Gemini Omni API: Google video with sound, prices and code
Google's Gemini Omni models make video with sound from a prompt, a start frame or reference pictures, up to 4K. This guide covers the three versions on Revana, what each costs per second and how to call them.
The Gemini Omni video models
Gemini Omni is Google's video family built on Gemini. The models make clips with sound from a prompt, a start frame or reference pictures. Revana carries three versions on one request format:
| Model | Model id | Does | Resolution | Length | Reference images | Price from | Routes |
|---|---|---|---|---|---|---|---|
| Gemini Omni 1.1 Flash | gemini-omni-1.1-flash | text to video, image to video, first and last frames, reference images | 360p, 720p, 1080p, 4K | 4, 6, 8 or 10 s | up to 10 | $0.04 / s | two routes |
| Gemini Omni | gemini-omni | text to video, image to video | 720p, 1080p, 4K | 4, 6, 8 or 10 s | one start frame | $0.10 / s | one route |
| Gemini Omni Flash Preview | gemini-omni-flash-preview | text to video, image to video, reference images | 720p | model default | up to 16 | $0.11 / s | one route |
For most work, start with Gemini Omni 1.1 Flash. It does the most (first and last frames, up to ten references), has two routes, and its 360p setting at $0.04 per second is a cheap way to test a prompt before rendering it properly.
Gemini Omni pricing (October 2026)
All three are billed per second of output, with sound included.
| Model | Resolution | Per second | 4 s clip | 8 s clip | 10 s clip |
|---|---|---|---|---|---|
| Gemini Omni 1.1 Flash | 360p | $0.04 | $0.16 | $0.32 | $0.40 |
| Gemini Omni 1.1 Flash | 720p or 1080p | $0.10 | $0.40 | $0.80 | $1.00 |
| Gemini Omni 1.1 Flash | 4K | $0.23 | $0.92 | $1.84 | $2.30 |
| Gemini Omni | 720p or 1080p | $0.10 | $0.40 | $0.80 | $1.00 |
| Gemini Omni | 4K | $0.23 | $0.92 | $1.84 | $2.30 |
| Gemini Omni Flash Preview | 720p | $0.11 | $0.44 | $0.88 | $1.10 |
720p and 1080p cost the same on both Gemini Omni and 1.1 Flash, so ask for 1080p. Gemini Omni and 1.1 Flash clips are 16:9 or 9:16. To see how these prices sit against other video models, read the cheapest video API guide; for Google's other video model, see Veo 3.1 API pricing.
Generate a Gemini Omni 1.1 Flash clip
Send POST /v1/generations, then poll until the job has succeeded or failed. This 8 second 1080p vertical clip costs $0.80.
export REVANA_API_KEY="sr_live_..."
# 1. Submit the job (returns 202 with the generation id)
curl https://api.revana.si/v1/generations \
-H "Authorization: Bearer $REVANA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "A chef plates a dessert in a busy restaurant kitchen, then slides it across the pass toward the camera. Clatter of pans, a ticket printer, someone calls service.",
"resolution": "1080p",
"duration": 8,
"aspect_ratio": "9:16"
},
"max_cost_usd": 1
}'
# 2. Poll with the id from step 1 until status is "succeeded" or "failed"
curl https://api.revana.si/v1/generations/gen_01JC2V8K5T \
-H "Authorization: Bearer $REVANA_API_KEY"import os
import time
import requests
API = "https://api.revana.si/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['REVANA_API_KEY']}"}
resp = requests.post(f"{API}/generations", headers=HEADERS, json={
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "A chef plates a dessert in a busy restaurant kitchen, then slides it across the pass toward the camera. Clatter of pans, a ticket printer, someone calls service.",
"resolution": "1080p",
"duration": 8,
"aspect_ratio": "9:16",
},
"max_cost_usd": 1,
})
resp.raise_for_status()
job = resp.json()
while job["status"] in ("queued", "running"):
time.sleep(5)
job = requests.get(f"{API}/generations/{job['id']}", headers=HEADERS).json()
if job["status"] == "succeeded":
print(job["output"]["urls"], job["cost_usd"])
else:
print("Failed:", job["error"])// Node 18 or later. Save as generate.mjs and run: node generate.mjs
const API = "https://api.revana.si/v1";
const headers = {
Authorization: `Bearer ${process.env.REVANA_API_KEY}`,
"Content-Type": "application/json",
};
const res = await fetch(`${API}/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "gemini-omni-1.1-flash",
input: {
prompt: "A chef plates a dessert in a busy restaurant kitchen, then slides it across the pass toward the camera. Clatter of pans, a ticket printer, someone calls service.",
resolution: "1080p",
duration: 8,
aspect_ratio: "9:16",
},
max_cost_usd: 1,
}),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
let job = await res.json();
while (job.status === "queued" || job.status === "running") {
await new Promise((r) => setTimeout(r, 5000));
job = await (await fetch(`${API}/generations/${job.id}`, { headers })).json();
}
if (job.status === "succeeded") console.log(job.output.urls, job.cost_usd);
else console.error("Failed:", job.error);{
"id": "gen_01JC2V8K5T",
"model": "gemini-omni-1.1-flash",
"status": "succeeded",
"output": {
"urls": [
"https://cdn.revana.si/g/gen_01JC2V8K5T/0.mp4"
],
"duration_s": 8,
"has_audio": true
},
"cost_usd": 0.8,
"attempts": 1,
"error": null,
"created_at": "2026-10-28T10:14:02Z",
"completed_at": "2026-10-28T10:15:31Z"
}Start on one frame and end on another
Gemini Omni 1.1 Flash can move between two pictures you send: the start in image_url and the end in end_image_url. This 6 second 720p clip costs $0.60:
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "The flower bud slowly opens into a full bloom as morning light moves across it.",
"image_url": "https://example.com/bud.jpg",
"end_image_url": "https://example.com/bloom.jpg",
"resolution": "720p",
"duration": 6,
"aspect_ratio": "16:9"
},
"max_cost_usd": 0.8
}Sound is always made with the picture on these models and is included in the price, so leave the audio field out. A length other than 4, 6, 8 or 10 seconds is refused before anything is charged.
All three are on the models page, every field is in the docs and credit packs are on the pricing page. Get an API key to start.
Frequently asked questions
How much does the Gemini Omni API cost?
In October 2026, Gemini Omni 1.1 Flash costs $0.04 per second at 360p, $0.10 at 720p or 1080p and $0.23 at 4K, with sound included.
Which Gemini Omni model should I use?
Gemini Omni 1.1 Flash for most work: it takes text, a start frame, first and last frames or up to 10 reference images, from 360p to 4K. Gemini Omni Flash Preview takes up to 16 references at 720p.
How long can a Gemini Omni clip be?
4, 6, 8 or 10 seconds on Gemini Omni and Gemini Omni 1.1 Flash.
Does Gemini Omni make sound?
Yes. Sound is generated with the picture and included in the price.
What aspect ratios does Gemini Omni support?
16:9 for landscape and 9:16 for vertical video.
Try Gemini Omni with one key
One API key for every Gemini Omni model and every other video and image model. Prepaid credit from $10, charged only for clips that are delivered.