Nemotron 3.5 Super VL 120B A12B

NVIDIA's vision-language Nemotron 3.5 Super, a 120B hybrid of Mamba-2, MoE and attention layers activating 12B per token, built on the Nemotron 3 Super base, under OpenMDW 1.1.

Params: 120B, 12B active
Context: 1M tokens
Released: Oct 2026
License: OpenMDW 1.1

Visit Nvidia Compare vs other LLMs →

Hosted API price

Cheapest via Together AI · per 1M tokens

USD

Input: $0.15 /1M
Output: $0.50 /1M
Hosted by: 3 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Nemotron 3.5 Super VL 120B A12B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Nemotron 3.5 Super VL 120B A12B, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Together AI Cheapest	$0.15	$0.50	$0.02	$2.50	Visit website
DigitalOcean	$0.30	$0.65	$0.06	$4.30	Visit website
Nvidia Creator	Open weights, no hosted price				Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Nemotron 3.5 Super VL 120B A12B needs about 68 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 4× RTX 3090 at about $662 a month.

That costs the same as roughly 3B tokens a month on Together AI's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Nemotron 3.5 Super VL 120B A12B at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 1M context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	68 GB76 GB	4× RTX 3090	$662$662	3B tokens /mo3B tokens /mo
8-bit FP8 / INT8	122 GB130 GB	8× RTX 3090	$1,325$1,325	6B tokens /mo6B tokens /mo
16-bit FP16 / BF16	242 GB250 GB	8× RTX A6000	$3,398$3,398	16B tokens /mo16B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Similarly priced models

The models nearest Nemotron 3.5 Super VL 120B A12B by blended rate, each at its own cheapest provider.

Models priced nearest Nemotron 3.5 Super VL 120B A12B per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Nemotron 3.5 Super VL 120B A12B
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	−18%
Llama 3.3 70B Meta	$0.1792	$0.135	$0.40	128K	Dec 2023	−14%
Qwen3.5-27B Alibaba Cloud	$0.1863	$0.086	$0.688	262K		−11%
Hy3 Tencent	$0.198	$0.132	$0.528	262K		−5%
Ministral 3 14B Mistral	$0.20	$0.20	$0.20	256K		−4%
Nemotron 3.5 Super VL 120B A12B This model Nvidia	$0.2083	$0.15	$0.50	1M
Command R 08-2024 Cohere	$0.225	$0.15	$0.60	128K	Jun 2024	+8%
GPT-4o Mini OpenAI	$0.225	$0.15	$0.60	128K	Oct 2023	+8%
MiniMax-M2.7 MiniMax	$0.225	$0.15	$0.60	205K		+8%
Mistral Small 4 Mistral	$0.225	$0.15	$0.60	256K		+8%
Qwen3.8-27B Alibaba Cloud	$0.225	$0.17	$0.50	262K		+8%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

GPUhub

Fully Dedicated GPU Servers

No Virtualization. No Shared GPUs

Stable Performance for AI Training & Inference

Full Control for Production Workloads

Learn more

Capabilities

What Nemotron 3.5 Super VL 120B A12B accepts and can do, as published by Nvidia.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Video Accepts video as input.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.

Common questions

What is Nemotron 3.5 Super VL 120B A12B good for?

Reasoning, coding, tool use and reading documents, images and video, with a switchable thinking mode. Open weights under the OpenMDW 1.1 license, on a multi-GPU node at full precision.

When is Nemotron 3.5 Super VL 120B A12B not a good fit?

Audio input: it takes text, images and video and returns text only. Memory follows the full 120B parameters, not the 12B active, and no maximum output or knowledge cutoff is published.

What is the cheapest way to run Nemotron 3.5 Super VL 120B A12B?

Hosted, unless you push serious volume. Together AI charges $0.15 in / $0.50 out per 1M tokens. The cheapest rental that fits is 4x RTX 3090 at $662 a month, which costs the same as about 3B tokens a month on that API.

How does Nemotron 3.5 Super VL 120B A12B compare with Nemotron 3 Super 120B A12B?

NVIDIA says Nemotron 3.5 Super VL starts from the Nemotron 3 Super base, adds a vision encoder for images, documents and video, and was further trained by distillation from Nemotron 3 Ultra and on software-engineering data. Same 1M-token context. Nemotron 3.5 Super VL 120B A12B costs 70% less per 1M input tokens and 67% less per 1M output tokens than Nemotron 3 Super 120B A12B, at each model's cheapest listed provider. It came out 7 months later, takes image and video input, which Nemotron 3 Super 120B A12B does not and is licensed under OpenMDW 1.1 against NVIDIA Nemotron Open Model License.

Can I self-host Nemotron 3.5 Super VL 120B A12B?

Yes. The weights are OpenMDW 1.1 licensed. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $662 a month on the cheapest rental that fits.