Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Nemotron 3 Super (free)

NVIDIA· released 11 Mar 2026

nvidia/nemotron-3-super-120b-a12b:free
Input / 1M tokens
free
Output / 1M tokens
free
Context window262K tokens

Longest answer: 236K tokens

reads textopen weightstool callingreasoning
See it on openrouter.ai

About

Nemotron 3 Super is NVIDIA’s 120-billion-parameter open-weight model, with a mixture-of-experts design that activates 12 billion parameters. Its hybrid Mamba-Transformer architecture is described as suited to complex multi-agent applications, with compute efficiency and accuracy as design goals. The model accepts and produces text, supports reasoning and tools, and has a 262,144-token context window. Its maximum output is 235,929 tokens. NVIDIA lists the weights as open, and the Hugging Face identifier is nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8. The model is available as nvidia/nemotron-3-super-120b-a12b:free. It was released on March 11, 2026. For builders, its long context and tool support are relevant to multi-agent workflows that operate on text; the listed input and output modalities are text only.

Who it is for

Teams building text-based multi-agent applications may find its tool support, reasoning, and 262,144-token context useful. Its open weights may suit builders who want access to model weights.

What is good

  • Open weights are available.
  • Supports reasoning and tools.
  • 262,144-token context window.
  • Maximum output is 235,929 tokens.
  • Listed as free.

What to know first

  • Inputs and outputs are text only.
  • No vision input is listed.

Verdict

Nemotron 3 Super pairs open weights with a large context window and tool support. Its listed scope is text in and text out, so teams needing other modalities should note that limitation.

Details

Lab
NVIDIAopenrouter.ai · 3 Oct 2026
Context
262Kopenrouter.ai · 3 Oct 2026
Input price
Freeopenrouter.ai · 3 Oct 2026
Output price
Freeopenrouter.ai · 3 Oct 2026
Max output
235,929 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list
Ling 3.1 Flash ctx262KinFreeoutFree inclusionAIApodex 1.1 Mini (free) ctx262KinFreeoutFree ApodexPareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiasedGPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAIGPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAIClaude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Sources