Nemotron 3 Super 120B is NVIDIA's flagship open-weight reasoning model, with 120B total parameters and only 12B active per token through a hybrid Latent Mixture-of-Experts (LatentMoE) architecture. Combined with Multi-Token Prediction layers, it offers up to 1 million token context and configurable reasoning modes for advanced problem-solving. Pre-trained on tens of trillions of tokens of code, math, science, and general knowledge, the model shows strong reasoning (around 90% on AIME 2025), code (around 81% on LiveCodeBench), and agentic performance (around 60% on SWE-Bench Verified), with competitive results across knowledge benchmarks. NVIDIA reports it matches or exceeds comparable open models in its size class. Designed for high-volume agent workloads such as IT ticket automation, multi-turn reasoning, retrieval-augmented generation at scale, and tool-calling architectures, the Super model targets enterprise deployments. A quantized NVFP4 variant is available alongside the full-precision build.
Nemotron 3 Super 120B 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 |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.09 | $0.50 |
Training posture across routes: No training on prompts by default.
Each route hosting Nemotron 3 Super 120B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper 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; SCCs; DPA available.
Call Nemotron 3 Super 120B 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: "geodd:us/nemotron-3-super",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
