Pass IndexThe State of AISign in

Nemotron 3 Super 120B A12B

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems.

text → text · made by NVIDIA

$0.061$0.29per Mtok in / out
Requesty · 2 sellers

Sold by 8 ways

SellerLaneRate
AWS Bedrock 0 ways$0.075per Mtok in$0.33per Mtok out
AWS Bedrock cloudnot on the seller's list todaybatch$0.075per Mtok in$0.33per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24
AWS Bedrock cloudin-region batch$0.075per Mtok in$0.33per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24
AWS Bedrock 0 ways$0.15per Mtok in$0.65per Mtok out
AWS Bedrock cloudnot on the seller's list todaystandard$0.15per Mtok in$0.65per Mtok outmodels.dev · read 2026-08-27
AWS Bedrock cloudin-region$0.15per Mtok in$0.65per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24
Requesty aggregatornot on the seller's list todaydeepinfra flex$0.061per Mtok in$0.29per Mtok outrouter.requesty.ai · read 2026-08-25
Requesty aggregatordeepinfra$0.068per Mtok in$0.32per Mtok outrouter.requesty.ai · read 2026-09-16
DeepInfra 0 ways$0.085per Mtok in$0.4per Mtok out
DeepInfra aggregatornot on the seller's list todaystandard$0.085per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-08-25
ElectronHub 0 ways$0.1per Mtok in$0.5per Mtok out
ElectronHub aggregatornot on the seller's list todaystandard$0.1per Mtok in$0.5per Mtok outapi.electronhub.ai · read 2026-08-27

About

Nemotron 3 Super 120B A12B — a text model from NVIDIA.

It takes text and returns text, with a context window of 1,048,576 tokens. The catalogue files it under chat.

Every current figure

Maker
NVIDIA
Register
model
Takes
text
Returns
text
Context
1,048,576 tokens
Parameters
120 billion · read from its own name, the total of a mixture

Known as 3 names

NVIDIA Nemotron 3 Super 120B A12Bdeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12Bdeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B:flex