Nex AGI

Nex AGI API

Access Nex AGI 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: "nex-agi/nex-n2-pro:free"
}).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: "nex-agi/nex-n2-pro:free"
        }).then(response => {
            console.log(response);
        });
    </script>
</body>
</html>

List of Nex AGI Models

Chat

Nex N2 Pro

nex-agi/nex-n2-pro:free

Nex N2 Pro is an open-source agentic mixture-of-experts language model from Nex AGI, post-trained on top of Qwen3.5-397B-A17B with 17B active parameters out of 397B total, released in June 2026 under an Apache 2.0 license. Built around an Agentic Thinking framework, the model unifies reasoning, tool use, and environment execution into a single closed loop — covering requirement understanding, task planning, code implementation, debugging, and iterative refinement. It supports function calling, structured outputs, and reasoning traces, and accepts both text and image inputs. Nex N2 Pro excels at coding, terminal execution, deep research, and long-horizon agentic workflows. Reported benchmarks include 75.3 on Terminal-Bench 2.1 and 90.7 on GPQA Diamond. With a 262K context window, it is a strong option for developers building agents, coding assistants, or multi-step automation pipelines.

Chat

DeepSeek V3.1 Nex N1

nex-agi/deepseek-v3.1-nex-n1

DeepSeek V3.1 Nex N1 is an agentic large language model post-trained by Nex AGI on top of DeepSeek's V3.1 base, built specifically for autonomous task execution, tool use, and multi-step workflows. It uses a 670B-parameter Mixture of Experts architecture with 37B activated parameters per token and supports a 131K context window. The model is optimized for agent-oriented use cases: function calling, web search integration, code generation, and complex planning tasks. It performs well on agentic benchmarks including SWE-bench, GAIA 2, BFCL, and Terminal-Bench, with particular strength in practical coding and HTML generation. Nex N1 is a strong pick for developers building AI agents, research assistants, or automated pipelines that need reliable tool use and multi-hop reasoning at an accessible price point.

Frequently Asked Questions

What is this Nex AGI API about?

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

Which Nex AGI models can I use?

Puter.js supports a variety of Nex AGI models, including Nex N2 Pro and DeepSeek V3.1 Nex N1. 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 Nex AGI 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.