Command A is a 111-billion-parameter dense transformer model developed by Cohere, tailored for enterprise AI applications. It excels in agentic workflows, retrieval-augmented generation (RAG), and multilingual tasks, delivering precise, data-grounded insights across 23 languages. Command A is optimized for efficiency and professional use cases such as coding, automation, and conversational intelligence.
Command A leverages a dense transformer architecture optimized for tool integration and RAG workflows. It supports a broad multilingual spectrum covering 23 languages including Arabic, Chinese (Simplified and Traditional), Russian, and Vietnamese. The model runs efficiently on two A100/H100 GPUs, achieving 150% higher throughput than its predecessor.
Based on Cohere’s reported metrics:
These metrics highlight strong reasoning (MMLU, IFEval), mathematical problem-solving (MATH), and moderate coding accuracy and business function calling capabilities (Taubench, BFCL). Command A supports a 256K token context window for extended document and workflow handling.
Command A demonstrates solid performance in enterprise AI benchmarks, achieving 85.5% on MMLU for reasoning, 63.8% on BFCL for business function calling, and 51.7% on Taubench for coding accuracy, indicating moderate performance in SQL and code translation. It scores 80.0% on MATH and 90.0% on IFEval, reflecting strong reasoning and instruction-following capabilities. Users note effective multilingual support across 23 languages and reliable RAG for data-grounded insights.
Accessible via AI/ML API. Documentation: available here.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Enterprise-grade coding assistants
Generate accurate SQL queries and translate code (e.g., Python to JavaScript). Ideal for automating internal tools, analytics scripts, and enterprise workflows.
Retrieval-Augmented Generation (RAG)
Deliver grounded insights using retrieval-based inputs from databases or documents. Suitable for financial analysis, compliance audits, and internal knowledge search.
Multilingual task automation
Translate and summarize across 23 languages to support global teams. Used in customer support automation, HR localization, and multi-language document workflows.
Agentic AI systems
Automate structured business processes by integrating tool-calling capabilities. Useful for invoice processing, CRM updates, and scheduling tasks via natural language.
Conversational intelligence
Deploy chatbots and copilots that handle large contexts (up to 256K tokens). Power enterprise Q&A systems, onboarding flows, or document-driven assistants.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "cohere/command-a", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "cohere/command-a", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"cohere/command-a","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| GPQA Diamond | 52.7% | Google-proof graduate science questions (hardest subset) | Source | July 8, 2026 |
| MMLU-Pro | 71.2% | Multi-discipline knowledge + reasoning (harder MMLU) | Source | July 8, 2026 |
| Intelligence | 13.9 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 27.8 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Command A This page | Coding + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Command A has a 256,000 tokens context window and can return up to 256,000 tokens.
Command A takes text as input and returns text.
Use cohere/command-a as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Command A became available on September 9, 2025.
Command A is priced at input $3.4385 / 1M tokens, output $13.754 / 1M tokens.
Yes, Command A can stream responses as they are generated.
Command A was built by Cohere.
Yes, Command A supports function calling and tool use, including parallel tool calls.
