cohere.ai/compatibility/v1/chat/completions \
# OpenAI-compatible endpoint
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "command-r-plus",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'