---
title: "Command R7B — LLM-TEST.com"
url: /models/command-r7b/
canonical_url: https://llm-test.com/models/command-r7b/
language: en
type: model
summary: "The smallest, cheapest member of the Command line, a compact model for on-device and high-volume enterprise use. Its tiny footprint makes local and edge RAG practical."
last_updated: "2026-11-05"
---

# Command R7B

_Cohere · Budget · open weights_

The smallest, cheapest member of the Command line, a compact model for on-device and high-volume enterprise use. Its tiny footprint makes local and edge RAG practical.

## At a glance

- Released: May 14, 2026
- Provider: Cohere
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Modalities: Text → text
- Knowledge cutoff: March 2026
- API model ID: `command-r7b`
- License: Open weights (CC-BY-NC, research)

## Pricing

- Standard: $0.0375 input / $0.15 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0002 (standard)

## Best use cases

- **On-device RAG** — Runs grounded retrieval locally where privacy or latency rules out the cloud.
- **Cost-sensitive volume** — Serves large request counts at the lowest Command price.
- **Edge agents** — Lightweight enough for embedded and offline deployments.

## Strengths

- Tiny and fast
- Lowest Command price
- Open weights

## Limitations

- Limited reasoning capacity
- Very short max output

## 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/