NVIDIA: Nemotron 3 Super

120B / 12B

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.

Context
1.0M
Max output
262K
Input price
$0.3/1M tokens
Output price
$2.4/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/nemotron-3-super-120b-a12b
Provider OpenRouter
Creator NVIDIA
Family—
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters120B / 12B
Architecture—
Context window1.0M tokens
Max input—
Max output262K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.3
Output
$2.4
Cache write
—
Cache read
$0.15
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/nvidia/nemotron-3-super-120b-a12b

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

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.

Changes · 19 entries
nvidia/nemotron-3-super-120b-a12bupdateca7a400Nov 2, 2026, 03:02 AM
context_window262144→1048576
pricinginput$0.09→$0.3output$0.45→$2.4cached input$0.1→$0.15
max_output_tokens262144
nvidia/nemotron-3-super-120b-a12bupdateb2f45bfOct 29, 2026, 03:29 AM
context_window262144→1048576
max_output_tokens235929→262144
nvidia/nemotron-3-super-120b-a12bupdate4e8b6afOct 21, 2026, 06:35 AM
pricinginput$0.08→$0.3output$0.45→$2.4cached input$0.06→$0.15
nvidia/nemotron-3-super-120b-a12bupdate70614e7Oct 9, 2026, 06:39 AM
pricinginput$0.085→$0.08output$0.4→$0.45
max_output_tokens16384→235929
nvidia/nemotron-3-super-120b-a12bupdateda0e420Oct 8, 2026, 06:41 AM
pricinginput$0.08→$0.085output$0.45→$0.4
max_output_tokens235929→16384
nvidia/nemotron-3-super-120b-a12bupdatea6d63d7Sep 15, 2026, 06:39 AM
pricinginput$0.085→$0.08output$0.4→$0.45
max_output_tokens16384→235929
nvidia/nemotron-3-super-120b-a12bupdate79684d6Sep 9, 2026, 06:38 AM
context_window1000000→262144
nvidia/nemotron-3-super-120b-a12bupdate97fe10eJul 25, 2026, 09:55 AM
pricinginput$0.08→$0.085output$0.45→$0.4
nvidia/nemotron-3-super-120b-a12bupdatebf78dcfJul 25, 2026, 05:49 AM
pricinginput$0.21→$0.08output$0.455→$0.45
nvidia/nemotron-3-super-120b-a12bupdate20c73acJul 17, 2026, 02:34 AM
pricinginput$0.08→$0.21output$0.45→$0.455cached input$0.1→$0.06
nvidia/nemotron-3-super-120b-a12bupdate53ef452Jul 9, 2026, 02:32 AM
pricinginput$0.085→$0.08output$0.4→$0.45
nvidia/nemotron-3-super-120b-a12bupdate88d97e5Jun 30, 2026, 04:49 AM
pricinginput$0.09→$0.085output$0.45→$0.4
nvidia/nemotron-3-super-120b-a12bupdate9e091d8May 23, 2026, 05:20 PM
pricinginput$0.1→$0.09output$0.5→$0.45
nvidia/nemotron-3-super-120b-a12bupdate73d11c6May 18, 2026, 03:39 AM
context_window262144→1000000
pricinginput$0.09→$0.1output$0.45→$0.5
max_output_tokens16384
nvidia/nemotron-3-super-120b-a12bupdate6231fb5Apr 22, 2026, 02:50 AM
pricinginput$0.1→$0.09output$0.5→$0.45
nvidia/nemotron-3-super-120b-a12bupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
nvidia/nemotron-3-super-120b-a12bupdateb301ebeMar 23, 2026, 11:47 PM
pricingcached input$0.04→$0.1
nvidia/nemotron-3-super-120b-a12bupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
parameters120
active_parameters12
release_date2026-03-11
taglineNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid M...
tools["function_calling"]
nvidia/nemotron-3-super-120b-a12bcreate7f5c66fMar 21, 2026, 05:16 AM