Nemotron 3 Super 120B A12B is the A12B build of NVIDIA's flagship reasoning model, with 120B parameters, 12B active per token, and a 262K token context for extended multi-turn agentic workflows. The hybrid Mamba-Transformer LatentMoE architecture with Multi-Token Prediction layers provides both efficient inference and native speculative decoding. Pre-trained on tens of trillions of tokens across code, math, and science, the model is built for collaborative multi-agent coordination, complex reasoning chains, and high-throughput tool-calling. NVIDIA reports accuracy comparable to or better than similarly sized open models across reasoning, code, and agent benchmarks. The A12B build is aimed at enterprises deploying collaborative agents, where one reasoning agent coordinates several specialists, along with knowledge-work automation and long-running reasoning pipelines. It is ready for commercial use and available in BF16 precision.
Nemotron 3 Super 120B A12B runs on 4 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.09 | $0.40 | |
| US | Not by default | No | $0.30 | $0.65 | |
| US | Zero data retention | No | $0.09 | $0.50 | |
| US | Not by default | No | $0.30 | $0.90 |
Nemotron 3 Super 120B A12B runs on 2 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes for this model are not on the board yet and are not counted above. See uptime for every provider qynio monitors.
Each route hosting Nemotron 3 Super 120B A12B has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; deposit available.
Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; deposit available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; wallets; deposit available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. US; wallets; deposit available.
Call Nemotron 3 Super 120B A12B through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
