modelbenchmark.io

Nemotron 3.5 Super VL 120B A12B

NVIDIA · nemotron-3-5-super-vl

Compare

NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use

Specification

most-agreed values

Context
1M
Max output
1M
Released
2026-10-15
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$0.90
Cache read
$0.06

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo · freefreefree——1M131K—
openrouter · freefreefree——1M131K—
kilo$0.06$0.35$0.01—262K236K—
kyma · kyma$0.081$0.4725$0.0135—1M236K—
nano-gpt$0.15$0.50$0.02—262K16K—
openrouter$0.15$0.50$0.02—1M236K—
vercel$0.20$0.50$0.04—1M1M—
digitalocean$0.30$0.65$0.06—1M1M—
nebius$0.30$0.90$0.06—1M1M—

Price history

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

DateHostField$/M
2026-10-16kiloCache read$0.08
2026-10-24kiloCache read$0.01
2026-10-16nebiusCache read$0.30
2026-10-24nebiusCache read$0.06
2026-10-16openrouterCache read$0.02
2026-10-17openrouterCache read$0.08
2026-10-20openrouterCache read$0.02
2026-10-16kiloInput$0.10
2026-10-24kiloInput$0.06
2026-10-16openrouterInput$0.15
2026-10-17openrouterInput$0.10
2026-10-20openrouterInput$0.15
2026-10-16kiloOutput$0.40
2026-10-24kiloOutput$0.35
2026-10-16openrouterOutput$0.50
2026-10-17openrouterOutput$0.40
2026-10-20openrouterOutput$0.50

Other listings of this model

same model, different key

More from NVIDIA

most-hosted first