modelbenchmark.io

Seedance 2.5

seedance-2-5

Compare

ByteDance multimodal audio-video model with up to 30-second single-pass generation, multi-round extension, reference inputs and timestamp-level editing.

Specification

most-agreed values

Context
0
Max output
0
Released
2026-07-31
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
video

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vercel · bytedance————00—