Command A
Command AAlternatives?
CheaperCommand A+thinkingOpen×5.5-86%$0.30 / $1.50Context: 256K → 128K+1
BetterGranite 4.2 3BthinkingOpen×2.9-99%$0.006Context: 256K → 128KOOpenMiniCPM5 1Bnon-thinking×85.8——Context: 256K → 131K
CheaperGemini 4 Argonhigh×5.1-9%*$1.62Synchronous output stops at 65,536+2lCheaperLFM2.5 2.6BthinkingOpen×4.8-91%$0.35 / $0.50Context: 256K → 131KCommand A+thinkingOpen×5.5-86%$0.30 / $1.50Context: 256K → 128K+1Gemini 4 Argonhigh×5.1-9%*$1.62Synchronous output stops at 65,536+2lLFM2.5 2.6BthinkingOpen×4.8-91%$0.35 / $0.50Context: 256K → 131K
Grok 4.3medium×4.6-64%$1.25 / $2.50
Qwen3.8 27Bnon-thinkingOpen×4.3-78%$2.49max_tokens range · QwenCloud+4Granite 4.2 3BthinkingOpen×2.9-99%$0.006Context: 256K → 128KGemma 4 E4BthinkingOpen×2.5-99%$0.008Context: 256K → 128K
GPT-5.6 Lunanon-thinking+3%-90%$0.01
Mistral Small 4thinkingOpen+16%-94%$0.017Memory (4-bit): 67 GB → 72 GBGranite 4.2 8BthinkingOpen×2.4-98%$0.024Context: 256K → 128KCommand A+thinkingOpen×5.5-86%$0.30 / $1.50Context: 256K → 128K+1lLFM2.5 2.6BthinkingOpen×4.8-91%$0.35 / $0.50Context: 256K → 131KTiny Aya GlobalOpen-20%——Context: 256K → 8K+1North Mini CodeOpen-7%——Command A+thinkingOpen×5.5—$0.30 / $1.50Context: 256K → 128K+1Command R (08-2024)unstatedOpenn/a—$0.15 / $0.60Context: 256K → 128K+1Command R+ (08-2024)unstatedOpenn/a—$2.50 / $10Context: 256K → 128K+1Command R+Openn/a——Context: 256K → 128KCommand ROpenn/a——Context: 256K → 128KAll Cohere models →Run it yourself
estimateBenchmarks
in Chat & KnowledgeFAQ
How much does Command A cost?›
$2.50 per 1M input tokens and $10 per 1M output tokens.
Is Command A free to use?›
There is no free API; the cheapest paid price is $2.50 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Command A, and what is it best at?›
#309 of 336 in Chat & Knowledge, #203 of 239 in Coding, #209 of 242 in Agents & Tool Use, #116 of 197 in Writing & Language.
Is Command A better than Qwen3 235B A22B Instruct 2507?›
On AA Omniscience · Hallucination Rate, Command A scores 77.3 vs 77.2 — about the same.
How can I use Command A?›
Through the API of Azure AI Foundry, Cohere.
What is the context window of Command A?›
256K tokens, with up to 8K output tokens.
When was Command A released? Is there a newer version?›
Released 2025-03-13. It is the current version in its line.
Is Command A open source?›
Yes, the weights are open (cc-by-nc-4.0 licence).
Can I run Command A locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Command A read images?›
No, it accepts text only.
What is Command A?›
Command A is an open-weights language model from Cohere, released Mar 2025.
What are the best alternatives to Command A?›
Command A+ (cheaper), Granite 4.2 3B (better), MiniCPM5 1B (open weights).