All models

ByteDance: Seedance 2.5

bytedance/seedance-2.5
video

Seedance 2.5 by ByteDance: long-form storytelling, multimodal references, first+last frame, native audio.

Pricing

per clip · 4s

Parameters

promptrequired
seconds · · · · · · · · · · · · · · · · · · · · · · · · · ·
size · · · · · · · · · · ·
input_references2–9 images

How to use via API

import time
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
video = client.videos.create(
model="bytedance/seedance-2.5",
prompt="Кот-космонавт на мотоцикле, ночь",
seconds="4",
size="480x480",
# input_references=[...] # 2–9 референс-картинок
)
while video.status not in ("completed", "failed"):
time.sleep(5)
video = client.videos.retrieve(video.id)
client.videos.download_content(video.id).write_to_file("video.mp4")
Try in the botAPI docs