Cohere

Cohere API

Access Cohere instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain AI like I'm five!", {
    model: "cohere/command-r-plus-08-2024"
}).then(response => {
    console.log(response);
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain AI like I'm five!", {
            model: "cohere/command-r-plus-08-2024"
        }).then(response => {
            console.log(response);
        });
    </script>
</body>
</html>

List of Cohere Models

Chat

Cohere: Command A

cohere/command-a

Command A is Cohere's most performant 111B parameter model with a 256K context length, excelling at tool use, RAG, agents, and multilingual tasks across 23 languages. It runs efficiently on just two GPUs while delivering 150% higher throughput than its predecessor Command R+. The model is optimized for enterprise applications including code generation, SQL, and complex reasoning tasks.

Chat

Cohere: Command R7B (12-2024)

cohere/command-r7b-12-2024

Command R7B is a compact 7B parameter model released in December 2024, designed as the smallest and fastest in the Command R family with a 128K context length. It excels at RAG, tool use, and agentic tasks while being deployable on commodity hardware with minimal latency. The model supports 23 languages and is priced for high-volume enterprise applications.

Chat

Cohere: Command R (08-2024)

cohere/command-r-08-2024

Command R 08-2024 is a 32B parameter multilingual model optimized for reasoning, summarization, and question answering with a 128K context length. It delivers 50% higher throughput and 20% lower latency than the original Command R while excelling at RAG, tool use, and code tasks. Trained on 23 languages, it features improved instruction following and Safety Modes.

Chat

Cohere: Command R+ (08-2024)

cohere/command-r-plus-08-2024

Command R+ 08-2024 is a 104B parameter flagship model with a 128K context length, optimized for complex tasks including multi-step tool use and RAG workflows. It offers roughly 50% higher throughput and 25% lower latency compared to the previous Command R+ version. Trained on 23 languages, it excels at reasoning, summarization, and sophisticated enterprise applications.

Frequently Asked Questions

What is this Cohere API about?

The Cohere API gives you access to models for AI chat. Through Puter.js, you can start using Cohere models instantly with zero setup or configuration.

Which Cohere models can I use?

Puter.js supports a variety of Cohere models, including Cohere: Command A, Cohere: Command R7B (12-2024), Cohere: Command R (08-2024), and more. Find all AI models supported by Puter.js in the AI model list.

How much does it cost?

With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.

What is Puter.js?

Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.

Does this work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Cohere API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.