Command A

Frontier

Cohere · Released March 2025 · Knowledge cutoff August 2024

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

It belongs to Cohere's Command family, focused on enterprise retrieval, tool use and multilingual text.

Facts and pricing

Provider
Cohere
Context window
256K tokens
Input price
27.5 credits / 1M tokens ($2.50 raw)
Output price
110 credits / 1M tokens ($10.00 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Command A now

Ask Command A anything. Your prompt opens in the Zeplik app with this model selected.

Command A

What Command A is best for

Example prompts

Prompts that suit a frontier model like Command A:

Cohere family

ModelContextInput cr/MOutput cr/MReleased
North Mini Code (free)256K00June 2026
Command A256K27.5110March 2025
Command R7B (12-2024)128K0.411.7December 2024
Command R (08-2024)128K1.76.6August 2024
Command R+ (08-2024)128K27.5110August 2024

Frequently asked questions

What is Command A?
Command A is an AI model by Cohere. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
How much does Command A cost on Zeplik?
Input tokens cost 27.5 credits per million and output tokens 110 credits per million (1 credit = $0.10; the raw provider rates are $2.50 and $10.00 per million). New accounts start with free credits.
How long can a conversation with Command A be?
Command A has a 256K-token context window (256,000 tokens), which covers the conversation plus any documents you attach.
Does Command A support images and tools?
Command A is text-only and does not support tool calling.

Related models

North Mini Code (free)Coding

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

256K ctx0 cr/M outJune 2026
Command R7B (12-2024)General purpose

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

128K ctx1.7 cr/M outDecember 2024
Command R (08-2024)General purpose

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

128K ctx6.6 cr/M outAugust 2024
Command R+ (08-2024)Frontier

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

128K ctx110 cr/M outAugust 2024
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
Command A - Cohere AI Model | Zeplik Chat