AI model comparison

Nemotron 3 Ultra vs Nemotron 3 Super

Side by side comparison of Nemotron 3 Ultra and Nemotron 3 Super on pricing, benchmark scores, context window, and more.

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Input / 1M
$0.50
Output / 1M
$2.20
Context
262K

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.

Input / 1M
$0.08
Output / 1M
$0.40
Context
262K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

nvidia logo

Nemotron 3 Super

6.0x cheaper for a typical chat

Higher intelligence score

nvidia logo

Nemotron 3 Super

12.8 vs 11.8 on Artificial Analysis

Larger context window

Tie

262K vs 262K tokens

Newer release

nvidia logo

Nemotron 3 Ultra

Released June 4, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

nvidia logoNemotron 3 Ultra11.8
nvidia logoNemotron 3 Super12.8

Coding index

nvidia logoNemotron 3 Ultra49.3
nvidia logoNemotron 3 Super37.7

Agentic index

nvidia logoNemotron 3 Ultra20.1
nvidia logoNemotron 3 Super1.7

Pricing

Nemotron 3 Ultra vs Nemotron 3 Super API pricing

Per-token API rates. Cheaper option highlighted.

Metricnvidia logoNemotron 3 Ultranvidia logoNemotron 3 Super
Input tokensPer 1M tokens$0.50$0.08
Output tokensPer 1M tokens$2.20$0.40
Cached input (read)Per 1M tokens$0.10Not available
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

nvidia logoNemotron 3 Ultra$2.10
nvidia logoNemotron 3 Super$0.35

Coding task

30K in, 4K out

nvidia logoNemotron 3 Ultra$23.80$11.80 cached
nvidia logoNemotron 3 Super$3.85

Long document summary

150K in, 2K out

nvidia logoNemotron 3 Ultra$79.40$19.40 cached
nvidia logoNemotron 3 Super$12.05

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricnvidia logoNemotron 3 Ultranvidia logoNemotron 3 Super
Context window262K tokens262K tokens
Max output16K tokens16K tokens
Input typesTextText
Output typesTextText
Reasoning effort levelsHigh, Medium, NoneMedium, Low, None
Default reasoning effortHighMedium
Release dateJune 4, 2026March 11, 2026

Features

Supported features

API features available for each model.

Metricnvidia logoNemotron 3 Ultranvidia logoNemotron 3 Super
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Nemotron 3 Super is 6.0x cheaper for a typical chat. Nemotron 3 Super scores higher on the Artificial Analysis Intelligence Index (12.8 vs 11.8). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Nemotron 3 Ultra or Nemotron 3 Super cheaper?

Nemotron 3 Super is cheaper for a typical chat (2K input tokens and 500 output tokens). Nemotron 3 Super costs $0.08 per 1M input tokens and $0.40 per 1M output tokens, while Nemotron 3 Ultra costs $0.50 per 1M input tokens and $2.20 per 1M output tokens.

Which has a bigger context window, Nemotron 3 Ultra or Nemotron 3 Super?

Nemotron 3 Ultra supports up to 262K tokens of context, compared with 262K for Nemotron 3 Super.

Is Nemotron 3 Ultra smarter than Nemotron 3 Super?

On the Artificial Analysis Intelligence Index, Nemotron 3 Ultra scores 11.8 and Nemotron 3 Super scores 12.8, putting Nemotron 3 Super ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Nemotron 3 Ultra and Nemotron 3 Super at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Nemotron 3 Ultra and Nemotron 3 Super answer side by side and keep the better response.

nvidia logonvidia logo

Why choose? Ask both.

Send one prompt to Nemotron 3 Ultra and Nemotron 3 Super at the same time. Compare the answers side by side and keep the best one.