by NVIDIAReleased 4 June 2026
Nemotron 3.5 Content Safety does not chat. You send what a user wrote, with or without a picture, and optionally the model's reply, and it answers safe or unsafe for each, names the safety categories that apply and, if you ask, explains its verdict. It covers 12 languages and keeps about 128 pages in mind. Use it to screen what goes into and out of another model, not to write anything.
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 | 66,57 DA | 66,57 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
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 LabTwo lines to welcome a shop in Oran.
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 LabTry 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-content-safety",
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_biasReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningAbout 0,10 DA per message. ↑ 66,57 DA · ↓ 66,57 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 Content Safety does not chat. You send what a user wrote, with or without a picture, and optionally the model's reply, and it answers safe or unsafe for each, names the safety categories that apply and, if you ask, explains its verdict. It covers 12 languages and keeps about 128 pages in mind. Use it to screen what goes into and out of another model, not to write anything.
Deposit dinars with your Edahabia or CIB card. Every model, Nemotron 3.5 Content Safety included, is paid from that balance. No foreign card, no conversion.
NVIDIA lists English, Arabic, German, Spanish, French, Hindi, Japanese, Thai, Dutch, Italian, Korean and Chinese. Darja is not named.
It reads text and images. Up to 131K tokens in one request, about 130 pages. It writes up to 88 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
NVIDIA. Released 4 June 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 3.5 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.
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 No.
Can call functions your code provides.
Fills your JSON No.
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats No.
A prompt it saw a moment ago costs less the second time.
Open weights
The model's weights are public.
Check each user message before it reaches your chatbot
Check a model reply before it is shown to the user
Screen uploaded images against your content policy
Images