modelbenchmark.io

Nemotron 3 Super 120B A12B (Nebius)

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
262K
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
$0.30
Output
$0.90
Cache read
$0.30

Available from 12 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kenari · freefreefree——262K262K—
requestyfreefree——1M66K—
nano-gpt$0.05$0.25$0.025—262K16K—
nano-gpt · thinking$0.05$0.25$0.025—262K16K—
kilo$0.08$0.45——1M262K—
kenari$0.0971$0.48$0.0097—262K262K—
vercel$0.15$0.65——256K32K—
perplexity-agent$0.25$2.50——1M32K—
edenai
$0.30
$0.085
$0.90
$0.40
$0.30—262K262K—
nebius$0.30$0.90$0.06—262K
33K
262K
—
openrouter$0.30$2.40$0.15—1M262K—
edenai · arkanecloud$0.40$0.80$0.10—256K262K—

Price history

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

DateHostField$/M
2026-09-02edenaiInput$0.30
2026-10-18edenaiInput$0.085
2026-10-19edenaiInput$0.30
2026-10-20edenaiInput$0.085
2026-10-22edenaiInput$0.30
2026-10-23edenaiInput$0.085
2026-10-25edenaiInput$0.30
2026-10-26edenaiInput$0.085
2026-10-28edenaiInput$0.30
2026-10-31edenaiInput$0.085
2026-11-01edenaiInput$0.30
2026-09-02kenariInputfree
2026-10-22kenariInput$0.0971
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
2026-09-19openrouterInput$0.08
2026-10-08openrouterInput$0.085
2026-10-09openrouterInput$0.08
2026-10-10openrouterInput$0.08
2026-10-21openrouterInput$0.30
2026-10-28openrouterInput$0.08
2026-10-29openrouterInput$0.30
2026-09-02openrouter · freeInputfree
2026-09-06openrouter · freeInputfree
2026-10-10openrouter · freeInputfree
2026-09-02edenaiOutput$0.90
2026-10-18edenaiOutput$0.40
2026-10-19edenaiOutput$0.90
2026-10-20edenaiOutput$0.40
2026-10-22edenaiOutput$0.90
2026-10-23edenaiOutput$0.40
2026-10-25edenaiOutput$0.90
2026-10-26edenaiOutput$0.40
2026-10-28edenaiOutput$0.90
2026-10-31edenaiOutput$0.40
2026-11-01edenaiOutput$0.90
2026-09-02kenariOutputfree
2026-10-22kenariOutput$0.48
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
2026-09-19openrouterOutput$0.45
2026-10-08openrouterOutput$0.40
2026-10-09openrouterOutput$0.45
2026-10-10openrouterOutput$0.45
2026-10-21openrouterOutput$2.40
2026-10-28openrouterOutput$0.45
2026-10-29openrouterOutput$2.40
2026-09-02openrouter · freeOutputfree
2026-09-06openrouter · freeOutputfree
2026-10-10openrouter · freeOutputfree
2026-10-21openrouterCache read$0.15
2026-10-29openrouterCache read$0.15
2026-10-22nebiusCache read$0.30
2026-10-24nebiusCache read$0.06

More from NVIDIA

most-hosted first