Gemini Omni Flash 1.1 clip cost on Sume, by length and resolution

Gemini Omni Flash 1.1 (gemini-omni-flash-1.1) bills by the second on Sume, at a rate set by resolution from 360p to 4K, with native synced audio always on and included. It takes clips of 3 to 10 seconds in 16:9 or 9:16, so a set of clips costs the per-clip price times the count.

Worked example: Gemini Omni Flash 1.1 3-second clip: 360p to 4K price

On Sume, a 3-second Gemini Omni Flash 1.1 (gemini-omni-flash-1.1) clip costs $0.1125 at 360p, $0.3750 at 720p, $0.5625 at 1080p and $1.1250 at 4K. Native synced audio is always on and included, and the model takes 3 to 10 seconds in 16:9 or 9:16.

The shape of the model comes from the Video Router docs (read 2026-10-06): 3 to 10 seconds, 360p/720p/1080p/4K, native audio that the API will not let you switch off.

What is the price per second at each resolution for 3 seconds?

Billing is per output second by resolution, at the provider list price times 1.25.

Which resolution should a draft use?

Draft at 360p or 720p and keep 1080p and 4K for the pick. The 4K clip costs 3 times the 720p one at 3 seconds, so a draft pass at 4K is the expensive way to choose between prompts.

curl -X POST https://api.sume.com/v1/video-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: omni-3s-720p-001" \
  -d '{
    "model": "gemini-omni-flash-1.1",
    "prompt": "A barista pours latte art, close-up, café ambience",
    "duration": 3,
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "mode": "async"
  }'

Every length and count in one table

This page replaces 11 posts that asked the same question with different numbers. Each row is one of them, with the answer it gave when it was published.