Nemotron 3 Nano Omni (free)
About this model
Nemotron 3 Nano Omni (free) is an AI model from NVIDIA, made available through the API on April 28, 2026. It can read up to 256,000 tokens in one request, roughly 480 pages of text, and write up to 65,536 tokens in a single answer. Besides text, it accepts audio, images and video as input.
It is currently offered for free through public APIs.
It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →Not rated yet. Independent test results usually appear a few weeks after a model is released.
Where to use it
No provider data yet.
Use it in your code
Call Nemotron 3 Nano Omni (free) through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0
- Summarise a 100-page document$0
- An app with 10,000 requests a day for a month$0
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
Ling 3.0 Flash Sante (free)inclusionAI (Ant Group) | Free | Free | 256K | Compare with ⇄ |
Dots3-Note Preview (free)Dots Studio | Free | Free | 512K | Compare with ⇄ |
LFM2.5-2.6B (free)Liquid AI | Free | Free | 64K | Compare with ⇄ |
North Mini Code (free)Cohere | Free | Free | 256K | Compare with ⇄ |
DeepSeek V4 Flash 0731DeepSeek | $0.018 | $0.32 | 1M | Compare with ⇄ |
| $0.017 | $0.11 | 131K | Compare with ⇄ |
News about NVIDIA
See all →Frequently asked questions
- How much does Nemotron 3 Nano Omni (free) cost?
- Nemotron 3 Nano Omni (free) is currently offered for free through public APIs, usually with usage limits. Free offers change often, so check the provider’s terms.
- What is the context window of Nemotron 3 Nano Omni (free)?
- Nemotron 3 Nano Omni (free) can read up to 256,000 tokens in one request, about 480 pages of text. It can write up to 65,536 tokens in a single answer.
- Is Nemotron 3 Nano Omni (free) open source?
- Yes. Its weights are published (nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16), so you can download it and run it on your own hardware, or use it through one of 1 API providers.
- Who makes Nemotron 3 Nano Omni (free)?
- Nemotron 3 Nano Omni (free) is made by NVIDIA. It became available through the API on April 28, 2026.
- Can Nemotron 3 Nano Omni (free) read images?
- Yes. Besides text, it accepts audio, images and video as input.
- What are the alternatives to Nemotron 3 Nano Omni (free)?
- Models with a similar price from other companies include Ling 3.0 Flash Sante (free), Dots3-Note Preview (free) and LFM2.5-2.6B (free). You can compare them side by side on this page.