Edit or regenerate an Omni clip? The per-second price is the same
On Sume, Gemini Omni Flash 1.1 edit mode and a fresh generation bill the same per output second. Compare three tries of each at 720p and pick by continuity.

Editing a clip with Gemini Omni Flash 1.1 and generating a new one cost the same per output second on Sume, so the decision is about continuity, not money. If the clip is right except for one object or one effect, edit; if the composition is wrong, regenerate. The docs bill both as the provider list times 1.25 per output second, by resolution.
What each path sends
A regeneration sends a prompt, optionally with an image or references, plus duration and aspect_ratio. An edit sends video_url and a prompt with the instructions, and takes no aspect_ratio or duration. You cannot mix video_url with image_url or reference fields.
If you need to change length or ratio, an edit cannot do it. That is a regeneration.
| Question | Edit | Regenerate |
|---|---|---|
| Keeps the original shot | yes | no |
| Can change duration | no | yes, 3 to 10 s |
| Can change aspect ratio | no | 16:9 or 9:16 |
| Resolution | optional, default 720p | 360p to 4K |
| Price basis | output seconds x rate | output seconds x rate |
Three tries of each
Take a 6-second result at 720p: 6 x 12.5 = 75 cents per try. Three edits are $2.25 and three regenerations are $2.25. The money is equal, so what you pay for is the chance of keeping the parts that already work.
Sume rounds each clip up to the next whole cent, so a clip total is ceil(seconds x rate), not a sum of fractional cents.
A regeneration has no seed to repeat, since the Sume docs say no v1 video model accepts a seed. A second try can change everything. An edit is more likely to preserve the clip, which is its main value.
A rule of thumb
Edit when the change is local: swap an object, add steam, change a colour. Regenerate when the idea or the framing fails. For the first, the prompt pattern in the docs is short: name the change and then say to keep everything else the same.
Whichever path you take, test at 360p first if the clip is long. Six seconds at 360p is 23 cents.
The same length at every tier
For reference, a 6-second Omni Flash clip at each resolution. Every price is the seconds times the billable rate, rounded up to a whole cent, as of 2026-10-08.
| Resolution | Arithmetic | Billed |
|---|---|---|
| 360p | 6 x 3.75 = 22.5 cents | $0.23 |
| 720p | 6 x 12.5 = 75 cents | $0.75 |
| 1080p | 6 x 18.75 = 112.5 cents | $1.13 |
| 4K | 6 x 37.5 = 225 cents | $2.25 |
Limits to remember
These apply to every request on this page, from the Video Router and Video generation docs:
- Length is 3 to 10 whole seconds in generation modes; an edit takes no duration.
- Aspect ratio is 16:9 or 9:16; an edit takes no aspect ratio.
- Native synced audio is always on, and
generate_audio: falseis rejected. - There is no
bitrate_mode, no reference audio and noseed. - Billing is the provider list times 1.25 per output second, reserved at submit and shown in
usage.cost.
Sources
Related posts
More in Developers
- Elixir Req: submit and poll a Sume video job after Sora
An Elixir script using Req: POST /v1/videos with an Idempotency-Key, poll every 30 seconds, stop on completed, failed or cancelled. Req never retries the POST.
- Env and secrets diff for removing Sora: SUME_API_KEY, one auth header
Which environment variables to delete, add and rotate when a service leaves the OpenAI Videos API for Sume, plus a startup check that fails on a missing secret.
- Extract 16 kHz mono audio from a video for transcription
A Python script that detaches speech-ready 16 kHz mono wav from a Sume-hosted video, then polls the job. Costs $0.01 per detach before the STT minute.
- Face swap request in Python: validate the video URL before you send
A Python snippet that rejects non-HTTPS, localhost and private-IP video URLs locally, then submits a Sume face-swap beta run with a quality and idempotency key.
Written by Sume