How much does a holiday catering promo reel with six dishes cost?
Six dish photos animated 5 seconds each, a voice, music and price captions: $4.235 for a 30-second catering reel on Sume at 720p, or $1.14 for the drafts.

A 30-second holiday catering reel with six dishes costs $4.235 on Sume at 720p: six 5-second gemini-omni-flash-1.1 clips at $0.63 each ($3.78), a 480-character voice ($0.03), a music bed ($0.125), one render ($0.10) and one caption job for dish names and prices ($0.20). The drafts at 360p cost $0.19 a clip, $1.14 for all six. Rates were read on 2026-10-07.
Catering orders are bigger than takeout orders and are decided by a few people, so the reel has to show the food, say the minimum order and how far ahead to book, and give one way to reach you.
One photo per dish, one clip per photo
Photograph each dish in the same light and from the same angle, so six clips feel like one menu. Pass each photo as a first frame. The prompt should describe a small motion that suits the dish: steam from a tray of roast vegetables, a serving spoon lifting a portion, a pour of gravy. The model fills in the movement, and your photo fixes how the food looks at the start.
Each clip is a separate job with its own Idempotency-Key. Submit them in a loop and poll them together. If one dish comes out wrong, you re-run that one at about 63 cents and do not repeat the other five.
Draft cheap, finish dear
At 360p a 5-second clip is $0.19. Run all six there first and read them on a phone. Keep the ones that move well and re-run only the keepers at 720p or 1080p. A 1080p 5-second clip is $0.94; at 4K it is $1.88. For a social reel on a phone, 720p is the sensible default.
A fair plan is six drafts ($1.14) plus four finals at 720p ($2.52), which is $3.66 before the voice and render. That is cheaper than six finals if you expect to drop two.
Voice, prices and render
About 480 characters covers six dishes at 80 characters each, with no room for an intro, so keep the dish lines short and put the contact in a caption. At $0.0475 per 1,000 characters the voice is $0.03. Render with the voice as audio.url (30 seconds), the six clips in video[] at 0, 5, 10, 15, 20 and 25 seconds, and the bed as a ducked soundtrack. The render is $0.10.
Use caption cues for dish names, the per-person price and the booking lead time. Prices belong in captions, since a caption is text you wrote and not text a model drew. One caption job covers the whole reel for $0.20.
What a catering reel has to say
A viewer deciding on catering asks four things: what is on the menu, how many does it feed, how much notice do you need, and how do I book. The reel answers the first with pictures, and the rest with captions. Put the booking lead time and the minimum order in the last two seconds, in the largest text, with one contact method.
Name the dishes in the order of the menu card, so the reel and the printed menu agree. If a dish has a common allergen, say so on the menu page the reel points to. A 30-second reel is not the place for the full allergen list, but it must not contradict it.
Keep a record per reel: the six prompts, the six job ids and the final usage.cost of each. The next holiday's reel starts from the same prompts with new photos, and the record tells you what a retake really cost you.
Reuse across the season
Catering demand runs from early November to the last week of December, and the same six clips can be cut three ways. A 15-second cut uses the best three clips (three slots of 5 seconds, still one started render minute). A 9:16 reel and a 16:9 version for your website differ only in the render's output size, and the clips can be generated once in each ratio that Omni supports. Change the caption cues to the offer of the week, and re-render at $0.10 and re-caption at $0.20.
Totals
- Omni clips run 3 to 10 seconds. Six clips at 5 seconds fills a 30-second render exactly.
- A second menu for another event reuses the bed and costs $4.11.
- Read
usage.coston each job poll to confirm the billed amount.
| Step | Unit | Price | This reel |
|---|---|---|---|
| gemini-omni-flash-1.1, 720p, 5 s | per clip | $0.63 | $3.78 |
| TTS, 480 characters | per 1,000 characters | $0.0475 | $0.03 |
| Music Router bed | per track | $0.125 | $0.125 |
| Timeline 1.0 render | per started minute | $0.10 | $0.10 |
| Caption cues | per job | $0.20 | $0.20 |
| Total | $4.235 |
Sources
Related posts
More in Pricing
- Test six ad hooks with 4-second avatar clips on standard: cost
Six 4-second hook clips on Sume's standard avatar tier cost $4.42 without a product image, $4.66 with one. The 4-second floor and how to run the test.
- Is a 4:5 render cheaper than 9:16 in Timeline? Same $0.10 a minute
Timeline bills output minutes, not pixels: 1080x1350 and 1080x1920 both cost $0.10 per ceil minute. See what changes instead: crop, fit, and file size.
- YouTube ad length by format, and what each costs to render in Timeline
Bumper 6 s, non-skippable 15 to 60 s, Shorts under 60 s, skippable with no max. Google's lengths mapped to Sume Timeline billable minutes and cost.
- How Sume pricing works: plans, one wallet, published model rates
Sume plans set access and concurrency. Usage draws from one prepaid wallet at each model's published USD rate, for generation, the Agent, Formats, and the API.
Written by Sume