How much does Gemini Omni Video cost?

Each render is one flat charge of about $1.01, whatever duration you request — a 4-second clip costs the same as a 10-second one, because this model is priced per output token and reports the same token count every time. The $0.10-per-second figure you may have seen is that flat charge divided by the 10-second maximum, so it only holds at full length. Ask for the full 10 seconds unless you need it shorter. Current rates are shown in the Hormouz dashboard.

Does a shorter clip cost less?

No. The provider bills the same token count for every render regardless of the duration requested, so a 5-second clip costs exactly the same as a 10-second one. Request the full 10 seconds unless you need a shorter clip for editorial reasons.

How do I access Gemini Omni Video from Iran?

Create a Hormouz account and get an API key. Hormouz provides a stable route to this model from inside Iran, with no foreign credit card and no circumvention tooling required.

How is Gemini Omni Video served on Hormouz?

Behind the asynchronous predictions API. POST to /v1/predictions with your prompt, then poll GET /v1/predictions/{id} until the clip is ready. Outputs are returned as Hormouz-hosted asset URLs.

Gemini Omni Video: image generation model

Gemini Omni Video is a Google video model that generates short clips with a synchronised audio track from a text prompt, a still image, or an existing video. Served asynchronously through Hormouz from inside Iran.

Pricing:: $1.01 / render (flat, 1-10s)
Type:: video

Gemini Omni Video generates up to 10 seconds of 720p video with a native synchronised audio track. It works from a text prompt alone, from a single still image used as the first frame, from up to four reference images that guide subject and style, or from an existing clip you want edited.

It is served through Hormouz behind an asynchronous predictions API: submit a prediction, then poll it until the clip is ready. Both landscape (16:9) and portrait (9:16) are supported, and every output carries an invisible SynthID watermark identifying it as AI-generated.

Each render is one flat charge of about $1.01 regardless of the duration you request — a 4-second clip is billed exactly the same as a 10-second one — so ask for the full 10 seconds unless you specifically need it shorter. The model is priced per output token rather than per second, and reports the same token count for every render, which is why the duration you ask for does not move the price. Hormouz provides stable access from inside Iran with no foreign credit card and no circumvention tooling.

Generates 1-10s of 720p video with a synchronised audio track from a text prompt, optionally seeded with a still image as the first frame, or up to 4 reference images. Billed as one flat charge per render: a 4s clip costs the same as a 10s one, so ask for the full length. Outputs carry an invisible SynthID watermark that identifies them as AI-generated.

Quickstart

# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"version":"google/gemini-omni-video","input":{"prompt":"A beautiful sunset"}}'

Specs

Vendor	Google
Type	Video
Context window	—
Pricing	$1.01 / render (flat, 1-10s)
API	predictions

Code example

cURL

# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"version":"google/gemini-omni-video","input":{"prompt":"A beautiful sunset"}}'

Python

import requests
BASE = "https://api.hormouz.net/v1"
H = {"Authorization": "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json"}
r = requests.post(f"{BASE}/predictions", headers=H,
    json={"version": "google/gemini-omni-video", "input": {"prompt":"A beautiful sunset"}})
print(r.json()["id"])

JavaScript

const BASE = "https://api.hormouz.net/v1";
const res = await fetch(`${BASE}/predictions`, {
  method: "POST",
  headers: { Authorization: "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ version: "google/gemini-omni-video", input: {"prompt":"A beautiful sunset"} }),
});
const { id } = await res.json();

Buy the Gemini Omni Video API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Gemini Omni Video and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account Buy Gemini API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Gemini Omni Video cost?: Each render is one flat charge of about $1.01, whatever duration you request — a 4-second clip costs the same as a 10-second one, because this model is priced per output token and reports the same token count every time. The $0.10-per-second figure you may have seen is that flat charge divided by the 10-second maximum, so it only holds at full length. Ask for the full 10 seconds unless you need it shorter. Current rates are shown in the Hormouz dashboard.
Does a shorter clip cost less?: No. The provider bills the same token count for every render regardless of the duration requested, so a 5-second clip costs exactly the same as a 10-second one. Request the full 10 seconds unless you need a shorter clip for editorial reasons.
How do I access Gemini Omni Video from Iran?: Create a Hormouz account and get an API key. Hormouz provides a stable route to this model from inside Iran, with no foreign credit card and no circumvention tooling required.
How is Gemini Omni Video served on Hormouz?: Behind the asynchronous predictions API. POST to /v1/predictions with your prompt, then poll GET /v1/predictions/{id} until the clip is ready. Outputs are returned as Hormouz-hosted asset URLs.

Updated 2026-10-13