LLM Reference

Nemotron 3 Nano Omni

Released
2026-04-28
Last refreshed
2026-05-14
Status
Researched 31d ago
Open WeightsCommercial use allowedMultimodalLong contextVisionClassification

Nemotron 3 Nano Omni is worth evaluating for long context, vision, and classification when its provider route and context window match the workload.

Use it for

  • Teams evaluating long context, vision, and classification
  • Workloads that can use a 262k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows
Specifications
Released
2026-04-28
Context
262k
Parameters
30B
Architecture
MoE + SSM Hybrid
Specialization
audio
Openness
Open weights
License
NVIDIA Open ModelCommercial use allowed
Created by

Accelerated AI for enterprise solutions

Santa Clara, California, United States
Founded 2015
Website
Pricing
Output / 1M
Free
Input / 1M
Free

Cheapest of 1 route · OpenRouter

About

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.

Nemotron 3 Nano Omni is an open-weight model in the Nemotron 3 family. The structured metadata tracks a 262k-token context window, multimodal input, and audio. This page tracks provider routes through OpenRouter, with the cheapest tracked route listed at free input and free output per 1M tokens. Headline tracked benchmarks include MMLU PRO 71.8.

Top use-case fit

Long context

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Classification

Q/$ A

1 relevant benchmark in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
OpenRouterFreeFree
Serverless

Capabilities

MultimodalAudio

Benchmark peer barsfor Classification

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
MMLU PRO71.8https://blogs.nvidia.com/blog/nemotron-3-nano-omni/

Migration checks

No linked migration route is available for this model yet.