modelbenchmark.io

Cosmos Reason2 8B

NVIDIA · cosmos-reason2-8b

Compare

Vision language model for physical-world understanding with structured reasoning on video and images

Specification

most-agreed values

Context
131K
Max output
16K
Released
2025-12-01
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree131K16K

More from NVIDIA

most-hosted first