Drop to 480p: Fabric saves 46.7 percent, H3 lip-sync 37.5 percent
Fabric is $0.10 at 480p against $0.1875 at 720p. H3 Max lip-sync is $0.0625 at 480p against $0.10 at 768p. Savings on 250 clips inside.

Moving a Fabric job from 720p to 480p cuts the per-second rate from $0.1875 to $0.10, a saving of 46.7 percent. Moving H3 Max lip-sync from 768p to 480p cuts it from $0.10 to $0.0625, a saving of 37.5 percent. Both are per whole audio second and use the rates in the Sume catalog.
The percentages
Fabric: ($0.1875 - $0.10) / $0.1875 = 0.4667. H3 Max lip-sync: ($0.10 - $0.0625) / $0.10 = 0.375. The Models overview names both routes, and the rates come from the API pricing page.
What it saves on real batches
The table prices a fixed 8 second clip at each resolution, then a batch of 250.
| Route and resolution | Rate per second | One 8 s clip | 250 clips |
|---|---|---|---|
| Fabric 720p | $0.1875 | $1.50 | $375.00 |
| Fabric 480p | $0.10 | $0.80 | $200.00 |
| H3 Max lip-sync 1080p | $0.20 | $1.60 | $400.00 |
| H3 Max lip-sync 768p | $0.10 | $0.80 | $200.00 |
| H3 Max lip-sync 480p | $0.0625 | $0.50 | $125.00 |
Choosing
The 250 clip saving is $175.00 for Fabric (from $375.00 to $200.00) and $75.00 for H3 Max between 768p and 480p (from $200.00 to $125.00). Check a few 480p outputs on the real display size. A clip shown in a small phone card may not need 720p, and a clip shown full screen likely does.
The two routes have different input windows. Fabric accepts up to 300 seconds of audio, while H3 Max lip-sync takes 5 to 14.8 seconds, so the cheaper rate does not help if your audio is a different length.
Mixing resolutions in one batch
You do not have to pick one resolution for a whole project. Render drafts and thumbnails at 480p and re-run only approved clips at 720p. For 250 eight second clips where 20 percent are approved, the cost is 250 x $0.80 + 50 x $1.50 = $200.00 + $75.00 = $275.00, against $375.00 for 250 clips at 720p straight away.
The first pass stays cheap, and the second is paid only for the clips that survive review. This works because each job is priced independently by its own resolution.
- Fabric 480p: $0.10 per audio second.
- Fabric 720p: $0.1875 per audio second.
- H3 Max lip-sync 1080p: $0.20 per audio second.
Which one to choose
Fabric turns a still image and audio into a talking clip of up to 300 seconds. H3 Max lip-sync takes a still and 5 to 14.8 seconds of audio. For a 10 second reply, Fabric at 480p is $1.00, and H3 Max at 480p is $0.625. For a 60 second explainer, only Fabric fits, at $6.00 (480p) or $11.25 (720p).
Sources
Related posts
More in Pricing
- A 61-second audio spine reserves 2 timeline minutes, 60 s reserves 1
Timeline 1.0 reserves $0.10 per ceil(audio minute). A 60 second spine reserves $0.10, 61 seconds reserves $0.20, and 1,800 seconds is the $3.00 ceiling.
- Amazon video at 30, 60 or 90 seconds: Sume jobs per model and cost
Amazon says its best shoppable videos run 30 to 90 seconds. On Sume that is 3 to 9 jobs depending on the model, from $3.75 to $52.02 for 90 seconds.
- Avatar video cost at 4, 8, 15, 30 and 60 seconds on three tiers
Avatar video costs $0.74 to $11.04 on standard, $0.98 to $14.70 on plus and $2.20 to $33.00 on max across the 4 to 60 second window, no product.
- Budgeting 100 Omni Flash clips with a mixed-resolution plan
A 100-clip Gemini Omni Flash plan across four resolutions costs $56.125 on Sume, versus $150.00 if every clip were an 8-second 1080p render.
Written by Sume