NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
- Modalities
- text + audio + image + video → text
- In / out per 1M
- Free / Free
- Context
- 256K tokens
- Added
- Apr 28, 2026
- Max output
- 66K tokens
- Tokenizer
- Other
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
One company serves Nemotron 3 Nano Omni (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.
| Provider | Context | Input /M | Output /M |
|---|---|---|---|
| Nvidia | 256K | Free | Free |
Provider list from the OpenRouter catalog, Jul 28, 2026. All providers
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- seed
- temperature
- tool_choice
- tools
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Nemotron 3 Nano Omni (free)
Nemotron 3 Nano Omni is NVIDIA's 30B-A3B mixture-of-experts model built to sit inside enterprise agent pipelines as a perception layer rather than a standalone chat model. It reads text, image, audio, and video and outputs text, with a 256,000-token context window and up to 65,536 completion tokens per response. Reasoning is supported but optional — you can turn it on per request rather than being forced into it. No benchmark scores are published for this release, so treat capability claims as unverified until you test against your own workload.
This is a free model (both prompt and completion priced at $0.00) in a lab lineup where siblings like Nemotron 3 Ultra run up to $0.50 input / $2.20 output per 1M tokens. Its 256K context window is larger than 52% of catalog models, and it's one of four input modalities (text, image, audio, video) feeding into a single text output — unusual breadth for a 30B-class model. Reasoning is on by default but can be disabled, which most fixed-reasoning models don't allow.
Questions
- How much does Nemotron 3 Nano Omni (free) cost via API?
- It's free — $0.00 per 1M input tokens and $0.00 per 1M output tokens from NVIDIA, and OpenKey's 3% fee on $0.00 is still $0.00. There's no cost calculation to do here; you pay nothing per token whether you access it directly or through OpenKey.
- What is Nemotron 3 Nano Omni's context window?
- It supports 256,000 tokens of context, with a separate cap of 65,536 tokens on completion output. That's enough to hold a large codebase, hours of transcribed audio, or several hundred pages of documents in a single request alongside image or video inputs.
- Does Nemotron 3 Nano Omni support tool calling and multimodal input?
- Yes — it supports tool calling (tool_choice, tools) and takes text, audio, image, and video as input, outputting text only. It also exposes reasoning as an optional parameter (default on) and supports include_reasoning, seed, temperature, and top_p for controlling generation.
- Is Nemotron 3 Nano Omni (free) actually free, or is there a catch via OpenKey?
- Yes, it's genuinely free — provider pricing is $0.00/1M tokens for both input and output, and OpenKey's flat 3% fee applies to that $0.00 base, so your bill stays $0.00. It's one of 25 free models on OpenKey's catalog of 329 models across 52 labs.
- How does Nemotron 3 Nano Omni (free) compare to Nemotron 3 Nano 30B A3B?
- They share the same 30B-A3B architecture, but the non-free Nemotron 3 Nano 30B A3B costs $0.05 per 1M input tokens and $0.20 per 1M output tokens, while the Omni variant is $0.00/$0.00. The Omni version also adds audio and video input on top of text and image, which the base Nano model may not support.
More from NVIDIA
All NVIDIA models →
NVIDIANemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
ctx 1M in $0.515 out $2.27
NVIDIAFreeNemotron 3 Ultra (free)
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
ctx 1M in Free out Free
NVIDIAFreeNemotron 3.5 Content Safety (free)
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
ctx 128K in Free out Free
NVIDIANemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
ctx 1M in $0.088 out $0.412