Nemotron 3 Nano Omni
- Family
- Nemotron 3
- Released
- 2026-04-28
- Context
- 256K
- Parameters
- 30B
- Architecture
- MoE + SSM Hybrid
- Specialization
- audio
- Openness
- Open weights
- License
- NVIDIA Open ModelPermitted
- Weights
- Available
- Code
- Unknown
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.
Top use-case fit
Classification
Q/$ AProviders(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | Free | Free | Serverless |
Capabilities
Benchmark peer barsfor Classification
Benchmark scores(1)
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Compare Nemotron 3 Nano Omni with other models
- Nemotron 3 Nano Omni vs Gemma 3221
- Nemotron 3 Nano Omni vs Hunyuan Hy3 Preview12
- Nemotron 3 Nano Omni vs Together AI - Gemma 3n-e4B10
- Nemotron 3 Nano Omni vs Claude Instant 1.17
- Nemotron 3 Nano Omni vs Claude Instant6
- Nemotron 3 Nano Omni vs Gemma 3n 2B (free)5
- Nemotron 3 Nano Omni vs Doubao Pro 256K4
- Nemotron 3 Nano Omni vs Gemma 3 12B2
Comparison and alternatives
Browse all comparisons →Cheapest of 1 route · OpenRouter