Nemotron 3 Nano Omni 30B A3B Reasoning is NVIDIA's efficient multimodal reasoning model, combining text, image, video, and audio understanding with explicit chain-of-thought processing. The 30B-parameter architecture (about 3B active per token) uses a hybrid Mamba-Transformer MoE with a configurable reasoning mode for multi-step problem-solving at high throughput. Built on the Nemotron 3 Nano 30B-A3B backbone and augmented with a C-RADIO vision encoder and a Parakeet audio encoder, it performs document reasoning, computer-use automation, video analysis with temporal understanding, and audio transcription. It supports up to 256K token context, processing video, long audio, and multiple document images. Optimized for enterprise agents that interact with complex visual environments, the model suits IT automation, financial document analysis, content summarization, and screen-based task execution. It is available in BF16, FP8, and NVFP4 for flexible deployment.
Nemotron 3 Nano Omni 30B A3B Reasoning 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 | Enterprise | No | $0.20 | $0.80 |
Training posture across routes: No training on prompts by default.
Each route hosting Nemotron 3 Nano Omni 30B A3B Reasoning 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; unknown.
Call Nemotron 3 Nano Omni 30B A3B Reasoning 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.click/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
