What is Gemini Omni Flash Preview API?
Gemini Omni Flash Preview is Google's multimodal video generation model. It produces video from text prompts, reference images, and existing video clips — and supports four task modes: text-to-video, image-to-video, reference-to-video, and video editing.
Output videos are delivered in 16:9 or 9:16 aspect ratios at durations from 3 to 10 seconds. Multi-turn editing is available via the Gemini Interactions API, enabling conversational refinement of generated content.
[Model Specifications embed]
[Performance Benchmarks embed]
API Pricing
Where to Use Gemini Omni
Text-to-video content creation
Describe a scene and receive a short video clip — for social content, marketing materials, or product demos where written briefs need to become motion assets.
Image-to-video animation
Animate a still image into a video sequence. Useful for product photography, character animation, and giving motion to static visuals.
Reference-guided generation
Bind reference images to specific roles in the prompt using tags like <IMAGE_REF_0> for precise control over character appearance, environment, or style.
Video editing workflows
Pass an existing video clip and prompt the model to modify it — background changes, motion adjustments, style transformation.
Gemini Omni vs. the Alternatives
Generate high-quality video from text, image, and video inputs, with native audio output.
Use it for conversational video editing, including refining and editing generated videos through natural-language prompts.
Animate still images or photos into video, including from text descriptions or reference assets.
Create and remix video assets in workflows that involve swapping characters or products, relighting scenes, altering angles, or adding objects.
import requests, time
headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
"https://api.aimlapi.com/v2/video/generations",
headers=headers,
json={
"model": "google/gemini-omni-flash-preview",
"prompt": "A serene timelapse of clouds over a mountain range"
},
).json()
gid = job["id"]
while True:
res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json()
if res.get("status") in ("completed", "error"):
break
time.sleep(5)
print(res["video"]["url"])
const headers = {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers,
body: JSON.stringify({
"model": "google/gemini-omni-flash-preview",
"prompt": "A serene timelapse of clouds over a mountain range"
}),
})).json();
let res;
do {
await new Promise((r) => setTimeout(r, 5000));
res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (!["completed", "error"].includes(res.status));
console.log(res.video.url);
# submit the generation — the response contains the job "id"
curl -X POST https://api.aimlapi.com/v2/video/generations \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemini-omni-flash-preview","prompt":"A serene timelapse of clouds over a mountain range"}'
# then poll until status is "completed" — video.url holds the result
curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
Input image tokens $1.95/1M · generated video tokens $22.75/1M (incidental text-response tokens, if any, $11.7/1M).
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemini Omni This page | Video generation | |||
| Video generation | ||||
| Cinematic video + native audio |
Gemini Omni takes image, text, video as input and returns video.
Gemini Omni is priced at input $1.95 / 1M tokens, output $22.75 / 1M tokens.
Gemini Omni is billed per token, charged separately for input and output.
Yes, Gemini Omni accepts image input as well as a text prompt.
Gemini Omni was built by Google.
Use google/gemini-omni-flash-preview as the model id on AI/ML API.
Yes. Gemini Omni is served through AI/ML API, so the same key and endpoint format used for other models applies.
Yes, Gemini Omni includes audio generation as part of its video generation capabilities.
Yes, Gemini Omni supports reference-to-video generation in addition to text-to-video and image-to-video.
-min.webp){kind=small}