NVIDIA

Nemotron 3 Super (free)

by NVIDIAtext->text1 endpoint

Overview

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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Deterministic seed

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
235.9K tokens
Tokenizer
Other
Uptime (24h)
9812.7%

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p

Pricing

Per 1M tokens
Free
Added
March 11, 2026
Last synced 9/20/2026