Hormouz AIHormouzSign in

NVIDIA: Nemotron 3 Nano Omni (free): AI model

NVIDIA's Nemotron 3 Nano Omni is a 30B-A3B multimodal model that takes text, image, video and audio input and produces text, with a 256K-token context and a reasoning mode. Free, reachable from inside Iran through Hormouz.

Context window:
256,000 tokens
Pricing:
$0.00/M in · $0.00/M out
Type:
text, audio, image, video
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Nemotron 3 Nano Omni is an open multimodal Mixture-of-Experts model (30B-A3B) from NVIDIA, designed to act as a perception-and-context sub-agent inside enterprise agent systems. It accepts text, image, video and audio inputs and produces text output, letting agents perceive and reason across modalities in a single inference loop.

It is built on a hybrid Transformer-Mamba architecture with 3D video layers and efficient video sampling, giving it higher throughput and lower compute cost for video reasoning than running separate vision and speech pipelines. It supports a toggleable reasoning mode, and through Hormouz it is served behind an OpenAI-compatible API. Point your base URL at Hormouz and drop in a Hormouz key. This is the free tier.

Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

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...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorNVIDIA
TypeText, Audio, Image, Video
Context window256,000 tokens
Pricing$0.00/M in · $0.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
46.9%
HLE
Humanity's Last Exam
5.3%
IFBench
Instruction-following
63.2%
AA-LCR
Long-context reasoning
35.7%
CritPt
Research-level physics reasoning
0%

Coding

SciCode
Python for scientific computing
27.8%
Terminal-Bench Hard
Agentic coding & terminal use
8.3%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
45.3%

Source: Artificial Analysis

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the NVIDIA: Nemotron 3 Nano Omni (free) API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches NVIDIA: Nemotron 3 Nano Omni (free) and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Nemotron 3 Nano Omni cost?
This is the free tier. Suited to testing and prototyping, and may be rate-limited.
How do I access Nemotron 3 Nano Omni from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Nemotron 3 Nano Omni compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window does Nemotron 3 Nano Omni have?
The model supports a context window of up to 256K tokens, which fits long documents and large multimodal inputs.
What are the capabilities of Nemotron 3 Nano Omni?
It accepts multimodal input (text, image, video and audio) and produces text output; it also supports tool calling and a reasoning mode.
What is Nemotron 3 Nano Omni good for?
It works well as a perception sub-agent for agent systems. Especially video understanding, multimodal document analysis and applications that must process several input types at once.

Updated 2026-10-13