by NVIDIAReleased 15 October 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.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 49,93 DA | 166,42 DA |
| Cached tokens read | 6,66 DA |
per 1M tokens
Ten 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.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Darkbloom | 19,97 DA | 116,49 DA | 3,33 DA | … | … | … |
| Crusoe | 33,28 DA | 133,13 DA | 26,63 DA | … | … | … |
| PrimeIntellect | 49,93 DA | 166,42 DA | 6,66 DA | … | … | … |
| Io Net | 49,93 DA | 166,42 DA | 6,66 DA | … | … | … |
| Together | 49,93 DA | 166,42 DA | 6,66 DA | … | … | … |
| DeepInfraUnited States | 49,93 DA | 166,42 DA | 6,66 DA | … | … | … |
| CoreWeaveUnited States | 49,93 DA | 166,42 DA | 6,66 DA | … | … | … |
| VeniceUnited States | 66,57 DA | 166,42 DA | 13,31 DA | … | … | … |
| BaseTen | 66,57 DA | 166,42 DA | 13,31 DA | … | … | … |
| Nebius | 99,85 DA | 299,55 DA | 19,97 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.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
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-3.5-super-vl",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
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_biaslogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceAbout 0,13 DA per message. ↑ 49,93 DA · ↓ 166,42 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
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.
Deposit dinars with your Edahabia or CIB card. Every model, Nemotron 3.5 Super VL included, is paid from that balance. No foreign card, no conversion.
NVIDIA names no languages for Nemotron 3.5 Super VL. Arabic, French and Darja: not stated.
It reads text, images and video. Up to 1M tokens in one request, about 1 000 pages. It writes up to 708 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
NVIDIA. Released 15 October 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.
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.
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
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.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights
The model's weights are public.
Watch a long video and answer questions about it, thinking step by step first
Thinks first
Turn GUI screenshots and scanned documents into structured JSON your apps can use
Fills your JSON
Drive agents that pick and call tools across mixed image and video evidence
Uses your tools