Command A
Command AAlternatives?
CheaperGemini 4 Argonhighwins 74%-9%*$1.99Synchronous output stops at 65,536+2
BetterGPT-6 Lunamaxwins 60%-95%$0.068Function calling only with none · Chat Completions+3OpenGemma 4 31Bunstatedwins 62%-96%$0.10 / $0.34CheaperGemini 3.8 Flashhighwins 70%-66%*$1.24Sampling parameters are ignored+1CheaperGemini 3.6 Flashhighwins 69%-66%*$1.60Gemini 4 Argonhighwins 74%-9%*$1.99Synchronous output stops at 65,536+2Gemini 3.8 Flashhighwins 70%-66%*$1.24Sampling parameters are ignored+1Gemini 3.6 Flashhighwins 69%-66%*$1.60
Muse Sparkunstatedwins 68%-54%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1
Claude Sonnet 5.5xhighwins 68%-9%$2.01No forced tool use+5GPT-6 Lunamaxwins 60%-95%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 60%-90%$0.085GPT-5.6 Terraxhighwins 63%same$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 67%-9%$0.72Remove unsupported parameters+5Muse Spark 1.2xhighwins 65%-54%$0.97Only auto tool_choice is supported+1Gemma 4 31BunstatedOpenwins 62%-96%$0.10 / $0.34
Mistral Medium 3.5unstatedOpenwins 59%-31%$1.50 / $7.50Memory (4-bit): 67 GB → 77 GBGemma 4 26B A4BunstatedOpenwins 59%-94%$0.15 / $0.60
Qwen3 235B A22B Thinking 2507unstatedOpenwins 55%-83%$0.23 / $2.30Memory (4-bit): 67 GB → 141 GB+1Qwen3.8 27BunstatedOpenwins 54%-78%$0.42 / $2.55max_tokens range · QwenCloud+4Command R+ (08-2024)unstatedOpenwins 40%—$2.50 / $10Context: 256K → 128K+1Command R+Openwins 36%——Context: 256K → 128KCommand R (08-2024)unstatedOpenwins 32%—$0.15 / $0.60Context: 256K → 128K+1Command ROpenwins 31%——Context: 256K → 128KNorth Mini CodeOpenn/a——Command A+thinkingOpenn/a—$0.30 / $1.50Context: 256K → 128K+1Tiny Aya GlobalOpenn/a——Context: 256K → 8K+1All Cohere models →Run it yourself
estimateBenchmarks
in Writing & LanguageFAQ
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?›
#307 of 334 in Chat & Knowledge, #203 of 239 in Coding, #209 of 242 in Agents & Tool Use, #110 of 195 in Writing & Language.
Is Command A better than GPT-5.4 Nano?›
On Arena Text · creative writing, Command A scores 1,336 vs 1,337 — 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?›
Gemini 4 Argon (cheaper), GPT-6 Luna (better), Gemma 4 31B (open weights).