Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google’s video model with a natively multimodal input: it understands text, images, audio and video at the same time. Generation from scratch, from a first frame or from references, plus editing and extending of a finished clip. Native voiceover, duration from 1 to 15 seconds. Generation is asynchronous: POST /v1/videos returns a job, then you poll the status and download the mp4.

Parameters

Field	Description
model	google/gemini-omni-1.1-flash (the short omni / gemini-omni)
prompt	Scene description, required; up to 30 000 characters
seconds	An integer from 1 to 15; defaults to 5. The upstream minimum charge is 3 seconds: requests shorter than 3 seconds are billed as 3
size	One of the six sizes below; defaults to 1280x720
input_reference	Image-to-video: one image as the starting frame, {"image_url": "data:image/...;base64,..."}
input_references	Not supported by the current channel: references return 400 (a direct-Google-channel feature, not accepted by the aggregator since Oct 31)
input_video	Video input: {"video_url": "https://..."} or a data: URL — up to 10 seconds for editing and extending
seed	Reproducibility seed: an integer 0…2147483647

Resolutions and frame formats (360p is for drafts; 1080p and 4K are upscaled):

Aspect	720p	1080p	4K
16:9	1280x720	1920x1080	3840x2160
9:16	720x1280	1080x1920	2160x3840

Examples

Text-to-video

Python

import requests

job = requests.post(
    "https://api.mixen.ai/v1/videos",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "model": "omni",
        "prompt": "A neon city in the rain, the camera glides over wet asphalt, reflections of the signs",
        "seconds": "8",
        "size": "1280x720",
    },
).json()
print(job["id"], job["status"])

cURL

curl https://api.mixen.ai/v1/videos \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni",
    "prompt": "A neon city in the rain, the camera glides over wet asphalt, reflections of the signs",
    "seconds": "8",
    "size": "1280x720"
  }'

Polling and download

curl https://api.mixen.ai/v1/videos/video_... \
  -H "Authorization: Bearer $MIXEN_API_KEY"

curl -L https://api.mixen.ai/v1/videos/video_.../content \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -o omni.mp4

Statuses: queued → in_progress → completed or failed. A sensible polling interval is 5–10 seconds. For the full cycle see the video guide.

Pricing

Billed per second: 360p — 4.28 ₽ per second, 720p — 13.06 ₽, 1080p — 19.00 ₽, 4K — 36.81 ₽. The upstream minimum charge is 3 seconds. Current prices — the catalog.

Strengths and limitations

• A multimodal input at once: text, images, audio and video in one request.
• First and last frame — in the web dashboard and bot.
• Editing and extending of a finished clip (up to 10 seconds of input), step-by-step edits in a dialogue — in the bot.
• A continuous 1–15 second duration; anything shorter than 3 seconds is billed as 3.
• Native voiceover; the API has no separate mute switch.
• Only two frame formats: 16:9 and 9:16.

All models — in the catalog. The general video workflow — the video guide.