Nemotron 3 Super

NVIDIAnvidia/nemotron-3-super-120b-a12bFree tieriProviders: 2
Inputi$0.08per 1M tokens
Outputi$0.45per 1M tokens
Contexti256K262,144 tokens
ReleasedMar 11, 2026Max output: 236K

About this model

Nemotron 3 Super is an AI model from NVIDIA, made available through the API on March 11, 2026. It can read up to 262,144 tokens in one request, roughly 492 pages of text, and write up to 235,929 tokens in a single answer.

Through the API it costs $0.08 per million input tokens and $0.45 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.

It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8), so it can also be downloaded and run on your own hardware.

Quality scores

Rankings →

Not rated yet. Independent test results usually appear a few weeks after a model is released.

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 2. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
DeepInfraCheapestbf16
$0.085$0.40256K100.0%
DekaLLMfp8
$0.08$0.45256K97.2%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call Nemotron 3 Super through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3-super-120b-a12b", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $0.175
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.0045
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $78.00

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
Gemma 4 26B A4B Google DeepMind
$0.077$0.26256KCompare with ⇄
$0.075$0.50256KCompare with ⇄
$0.075$0.25256KCompare with ⇄
$0.074$0.308KCompare with ⇄
$0.09$0.36512KCompare with ⇄
Laguna S 2.1Poolside
$0.09$0.181MCompare with ⇄

News about NVIDIA

See all →

Frequently asked questions

How much does Nemotron 3 Super cost?
Nemotron 3 Super costs $0.08 per million input tokens and $0.45 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.175.
What is the context window of Nemotron 3 Super?
Nemotron 3 Super can read up to 262,144 tokens in one request, about 492 pages of text. It can write up to 235,929 tokens in a single answer.
Is Nemotron 3 Super open source?
Yes. Its weights are published (nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8), so you can download it and run it on your own hardware, or use it through one of 2 API providers.
Who makes Nemotron 3 Super?
Nemotron 3 Super is made by NVIDIA. It became available through the API on March 11, 2026.
Can Nemotron 3 Super read images?
No. Nemotron 3 Super only accepts text as input.
What are the alternatives to Nemotron 3 Super?
Models with a similar price from other companies include Gemma 4 26B A4B , Ternary Bonsai 2 27B and Nex-N2.5-Pro. You can compare them side by side on this page.