modelbenchmark.io

NVIDIA Nemotron 3 Super 120B A12B

NVIDIA · nemotron-super-3-120b

Compare

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Specification

most-agreed values

Context
262K
Max output
131K
Released
2026-03-11
Knowledge cutoff
2025-06
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.65

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock$0.115
Batch inputbedrock_converse$0.075
Batch outputbedrock$0.505
Batch outputbedrock_converse$0.325
Priority inputbedrock$0.4025
Priority inputbedrock_converse$0.2625
Priority outputbedrock$1.7675
Priority outputbedrock_converse$1.1375

Batch input is 50% below the interactive input price at the same listing.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.15$0.65——262K131K—
bedrock_converse$0.15$0.65——256K32K—
bedrock
$0.23
$0.18
$1.01
$0.78
——256K
32K
33K
—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-04bedrockInput$0.18
2026-09-23bedrockInput$0.23
2026-09-04bedrockOutput$0.78
2026-09-23bedrockOutput$1.01

More from NVIDIA

most-hosted first