NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
Specification
most-agreed values
Context
66K
Max output
66K
Released
2026-10-15
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.57
Output
$1.44
Cache read
$0.114
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| thinkingmachines | $0.57 | $1.44 | $0.114 | — | 66K | 66K | — |
Other listings of this model
this page is one of them
The corpus files Nemotron 3.5 Super VL 120B A12B under several keys. This page is the nvidia-nemotron-3-5-super-vl-120b-a12b-bf16 listing. The full record — every host, every price and every benchmark score — is on the main Nemotron 3.5 Super VL 120B A12B page.
More from NVIDIA
most-hosted first