Gemini Omni Flash API
Google's all-in-one video model — references, frames and sound in one prompt
Try Gemini Omni Flash
Runs on your balance at the price shown on the button. Results are saved to your account.
Landscape or portrait.
720p (1080p and 4K aren't available on our channel yet).
Clip length: 4, 6, 8 or 10 seconds.
Create a free account with Google or email — pay only for what you generate.
Your video will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
What is Gemini Omni Flash?
Gemini Omni Flash 1.1, Google's default video model, generates 4–10 second 720p videos with dialogue, music and effects from text, a first and last frame, or reference images.
One model for every input
Omni understands text, images and sound together: describe a scene, animate a still between two frames, or cast people and products from reference images — the audio is generated with the picture.
Google's new default
Google now points new video work to Gemini Omni Flash, and it ranks among the best image-to-video models on public leaderboards.
Gemini Omni Flash pricing
Pay per second of video. No subscription. Failed generations are refunded automatically.
| Tier | Official price | Cheaper Gen. | You save |
|---|---|---|---|
720p · 4 s audio included | $0.087/s | −15% | |
720p · 8 s audio included | $0.072/s | −29% |
- Official price: Gemini API list price for gemini-omni-1.1-flash ($17.50 / 1M video output tokens: 5,792 tokens/s at 720p ≈ $0.101 / s, 8,688 at 1080p ≈ $0.152, 17,376 at 4K ≈ $0.304; input $1.50 / 1M, thinking $9 / 1M). Prices verified 2026-10-16.
- Output is billed per clip length (4, 6, 8 or 10 s); reference images add a fraction of a cent each at Google's rates.
Specifications
- Resolution
- 720p
- Duration
- 4, 6, 8 or 10 s
- Aspect ratios
- 16:9 · 9:16
- Audio
- Always on (included)
- Model id (Google)
- gemini-omni-1.1-flash
- Released
- Aug 27, 2026
Use Gemini Omni Flash via API
One request to start a job, one to fetch the result. Same shape for every model.
import os, time, requests
API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}
# 1. Submit the job
job = requests.post(f"{API}/run/google/gemini-omni-flash/text-to-video", headers=headers, json={
"prompt": "A jazz trio plays in a smoky basement club, the singer leans into the mic and the crowd snaps along",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 8
}).json()
# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
time.sleep(3)
job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()
print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])Example prompts
Hit “Try it” to load a prompt into the playground above.
Gemini Omni Flash FAQ
Related models

Veo3.1
Text · Image → Video
Google's cinematic video model with native audio, up to 4K

Veo3.1 Lite
Text · Image → Video
The lowest-cost Veo — native audio from a few cents a second

Kling3.0 Omni
Text · Image · Reference → Video
Kling 3.0 with multi-image references for consistent characters
Gemini Omni Flash is developed by Google. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI
