NVIDIA
Nemotron 3 Nano Omni
Open Nemotron omni model combining reasoning with text, vision, and audio
Model facts
- Context window
- 256K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $0.059 per 1M tokens
- Cheapest paid output
- $0.237 per 1M tokens
- Open weights
- yes
- Providers
- 7
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, audio, video.
Observed price history
- 2026-08-24: $0.054 input / $0.216 output per 1M tokens
- 2026-08-28: $0.059 input / $0.237 output per 1M tokens
API providers
- Nvidia — model id nvidia/nemotron-3-nano-omni-30b-a3b-reasoning; free input / free output per 1M tokens; provider documentation
- OpenRouter (free) — model id nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free; free input / free output per 1M tokens; provider documentation
- Cortecs — model id nvidia-nemotron-3-nano-omni; $0.059 input / $0.237 output per 1M tokens; provider documentation
- Requesty — model id nemotron-3-nano-omni; $0.06 input / $0.24 output per 1M tokens; provider documentation
- Vultr (NVIDIA) — model id nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16; $0.13 input / $0.38 output per 1M tokens; provider documentation
- NanoGPT (Nvidia) — model id nvidia/nemotron-3-nano-omni-30b-a3b-reasoning; $0.105 input / $0.42 output per 1M tokens; provider documentation
- DigitalOcean — model id nemotron-3-nano-omni; $0.5 input / $0.9 output per 1M tokens; provider documentation