opendunes

Nemotron 3 Nano 30B A3B

by NVIDIAReleased 14 December 2025

Nemotron 3 Nano 30B A3B reads text and writes text back, keeping about 256 pages in mind, with thinking you can turn on or off and the ability to use the tools you connect. It was released openly, with its training data and recipes, and is built for developers assembling specialised assistants, chatbots and systems that answer from your own documents.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,060 DA per message3 000 DA buys about 50 000 messages

One message, the ordinary use

1 000 tokens sent× 19,97 DA per 1M0,020 DA
500 tokens back× 79,88 DA per 1M0,040 DA
Total≈ 0,060 DA

Every rate

Meter↑ you send↓ comes back
Text tokens19,97 DA79,88 DA
Cached tokens read3,99 DA

per 1M tokens

Answer a quick question≈ 0,023 DA
Reply to a customer email≈ 0,044 DA
Classify 20 support tickets by topic≈ 0,056 DA
Translate a full page of text≈ 0,078 DA
Explain a stack trace and suggest a fix≈ 0,078 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Nebius…
↑ Sent, per 1M
19,97 DA
↓ Back, per 1M
79,88 DA
Cache read
3,99 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Nebius19,97 DA79,88 DA3,99 DA………

You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
nvidia/nemotron-3-nano-30b-a3b
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="nvidia/nemotron-3-nano-30b-a3b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Questions about Nemotron 3 Nano 30B A3B

  • How much does Nemotron 3 Nano 30B A3B cost in dinars?

    About 0,060 DA per message. ↑ 19,97 DA · ↓ 79,88 DA per 1M tokens.

  • Is Nemotron 3 Nano 30B A3B free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Nemotron 3 Nano 30B A3B best for?

    Nemotron 3 Nano 30B A3B reads text and writes text back, keeping about 256 pages in mind, with thinking you can turn on or off and the ability to use the tools you connect. It was released openly, with its training data and recipes, and is built for developers assembling specialised assistants, chatbots and systems that answer from your own documents.

  • Nemotron 3 Nano 30B A3B or Nemotron 3 Ultra?

    Nemotron 3 Ultra costs 0,54 DA more for the same message.

  • How do I pay for Nemotron 3 Nano 30B A3B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Nemotron 3 Nano 30B A3B included, is paid from that balance. No foreign card, no conversion.

  • Does Nemotron 3 Nano 30B A3B work in Arabic, French or Darja?

    NVIDIA lists English, German, Spanish, French, Italian and Japanese. Arabic is in the training data but not in the supported list. Darja is not named.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 262K tokens in one request, about 260 pages. It writes up to 177 000 words at once.

  • Is Nemotron 3 Nano 30B A3B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Nemotron 3 Nano 30B A3B, and when was it released?

    NVIDIA. Released 14 December 2025. It knows the world up to June 2025.

Other NVIDIA models, priced in dinars

See all NVIDIA models
Nemotron 3.5 ASR Streaming Multilingual 0.6BNVIDIA · Aug 13, 2026

Nemotron 3.5 ASR Streaming Multilingual 0.6B takes audio and writes out what is said, built to respond quickly in over 40 languages. It suits live work such as real-time captions and voice assistants, or pipelines that transcribe several languages, where text should appear while the speaker is still talking.

0,067 DAper minute of audio
View model
Nemotron 3.5 TranscribeNVIDIA · Oct 29, 2026

This model is designed to listen to audio recordings and convert the spoken words into written text. It excels at the task of accurately transcribing spoken content from various sources. A key feature is its ability to handle speech in 40 different languages. This model is strictly for speech recognition and cannot perform other general language or visual tasks.

0,67 DAper minute of audio
View model
Parakeet TDT 0.6B v3NVIDIA · May 27, 2026

NVIDIA's 600M multilingual speech recogniser trained on over 670,000 hours, detecting every official EU language by itself and returning punctuated text with segment timestamps at a 6.34% average word error rate

0,50 DAper minute of audio
View model
Nemotron 3.5 Super VLNVIDIA · Oct 15, 2026

Nemotron 3.5 Super VL reads text, pictures, documents, screenshots of app screens and video, and writes text back, taking in about a thousand pages at once. It is made for assistants that look at a screen or a document, then think and use the tools you connect. It thinks unless you switch that off, and you can limit how much effort it spends thinking. Nemotron 3 Super is the text-only model of the same size.

Thinks firstUses your tools1 000 pages at once
≈0,13 DAper message
View model