modelbenchmark.io

Nvidia Nemotron 3 Super 120B Thinking

NVIDIA · nemotron-3-super-120b-a12b

Compare

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

Specification

most-agreed values

Context
262K
Max output
236K
Released
2026-03-01
Knowledge cutoff
2026-02
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$0.90
Cache read
$0.025
Cache write
$0.375

Available from 16 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kenarifreefree262K262K
kenari · freefreefree262K262K
kilo · freefreefree262K236K
openrouter · freefreefree262K236K
requestyfreefree1M66K
nano-gpt$0.05$0.25$0.025262K16K
nano-gpt · thinking$0.05$0.25$0.025262K16K
kilo$0.08$0.45262K236K
openrouter
$0.08
$0.085
$0.45
$0.40
262K
1M
236K
16K
edenai · flexai$0.085$0.40262K262K
vercel$0.15$0.65256K32K
nvidia$0.20$0.80262K262K
perplexity-agent$0.25$2.501M32K
edenai$0.30$0.90$0.30262K262K
nebius$0.30$0.90262K
33K
262K
tensorx$0.30$0.90$0.075$0.375262K262K

Price history

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

DateHostField$/M
2026-09-02kiloInput$0.085
2026-09-12kiloInput$0.08
2026-09-02nebiusInput$0.30
2026-09-06nebiusInput$0.30
2026-09-02openrouterInput$0.085
2026-09-06openrouterInput$0.085
2026-09-15openrouterInput$0.08
2026-09-02openrouter · freeInputfree
2026-09-06openrouter · freeInputfree
2026-09-02kiloOutput$0.40
2026-09-12kiloOutput$0.45
2026-09-02nebiusOutput$0.90
2026-09-06nebiusOutput$0.90
2026-09-02openrouterOutput$0.40
2026-09-06openrouterOutput$0.40
2026-09-15openrouterOutput$0.45
2026-09-02openrouter · freeOutputfree
2026-09-06openrouter · freeOutputfree

More from NVIDIA

most-hosted first