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 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Nebius | US | Enterprise | No | $0.30 | $0.90 |
Training posture across routes: No training on prompts by default.
Each route hosting Nemotron 3 Super 120B A12B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Call Nemotron 3 Super 120B A12B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "nebius/nemotron-3-super-120b-a12b",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
