Command A
Command ARankingin non-thinking mode?
Alternatives?
CheaperClaude Sonnet 5.5max×8-9%$5.46No forced tool use+5
BetterGPT-6 Lunalow×3.1-95%$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 Flashthinking×5.7-95%$0.37Memory (4-bit): 67 GB → 108 GB+6
CheaperGemini 4 Argonhigh×7.6-9%*$1.99Synchronous output stops at 65,536+2CheaperGPT-6.1 Solmax×7.4-9%$0.72Remove unsupported parameters+5Claude Sonnet 5.5max×8-9%$5.46No forced tool use+5Gemini 4 Argonhigh×7.6-9%*$1.99Synchronous output stops at 65,536+2GPT-6.1 Solmax×7.4-9%$0.72Remove unsupported parameters+5
Muse Spark 1.3max×6.9-54%$1.60Only auto tool_choice is supported+5GPT-6 Solmax×6.8-9%$1.04GPT-6 Lunalow×3.1-95%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+30%-99%$0.006Context: 256K → 128KGPT-5.6 Lunalow×3-90%$0.01GPT OSS 20BhighOpen+29%-99%$0.011Context: 256K → 131K
Mistral Small 4thinkingOpen+62%-94%$0.015Memory (4-bit): 67 GB → 72 GBQwen3.8 FlashthinkingOpen×5.7-95%$0.37Memory (4-bit): 67 GB → 108 GB+6Qwen3.8 27BxhighOpen×4.8-78%$1.01max_tokens range · QwenCloud+4
Nemotron 3.5 Super VLOpen×3.8-96%$0.19Memory (4-bit): 67 GB → 75 GBTInkling SmallthinkingOpen×3.7-85%$0.089Memory (4-bit): 67 GB → 160 GB+1IK2 Horizon MoVA 36B A4BthinkingOpen×3.6-60%$1 / $4Command A+thinkingOpen+89%—$0.30 / $1.50Context: 256K → 128K+1North Mini CodeOpen+42%——Tiny Aya GlobalOpen-31%——Context: 256K → 8K+1Command R7B (12-2024)Openn/a—$0.037 / $0.15Context: 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
all categoriesFAQ
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 Qwen3 VL 4B (Reasoning)?›
On AA Intelligence Index 4.3.2, Command A scores 7 vs 7 — 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?›
Claude Sonnet 5.5 (cheaper), GPT-6 Luna (better), Qwen3.8 Flash (open weights).