modelbenchmark.io

Nvidia Nemotron Super 49B

NVIDIA · llama-3-3-nemotron-super-49b

Compare

Nemotron model for efficient reasoning, coding, and specialized AI agents

Specification

most-agreed values

Context
131K
Max output
131K
Released
2025-08-08
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.40
Cache read
$0.075

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree131K66K
nebius$0.10$0.40131K131K
nano-gpt$0.15$0.15$0.075128K16K
deepinfra
$0.40
$0.10
$0.40131K131K

More from NVIDIA

most-hosted first