Using Nemotron 3 Nano Omni on OpenRouter

Quick Start

1. 1
   Create an account at OpenRouter and generate an API key.
2. 2
   Use the OpenRouter SDK or REST API to call nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — see the documentation for request format.
3. 3
   You'll be billed Free/1M input, Free/1M output tokens. See full pricing.

Code Examples

About OpenRouter

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

Multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Pricing on OpenRouter

Capabilities

About Nemotron 3 Nano Omni

NVIDIA Nemotron 3 Nano Omni is an open-weight 30B hybrid MoE multimodal model (3B active parameters) that natively accepts text, image, video, and audio inputs in a single inference loop. Built on a hybrid Mamba-Transformer architecture with 23 Mamba-2 layers, 23 MoE layers (128 experts, 6+1 active), and 6 GQA layers, plus Conv3D video layers and Efficient Video Sampling (EVS). Delivers up to 9x higher throughput than comparable omni models. Supports a 256K context window and a 16,384 reasoning budget. Open weights, datasets, and training recipes released under a permissive license.