opendunes

Nemotron 3 Ultra

by NVIDIAReleased 4 June 2026

Nemotron 3 Ultra reads text and writes text back, thinks before it answers and can use the tools you connect. It is the biggest member of its family, meant for long-running assistant work such as coordinating other assistants, running coding assistants and deep research, where planning over many steps matters.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 0,60 DA per message3 000 DA buys about 5 000 messages

One message, the ordinary use

1 000 tokens sent× 199,70 DA per 1M0,20 DA
500 tokens back× 798,81 DA per 1M0,40 DA
Total≈ 0,60 DA

Every rate

Meter↑ you send↓ comes back
Text tokens199,70 DA798,81 DA
Cached tokens read39,94 DA

per 1M tokens

Answer a quick question≈ 0,23 DA
Reply to a customer email≈ 0,44 DA
Translate a full page of text≈ 0,78 DA
Review a 300-line pull request≈ 1,52 DA
Summarise a 20-page report≈ 2,96 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

Three companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

DeepInfraUnited States…
↑ Sent, per 1M
166,42 DA
↓ Back, per 1M
732,24 DA
Cache read
33,28 DA
Latency
…
Throughput
…
BaseTenUnited States…
↑ Sent, per 1M
199,70 DA
↓ Back, per 1M
798,81 DA
Cache read
39,94 DA
Latency
…
Throughput
…
BaseTen…
↑ Sent, per 1M
199,70 DA
↓ Back, per 1M
798,81 DA
Cache read
39,94 DA
Latency
…
Throughput
…
VeniceUnited States…
↑ Sent, per 1M
208,02 DA
↓ Back, per 1M
1 040,11 DA
Cache read
62,41 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
DeepInfraUnited States166,42 DA732,24 DA33,28 DA………
BaseTenUnited States199,70 DA798,81 DA39,94 DA………
BaseTen199,70 DA798,81 DA39,94 DA………
VeniceUnited States208,02 DA1 040,11 DA62,41 DA………

You pay the price of the provider that served your request. Prices read 15:21 · 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-ultra-550b-a55b
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-ultra-550b-a55b",
    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_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_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 Ultra

  • How much does Nemotron 3 Ultra cost in dinars?

    About 0,60 DA per message. ↑ 199,70 DA · ↓ 798,81 DA per 1M tokens.

  • Is Nemotron 3 Ultra 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 Ultra best for?

    Nemotron 3 Ultra reads text and writes text back, thinks before it answers and can use the tools you connect. It is the biggest member of its family, meant for long-running assistant work such as coordinating other assistants, running coding assistants and deep research, where planning over many steps matters.

  • Nemotron 3 Ultra or Nemotron 3 Super?

    Nemotron 3 Super costs 0,51 DA less for the same message.

  • How do I pay for Nemotron 3 Ultra without an international card?

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

  • Does Nemotron 3 Ultra work in Arabic, French or Darja?

    NVIDIA lists English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese and Chinese. Arabic appears in the card's language tags but not in that 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 137 000 words at once.

  • Is Nemotron 3 Ultra open source?

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

  • Who makes Nemotron 3 Ultra, and when was it released?

    NVIDIA. Released 4 June 2026. It knows the world up to September 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