modelbenchmark.io

Vision Small

vision-small

Compare

Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.

Specification

most-agreed values

Context
1M
Max output
66K
Released
2024-05-15
Knowledge cutoff
Retires
Open weights
no
Input
text, image, audio, video, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.05
Output
$3.16

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vispark · vispark$1.05$3.161M66K