modelbenchmark.io

minicpm-v-4.5

minicpm-v-4-5

Compare

MiniCPM-V 4.5 is a compact, high-performance vision-language model excelling in video understanding, OCR, and multimodal reasoning with efficient deployment.

Specification

most-agreed values

Context
32K
Max output
32K
Released
2026-06-02
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.651
Output
$1.097

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cortecs$0.651$1.09732K32K
nebius$0.658$1.1132K32K