Gemini Omni 1.2 Flash overview
Gemini Omni 1.2 Flash by Google
Gemini Omni 1.2 Flash is Google's conversational video generation and editing model. It is the latest release after Gemini Omni 1.1 Flash.
Gemini Omni 1.2 Flash specs
- Model ID
google/gemini-omni-1.2-flash- Developer
- Input
- Image, Text, Video
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
Refine a clip one turn at a time
Each editing turn produces a new video while preserving context from earlier turns. Google describes the model as built for fast video generation, conversational editing and cinematic control. Output runs at 24 frames per second.
Extension adds 3 to 10 seconds per turn, up to a total video length of 30 seconds. Review the last seconds of each turn before you extend again, because the next turn builds on what the previous one produced.
Pick the task, shape and length
The task option accepts text to video, image to video, reference to video, or edit or extend. The default task is inferred from the media you attach, so set it explicitly only when the intent is ambiguous. Reference to video takes up to six reference images for character and subject consistency, according to Google.
Duration takes 3 to 15 seconds. Aspect ratio is 16:9 or 9:16. The resolution value refers to the short side in pixels, from 360p up to 4k. Start with a short clip at 720p, check motion and audio, then raise the resolution to 1080p or 4k for the final render.
Use cases
Turn a written scene description into a short clip with native audio for a social post.
Animate a still product image into a vertical 9:16 video.
Keep one character consistent across several shots by supplying reference images.
Edit an existing clip through follow-up instructions, then extend it toward a 30 second cut.
Gemini Omni 1.2 Flash API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.0695 | per second |
Prices from the AI/ML API price list, checked on Nov 6, 2026.
Gemini Omni 1.2 Flash vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 Gemini Omni 1.2 Flash | $0.0695 |
| Veo 3.1 Lite Generate Preview | $0.03 |
| Veo 3.1 Fast | $0.08 |
| Gemini Omni 1.1 Flash | $0.1014 |
| Veo 3.1 | $0.2 |
How to use the Gemini Omni 1.2 Flash API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/gemini-omni-1.2-flash",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/gemini-omni-1.2-flash",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "google/gemini-omni-1.2-flash",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to Gemini Omni 1.2 Flash
Related articles
Gemini Omni 1.2 Flash FAQ
How much does Gemini Omni 1.2 Flash cost?
Gemini Omni 1.2 Flash costs $0.069504 / sec on AI/ML API.
Which inputs does the model accept?
It accepts text, image and video inputs and returns a video with native audio. The task option selects text to video, image to video, reference to video, or edit or extend.
How long can a generated video be?
A single generation lasts 3 to 15 seconds. Extension adds 3 to 10 seconds per turn, up to a total length of 30 seconds.
How do I keep a character consistent across clips?
Use reference to video with up to six reference images. Google lists this as the way to keep characters and subjects consistent.
What does the resolution value mean?
The number refers to the short side of the video in pixels. The options are 360p, 720p, 1080p and 4k, and output runs at 24 frames per second.
What is the Gemini Omni 1.2 Flash model ID?
Use google/gemini-omni-1.2-flash as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.