When was Nemotron 3.5 Super VL released?

NVIDIA released Nemotron 3.5 Super VL on 15 Oct 2026. It is available through the Opper gateway.

Does Nemotron 3.5 Super VL support zero data retention?

Yes. Nemotron 3.5 Super VL is available with zero data retention on DeepInfra, Jarvislabs through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is Nemotron 3.5 Super VL hosted?

Nemotron 3.5 Super VL runs on US hosting routes through the Opper gateway.

Is Nemotron 3.5 Super VL trained on prompts and outputs?

No. Every hosting route for Nemotron 3.5 Super VL is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Nemotron 3.5 Super VL?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Nemotron 3.5 Super VL. Contact hello@opper.ai to receive it.

Nemotron 3.5 Super VL

by NVIDIA

Released 65 days after Nemotron 3.5 Lightning 30B A3B · Announcement · All NVIDIA releases

Nemotron 3.5 Super VL is the vision-language model of NVIDIA's Nemotron 3.5 family, released on October 15, 2026. It interleaves Mamba-2, mixture-of-experts and attention layers, with 120B total and 12B active parameters, and adds a C-RADIO vision encoder and a vision-language connector so the language backbone can read images, document pages and sampled video frames (MP4 clips of up to two minutes). NVIDIA trained it for agents that see, reason and act: tool calling, coding, document understanding and video understanding, with a context of up to 1M tokens that the prompt, visual inputs, conversation history and response share. Reasoning is configurable: off, on at medium effort, or fully on, and a multi-token prediction head enables native speculative decoding. NVIDIA publishes BF16 and NVFP4 weights under the OpenMDW-1.1 license, together with a technical report covering Nemotron 3.5 Super VL and Lightning.

Call Nemotron 3.5 Super VL on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

—

Input price

$0.10 /1M$0.08 cache read

Output price

$0.40 /1M

Released

15 Oct 2026

Web search

Via Opper

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Nemotron 3.5 Super VL runs on 5 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Training	Input	Output	Cache read
DeepInfra	US	No	$0.10	$0.40	$0.08
DigitalOcean	US	No	$0.30	$0.65	$0.06
Jarvislabs	India	No	$0.15	$0.50	$0.02
Nebius	Multi	No	$0.30	$0.90	Input price
Perplexity	Multi	No	$0.20	$0.50	$0.04

Live routes and prices as JSON: api.opper.ai/v3/models?q=nemotron-3.5-super-vl

Uptime and availability

Nemotron 3.5 Super VL runs on 3 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 96.23% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

3 monitored providers serve Nemotron 3.5 Super VL.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Nemotron 3.5 Super VL has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

DigitalOcean — United States🇺🇸

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. US; dpf sccs; DPA available.

Zero data retention: With abuse monitoring, flagged content held.
Training: No training on customer data.
Logging: None
Abuse monitoring: Always on, holds flagged content, stored in United States
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: dpf sccs

Jarvislabs — India🇮🇳

Zero data retention: nothing is logged or used for training. No training on customer data. IN; unknown.

Zero data retention: Yes. Nothing is logged or used for training.
Training: No training on customer data.
Logging: None
Caching: Content cached for replay
GDPR DPA: No DPA
Transfer mechanism: unknown

Nebius — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

Perplexity — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; unknown.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Caching: Content cached for replay
Transfer mechanism: unknown

Best for

Where Nemotron 3.5 Super VL ranks among the models on Opper with a score for each use case.

Healthcare21.0

Healthcare and medicalSee the Healthcare ranking →Finance26.7

Finance and accountingSee the Finance ranking →Legal25.3

Legal tasks and reasoningSee the Legal ranking →Coding3.7

FrontierCode 2.0 and Terminal-Bench 4.0See the Coding ranking →Agents7.4

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#42 of 507 LLMs

TierEfficient

Output speed398 tok/s

Intelligence Index13.6

Coding

FrontierCode 2.0

Terminal-Bench 4.0

SciCode

48%

Agentic & knowledge work

AutomationBench

15%

GDPval

33%

GDP.pdf

Briefcase (Elo)999

Science & reasoning

Terminal-Bench Science

CritPt (hard)

14%

HLE Diamond

Humanity's Last Exam

31%

Long-context reasoning

69%

Knowledge

Omniscience-2.9

By domain

Finance & accounting

26.7

Legal

25.3

Healthcare & medical

21.0

Engineering

23.5

Economics

27.0

Strategy & operations

21.8

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Nemotron 3.5 Super VL through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Nemotron 3.5 Super VL is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "nemotron-3.5-super-vl",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);