modelbenchmark.io

riva-translate-4b-instruct-v1_1

NVIDIA · riva-translate-4b-instruct

Compare

Translation model for multilingual conversion, localization, and cross-language workflows

Specification

most-agreed values

Context
128K
Max output
4K
Released
2025-12-12
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree128K4K

More from NVIDIA

most-hosted first