# Nemotron 3 Nano Omni (free)

> Nemotron 3 Nano Omni (free) is an open-weight language model from NVIDIA, released on 28 Apr 2026. It accepts text, images, video and audio and generates text, with a 256K-token context window and up to 66K output tokens per response.

Source page: https://www.aimodel.directory/models/nemotron-3-nano-omni-30b-a3b-reasoning
Last verified: 4 Oct 2026

## Specifications

- **Developer:** NVIDIA
- **Release date:** 28 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Context window:** 256K (256,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Input:** Text, images, video and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | 256K |

## FAQ

### What is the context window of Nemotron 3 Nano Omni (free)?

Nemotron 3 Nano Omni (free) has a context window of 256,000 tokens (256K) and can generate up to 65,536 tokens in a single response, according to models.dev.

### Is Nemotron 3 Nano Omni (free) open source?

Nemotron 3 Nano Omni (free) is an open-weight model. Check the license terms before commercial use.

### When was Nemotron 3 Nano Omni (free) released?

NVIDIA released Nemotron 3 Nano Omni (free) on 28 Apr 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Nemotron 3 Nano Omni (free)", https://www.aimodel.directory/models/nemotron-3-nano-omni-30b-a3b-reasoning