Cohere: Command A
cohere/command-a
Try Command A for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "cohere/command-a"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "cohere/command-a"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Command A is Cohere's flagship enterprise language model with 111 billion parameters and a 256K token context window, released in March 2025.
Built for complex agentic workflows, it leads on tool-use benchmarks including BFCL-v3 and Tau-bench, and performs on par with GPT-4o on MMLU and SQL tasks. It is particularly strong at multi-step tool calling — including knowing when not to invoke a tool, a critical quality for production agents.
Supporting 23 languages with 150% higher throughput than Command R+, it's a strong choice for developers building RAG pipelines, autonomous agents, or multilingual enterprise applications.
Context Window 256K
tokens
Max Output 8K
tokens
Input Cost $2.5
per million tokens
Output Cost $10
per million tokens
Input text
modalities
Tool Use No
Release Date Mar 13, 2025
Output Speed 59
tokens / sec
Latency 0.38s
time to first token
Try Command A for free
Try Command A instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Command A performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 52.7% |
| Humanity's Last Exam Cross-domain reasoning | 4.0% |
| LiveCodeBench Recent coding problems | 28.7% |
| MATH-500 Competition math | 81.9% |
| AIME 2024 Advanced math exam | 9.7% |
| AIME 2025 Advanced math exam | 13.0% |
| IFBench Instruction following | 36.5% |
| LCR Long-context reasoning | 21.3% |
| Terminal-Bench Hard Agentic terminal tasks | 0.8% |
| τ²-Bench Tool use / agents | 15.2% |
Scores sourced from Artificial Analysis.
Find other Cohere models →
Command A+
Command A+ is Cohere's newest flagship model, a sparse mixture-of-experts architecture with 218 billion total parameters and 25 billion active per token, released in 2026 as a successor to Command A. It extends language coverage from 23 to 48 languages, including all official EU languages, and adds image understanding alongside text, complex reasoning, and agentic tool use in a single model. Cohere reports higher scores on agentic benchmarks compared to its own Command A Reasoning model, including 85% on Tau2-Bench Telecom (up from 37%) and 25% on Terminal-Bench Hard (up from 3%), plus a score of 37 on the Artificial Analysis Intelligence Index. With a 192,000 token context window and 64,000 token max output, it suits developers building multilingual enterprise assistants, RAG pipelines, and multi-step tool-calling agents who need reasoning, vision, and tool use in one model.
ChatNorth Mini Code
Cohere North Mini Code is an open-weight agentic coding model from Cohere Labs, built on a sparse Mixture-of-Experts architecture with 30B total parameters and 3B active per token. It is optimized for code generation, agentic software engineering workflows — including sub-agent orchestration, multi-file analysis, and code review — and real terminal tasks. On the Artificial Analysis Coding Index it scores 33.4, outperforming open-source models up to 4x its size. It delivers 2.8x higher throughput and 30% lower inter-token latency than Devstral Small 2. With a 256K context window and 64K max output, it suits developers building AI coding agents or automated engineering pipelines. Released under Apache 2.0.
ChatCommand A (03-2025)
Command A (03-2025) is Cohere's flagship enterprise chat model, built for tool use, retrieval-augmented generation, and agentic workflows across a 256K token context window. Cohere reports it performs on par with or better than GPT-4o and DeepSeek-V3 on agentic enterprise tasks. In Cohere's human evaluations against GPT-4o (November version), it reached win rates of 50.4% on general prompts, 51.4% on business tasks, and 49.6% on code. Cohere also measured serving speeds of up to 156 tokens per second, about 1.75x what it measured for GPT-4o. It supports 23 languages and produces citation-backed answers in RAG settings, which makes it a fit for enterprise assistants, multilingual applications, and multi-step agents that call external tools.
Frequently Asked Questions
You can access Command A by Cohere through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Command A is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Command A is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $2.5 |
| Output | $10 |
Command A was created by Cohere and released on Mar 13, 2025.
Command A supports a context window of 256K tokens. For reference, that is roughly equivalent to 512 pages of text.
Command A can generate up to 8K tokens in a single response.
Command A accepts the following input types: text. It produces: text.
No, Command A does not currently support tool use (function calling).
Command A scores 7.0 on the Artificial Analysis Intelligence Index, outperforming 22% of tracked models. On math, it scores 13.0 (outperforms 15% of models).
Yes — the Command A API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Command A to your app for free
Developers can integrate Command A for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.