Claymation look test: four Sume video models at low resolution
Test a claymation prompt on Omni Flash 1.1, Wan 3.0, H3 and Seedance 2.0 Mini for under $1.20 in drafts, then price the finals at 1080p before committing.

To test a claymation look, run the same prompt on four Sume models at their lowest resolution: gemini-omni-flash-1.1 at 360p for $0.15, wan-3.0 at 480p for $0.25, minimax-h3 at 480p for $0.32 and seedance-2-mini at 480p for $0.35. That is $1.07 for a four-model comparison of 4-to-5-second clips, before you spend anything on a final.
Sume does not publish a ranking of which model renders a style best, so this post only prices the test. The limits and rates come from the Video Router page, read 2026-10-06, and each row below is the catalog rate times 1.25, rounded up to the cent.
What does the draft pass cost?
Each model is at its lowest listed resolution and shortest clip that fits its minimum (Omni 3 s and up, Wan 2 s and up, Seedance 4 s and up, H3 5 s and up). I used 4 seconds except H3, whose minimum is 5.
| Model id | Resolution | Length | Sume price | Note |
|---|---|---|---|---|
| gemini-omni-flash-1.1 | 360p | 4 s | $0.15 | |
| wan-3.0 | 480p | 4 s | $0.25 | |
| minimax-h3 | 480p | 5 s | $0.32 | H3 minimum is 5 s |
| seedance-2-mini | 480p | 4 s | $0.36 |
What would the finals cost?
If one draft nails the clay texture, repeat it at a higher rung. The same 4-second clip at 1080p is $0.75 on Omni Flash 1.1 and $1.00 on Wan 3.0. H3 tops out at 768p, so pick it only if its draft already looks final.
| Model id | Resolution | Length | Sume price | Note |
|---|---|---|---|---|
| gemini-omni-flash-1.1 | 1080p | 4 s | $0.75 | |
| wan-3.0 | 1080p | 4 s | $1.00 | |
| minimax-h3 | 768p | 5 s | $0.38 | highest H3 rung |
| seedance-2.5 | 1080p | 4 s | $5.69 | higher-tier Seedance |
How should I word the test?
Use one prompt for all four, name the material (hand-sculpted clay, visible thumbprints, stop-motion jitter) and the camera in the same sentence, and send it as text-to-video so no first frame biases the result. A claymation restyle of footage you already have is a different job: that is Omni Flash's video edit mode, which takes a video_url.
Sources
Related posts
More in Models
- Exact 16:9 sizes on GPT Image 2.5: 1280x720, then steps of 256
Only widths that are multiples of 256 give an exact 16:9 box GPT Image 2.5 accepts. 1280x720 is the smallest; 1024x576 and 1920x1080 both fail.
- Omni Flash or Veo 3.1 for the Gemini API? What Sume runs
Google's video docs now call Omni Flash the default over Veo 3.1. Here are Google's listed prices for both, and which one Sume's video router carries.
- Gemini Omni scene extension: app, Flow, API or Sume?
Google's launch post lists four places Omni 1.1 Flash runs. Scene extension is not in all of them, and Sume's router does not expose it. Where to go instead.
- gpt-image-1 retires December 1: scan your repo, move to gpt-image-2.5
OpenAI's deprecations page lists gpt-image-1, 1.5 and 1-mini for December 1, 2026. A Python scan finds the ids, and Sume serves openai/gpt-image-2.5.
Written by Sume