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-n2.5-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-n2.5-pro:free"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Nex AGI Models
Nex-N2.5-Pro
nex-agi/nex-n2.5-pro
Nex-N2.5-Pro is an agentic multimodal model from Nex AGI, the mid-size member of the Nex-N2.5 family alongside Mini and Max. It accepts text and images, supports tool calling and adjustable reasoning effort, and has a 262K context window. The model is built for agentic coding inside a visual feedback loop, exploring codebases, making multi-file changes, running commands, driving browser and desktop interfaces, and testing the result before revising. Nex AGI describes it as building on Nex-N2's multimodal foundations with improvements in computer use and web browsing. Reported scores include 82.7 on Terminal-Bench 2.1, 61.2 on SWE-Bench Pro, 82.2 on OSWorld-Verified, and 87.4 on OSWorld-G, where Nex AGI's table puts it above Claude Opus 5 (76.8) and GPT-5.6 Sol (77.7). Targeted uses are autonomous software engineering, GUI-based QA, computer-use automation, deep research, and scientific workflows. It's priced at $0.08 per million input tokens and $0.25 per million output tokens, with a free-tier variant also offered through this listing.
ChatNex-N2.5-Mini
nex-agi/nex-n2.5-mini
Nex-N2.5-Mini is the smallest model in Nex AGI's Nex-N2.5 family, a multimodal agentic line that also includes Nex-N2.5-Pro and Nex-N2.5-Max. It takes text and image input, supports function calling, and runs in three reasoning modes (non-thinking, adaptive thinking by default, and high thinking). Nex AGI targets it at computer use, web browsing, and agentic coding, where the model explores a codebase, makes multi-file edits, runs commands, and checks the result through visual feedback before continuing. On Nex AGI's own benchmark table it scores 73.4 on Terminal-Bench 2.1, 71.2 on OSWorld-Verified, and 43.8 on SWE-Bench Pro. Claude Opus 5 leads on all three in the same table (89.1, 83.4, and 79.2). It's priced at $0.03 per million input tokens and $0.10 per million output tokens, with a free-tier variant also available, giving a 262K context window for long agent loops over browser and desktop sessions.
ChatNex N2 Mini
nex-agi/nex-n2-mini
Nex N2 Mini is Nex AGI's smaller agentic model in the Nex N2 family, built on a Qwen3.5 base with 35B total parameters and 3B active per token, released open-source under Apache 2.0 alongside the larger Nex N2 Pro. It shares Nex N2 Pro's Agentic Thinking framework, pairing Adaptive Thinking, deciding on its own when and how deeply to reason, with Coherent Thinking, a consistent reasoning approach carried across general and agentic tasks. It supports a 262K context window and function calling. On benchmarks it scores 50.2 on SWE-Bench Pro, 60.7 on Terminal-Bench 2.1, 82.6 on GPQA Diamond, and 74.1 on BrowseComp, below Nex N2 Pro's 58.8, 75.3, and 90.7 on the same tests but at a fraction of the price. It fits developers who want Nex N2's agentic coding and tool-calling behavior for lighter, latency-sensitive, or budget-constrained workloads rather than maximum accuracy.
ChatNex N2 Pro
nex-agi/nex-n2-pro
Nex N2 Pro is an agentic mixture-of-experts model from Nex AGI, built on a Qwen3.5 base with 397B total parameters and 17B active per token, released open-source under Apache 2.0 in June 2026. The model's Agentic Thinking framework closes the loop between planning, code implementation, environmental feedback, and iterative debugging — making it especially capable at long-horizon tasks. It supports function calling, structured outputs, vision inputs, and reasoning traces. Benchmark highlights include 75.3 on Terminal-Bench 2.1, 80.8 on SWE-Bench Verified, and 90.7 on GPQA Diamond. It is a strong fit for developers building coding agents, deep research pipelines, or multi-step automation that demands reliable tool use and a 262K context window.
ChatDeepSeek 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
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.
Puter.js supports a variety of Nex AGI models, including Nex-N2.5-Pro, Nex-N2.5-Mini, Nex N2 Mini, and more. Find all AI models supported by Puter.js in the AI model list.
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.
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.
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.