Gemini Omni 4K clip cost: a 10-second render is $3.75 on Sume
A 10-second Gemini Omni 4K clip lists at $3.00 on Sume's catalog and bills $3.75 after the 1.25 multiplier. Here is every resolution with the rounding shown.

A 10-second Gemini Omni Flash 1.1 clip at 4K costs $3.00 at the provider list rate of $0.30 per second, and Sume bills $3.75 because it charges list times 1.25. The 360p, 720p and 1080p tiers for the same 10 seconds bill $0.38, $1.25 and $1.88.
The rate card
Sume's Video Router doc lists gemini-omni-flash-1.1 at 360p, 720p, 1080p and 4K, for 3 to 10 seconds, with list prices of $0.03, $0.10, $0.15 and $0.30 per second (fal list, 2026-08-28). Billing uses list times 1.25, rounded up to cents, on each row. The default resolution is 720p and the default duration is 8 seconds.
| Resolution | List per second | 10 s list | 10 s x 1.25 | Billed (cents up) |
|---|---|---|---|---|
| 360p | $0.03 | $0.30 | $0.375 | $0.38 |
| 720p | $0.10 | $1.00 | $1.25 | $1.25 |
| 1080p | $0.15 | $1.50 | $1.875 | $1.88 |
| 4K | $0.30 | $3.00 | $3.75 | $3.75 |
Sending 4K
The API sends 4K to the provider as its enum value 4k, and for this model only it also accepts a lowercase 4k alias. Duration and resolution go in the normal /v1/videos body. Omni takes 16:9 or 9:16 only, so any other aspect ratio is a 400.
import os, requests
body = {
"model": "gemini-omni-flash-1.1",
"prompt": "A glass sphere rolls down a marble staircase. In a single continuous shot.",
"duration": 10,
"resolution": "4K",
"aspect_ratio": "16:9",
}
r = requests.post(
"https://api.sume.com/v1/videos",
json=body,
headers={
"Authorization": f"Bearer {os.environ['SUME_API_KEY']}",
"Idempotency-Key": "omni-4k-demo-001",
},
timeout=60,
)
print(r.status_code, r.json())
What happens to the money
Sume reserves the estimated cost from the workspace balance when you submit. If the balance cannot cover a $3.75 reserve, the response is 402 insufficient_credits and no job starts. When the job completes, the poll response reports usage.cost as the billable amount. Webhooks and polling are both covered in the Videos guide.
A render ladder
The ladder cost for one keeper is $0.38 + $1.25 + $3.75 = $5.38, against $3.75 if you went straight to 4K, so a ladder only pays when it avoids at least one wasted 4K attempt.
- Draft at 360p for $0.38 per 10 seconds to test the idea.
- Review at 720p for $1.25 to judge motion and audio.
- Approve at 1080p for $1.88 if the platform caps at that size.
- Spend on 4K only for hero assets, at $3.75 per 10 seconds.
A cheaper way to find a good take
Four 4K attempts cost $15.00, while four 720p attempts cost $5.00. Iterate at 720p, fix the prompt, then render the keeper once at 4K. Because the edit path and the generate path share the same catalog row, the rate card above also prices a 10-second 4K edit when the source clip is 10 seconds, though the edit reserve is a hint and not a probe of the output length.
Sources
Related posts
More in Pricing
- Omni video edit on Sume: the 8-second default holds $1.00 at 720p
Omni edit takes its length from your source clip, but the reserve uses an 8-second hint unless you send duration. At 720p that hold is $1.00 on Sume.
- Omni Flash on Sume: a 4K clip of 3 s is $1.13, 1080p of 10 s $1.88
Gemini Omni Flash 1.1 offers native 4K on Sume's Video Router. A 3-second 4K clip costs $1.13; a 10-second 1080p clip $1.88. How to pick resolution by use.
- Gemini Omni Flash pricing: Google quotes 720p; Sume lists four rows
Google's Gemini API pricing page gives Omni Flash video as $17.50 per 1M tokens, about $0.10 a second at 720p. Sume lists 360p, 720p, 1080p and 4K rows.
- gpt-image-1 low, medium, high on GPT Image 2.5: Sume prices
Moving from gpt-image-1 to GPT Image 2.5 keeps low, medium and high and adds xhigh and max. Sume's price per tier at 1024x1024 and what omitting quality bills.
Written by Sume