Eight 6-second room clips on Omni Flash: $18.00 at 4K, $6.00 at 720p

Price a real estate listing tour of eight 6-second room clips on Sume's gemini-omni-flash-1.1: $6.00 at 720p, $9.00 at 1080p, $18.00 at 4K.

5 min readSume
All posts

Eight 6-second room clips from listing photos on Sume's gemini-omni-flash-1.1 cost $6.00 at 720p, $9.00 at 1080p and $18.00 at 4K, before the Timeline render that joins them. Each clip is 6 seconds times the per-second rate: $0.125, $0.1875 or $0.375. The model accepts 3 to 10 seconds in 16:9 or 9:16 and always has native audio.

The arithmetic by resolution

Sume's catalog lists gemini-omni-flash-1.1 at $0.0375 per output second at 360p, $0.125 at 720p, $0.1875 at 1080p and $0.375 at 4K (read 2026-10-09 against the catalog). One 6-second room clip is 6 times the rate, and eight clips multiply by eight.

The joined tour is 48 seconds. Timeline 1.0 bills $0.10 per output minute rounded up, so a 48-second tour is one billed minute, $0.10, on top of the clip cost.

Eight 6-second clips by resolution, Sume list prices read 2026-10-09
ResolutionPer secondOne 6 s clipEight clipsWith $0.10 render
360p$0.0375$0.225$1.80$1.90
720p$0.125$0.75$6.00$6.10
1080p$0.1875$1.125$9.00$9.10
4K$0.375$2.25$18.00$18.10

Which resolution to buy

A listing tour usually plays on a phone, and the delivery platform sets the pixel need. A 720p clip is enough for a vertical social post. Spend on 4K only if the clip will be shown on a large screen or cropped hard. A practical pattern is to draft all eight rooms at 360p for $1.80, pick the rooms that hold up, and rerun only those at a higher tier.

Omni Flash takes image input references, so each clip starts from a real room photo. The prompt should say what moves, such as a slow push in, and nothing that changes the room, because a buyer will compare the clip with the photos.

Assembling the tour

Import the eight clips to your workspace, set audio.duration_seconds to 48 and add a spine. Because the clips carry native audio, decide whether to keep it or lay a voiceover or music track over the render. Generated audio under a property tour can talk about things the photos do not show, so listen before you publish.

Sume does not decide disclosure rules for AI-edited listing media. Check your local MLS and platform requirements, and keep original photos linked alongside the generated clip.

A practical note

If a room fails, the retry cost is one clip, not the tour. A failed 4K take costs $2.25, while a failed 720p take costs $0.75, which is why the draft-then-final routine pays: eight 360p drafts are $1.80, and rerunning only the three best rooms at 4K is 3 times $2.25, or $6.75. Order the rooms the way a buyer walks the home, entry first, and keep the same time of day in every prompt so the tour does not jump between morning and evening light.

Before you scale

Every price in this post is a Sume list price read from the public catalog on 2026-10-09, and the arithmetic is shown so you can redo it with your own counts. Rates can change, so re-read the catalog before a large batch and run a small test first. Sume bills the job's captured amount, and the job result tells you what was used, so compare the first run's receipt with your estimate before you scale the work to the full set.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume