---
title: "Command R — LLM-TEST.com"
url: /models/command-r/
canonical_url: https://llm-test.com/models/command-r/
language: en
type: model
summary: "The cost-efficient mid-tier of the Command line, built for scalable RAG and routine enterprise tasks. It keeps the family's grounding strengths at a lower price than R+."
last_updated: "2026-11-05"
---

# Command R

_Cohere · Balanced · open weights_

The cost-efficient mid-tier of the Command line, built for scalable RAG and routine enterprise tasks. It keeps the family's grounding strengths at a lower price than R+.

## At a glance

- Released: Jul 9, 2026
- Provider: Cohere
- Context window: 128,000 tokens
- Max output: 8,000 tokens
- Modalities: Text → text
- Knowledge cutoff: March 2026
- API model ID: `command-r`
- License: Open weights (CC-BY-NC, research)

## Pricing

- Standard: $0.15 input / $0.60 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0006 (standard)

## Best use cases

- **Scalable RAG** — Handles high-volume retrieval workloads at a lower per-token cost.
- **Business chat** — Powers internal assistants grounded in company data.
- **Summarization** — Condenses documents with reliable source attribution.

## Strengths

- Good RAG grounding
- Lower cost than R+
- Enterprise-ready

## Limitations

- Less capable than R+ on complex tasks
- Research-only license

## Where to get access

- API: the Cohere dashboard — https://dashboard.cohere.com
- Also available: Amazon Bedrock, Azure AI Foundry and Oracle OCI
- Docs: https://docs.cohere.com

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/