← All models
Google: Gemini Omni 1.1 FlashNEW
google/gemini-omni-1.1-flashvideo
A Google video model with natively multimodal input: it takes text, images, audio, and video simultaneously. Generate from scratch, a first frame, or references, then edit, extend, and iteratively refine the finished clip in conversation. Native audio, 16:9 and 9:16.
Price
Released
Sep 8, 2026
Calculator
per clip · 3s
Parameters
promptrequired, up to 30,000 characterssecondssizeinput_references2–7 imagesFine-tuning · 1
seedReproducibility number: the same prompt with the same seed yields the same clipHow 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="google/gemini-omni-1.1-flash",
prompt="Кот-космонавт на мотоцикле, ночь",
seconds="3",
size="720x1280",
# input_references=[...] # 2–7 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")
