Command A
Command AAlternatives?
CheaperGemini 4 Argonunstated+11%-9%*$2 / $10Synchronous output stops at 65,536+2
BetterClaude Sonnet 4.5thinking+5%+37%$0.56
OpenMiniMax M2.7unstated+5%-88%$0.30 / $1.20Context: 256K → 205K+1CheaperGemini 3.8 Flashunstated+9%-66%*$0.75 / $3.75Sampling parameters are ignored+1CheaperGemini 3 Flash Previewunstated+9%-74%$0.50 / $3Gemini 4 Argonunstated+11%-9%*$2 / $10Synchronous output stops at 65,536+2Gemini 3.8 Flashunstated+9%-66%*$0.75 / $3.75Sampling parameters are ignored+1Gemini 3 Flash Previewunstated+9%-74%$0.50 / $3Gemini 3.6 Flashunstated+9%-66%*$0.75 / $3.75
Grok 4.6unstated+8%-31%$2 / $6Claude Sonnet 4.5thinking+5%+37%$0.56Claude Fable 5unstated+11%+357%$10 / $50Claude Fable 5.1unstated+11%+357%$10 / $50Replace forced tool_choice+5Gemini 4 Argonunstated+11%-9%*$2 / $10Synchronous output stops at 65,536+2Gemini 3.1 Pro Previewunstated+10%same$2 / $12Cannot use both thinking controlsMiniMax M2.7unstatedOpen+5%-88%$0.30 / $1.20Context: 256K → 205K+1TInkling SmallunstatedOpen+4%-85%$0.45 / $1.20Memory (4-bit): 67 GB → 160 GB+1
Qwen3.8 27BunstatedOpen+3%-78%$0.42 / $2.55max_tokens range · QwenCloud+4MiniMax M2.5unstatedOpensame-88%$0.30 / $1.20Context: 256K → 205K+1
Ling 3.0 FlashunstatedOpensame-98%$0.06 / $0.18Memory (4-bit): 67 GB → 76 GBCommand R+Open-14%——Context: 256K → 128KCommand A+unstatedOpen-23%—$0.30 / $1.50Context: 256K → 128K+1Command ROpen-59%——Context: 256K → 128KNorth Mini CodeOpenn/a——Tiny Aya GlobalOpenn/a——Context: 256K → 8K+1Command R (08-2024)unstatedOpenn/a—$0.15 / $0.60Context: 256K → 128K+1Command R+ (08-2024)unstatedOpenn/a—$2.50 / $10Context: 256K → 128K+1All 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?›
#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 MiniMax M2.5?›
On Vals LegalBench, Command A scores 79.7 vs 80 — 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), Claude Sonnet 4.5 (better), MiniMax M2.7 (open weights).