Command R7B
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-r7bLicense
Open weights (CC-BY-NC, research)
Pricing
Standard
Input$0.0375 / 1M
Output$0.15 / 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 ≈ $0.0002 on the standard tier. Run your own prompt through the calculator →
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 & limitations
Strengths
- Tiny and fast
- Lowest Command price
- Open weights
Limitations
- Limited reasoning capacity
- Very short max output
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-r7b",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'