NVIDIA: Nemotron 3 Super (free)

nvidia/nemotron-3-super-120b-a12b:free · NVIDIATokenizer lineage measured

Tokenizer lineage (measured): Mistral
Entered catalogue: 11 March 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from nvidia/nemotron-3-super-120b-a12b: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from nvidia/nemotron-3-super-120b-a12b: a serving variant shares its base model's tokenizer

Compare with NVIDIA: Nemotron 3 Super

Report a correction

This entry is a serving variant of NVIDIA: Nemotron 3 Super. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

NVIDIA: Nemotron 3 Super (free) is NVIDIA's model. Its measured tokenizer sits with the Mistral group, which is evidence that it builds on the Mistral tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against NVIDIA's authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_01cf8ac9
How much it can read and write	Reads up to 262,144 tokens at onceOpenRouter's listing shows 235,929 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Reasons when asked to, at medium, low, medium by default	its own listing

Declared record

What the catalogue claims about this model

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. Built on a hybrid Mamba-Transformer...

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0 / M tokens
Completion price: $0 / M tokens

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p

defaults: {"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

11 March 2026Enters the OpenRouter catalogue with no declared family.