Neon cyberpunk street at 1080p for 10 seconds: five Sume models
A 10-second 1080p cyberpunk street clip costs $1.40 to $2.50 on Kling 3, Omni Flash 1.1, H3 Max and Wan 3.0 on Sume; Seedance 2.5 is $14.22.

A 10-second 1080p clip costs $1.40 on kling-3 without sound, $1.88 on gemini-omni-flash-1.1, $2.00 on minimax-h3-max, $2.10 on kling-3 with sound, $2.50 on wan-3.0 and $14.22 on seedance-2.5. Those are Sume billable prices for a 16:9 request: the catalog rate times 1.25, rounded up to the cent.
Two of those rows need a caveat. H3 Max's 1080p is a latent refinement of its native 768p render, not a native 1080p pass, and Omni Flash 1.1 is limited to 3-to-10-second 16:9 or 9:16 clips, so 10 seconds is its ceiling. See the Video Router page, read 2026-10-06.
What is the price table?
One request shape for every row: 10 seconds, 1080p, 16:9.
| Model id | Resolution | Length | Sume price | Note |
|---|---|---|---|---|
| kling-3 | 1080p | 10 s | $1.40 | silent |
| gemini-omni-flash-1.1 | 1080p | 10 s | $1.88 | 10 s is the ceiling |
| minimax-h3-max | 1080p | 10 s | $2.00 | latent refinement from 768p |
| kling-3 | 1080p | 10 s | $2.10 | with sound |
| wan-3.0 | 1080p | 10 s | $2.50 | |
| seedance-2.5 | 1080p | 10 s | $14.22 |
How do I decide?
Neon scenes put sharp light on dark water and glass, which is where a cheap draft and a final can differ most. Draft the shot at 480p on wan-3.0 for $0.63, pick the take whose camera move you like, then re-run the winner at 1080p. The per-resolution rungs on each id are in GET /v1/videos/models, so a script can read the price instead of trusting this table.
curl -sS -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3.0",
"prompt": "Rain-soaked neon street at night, slow dolly forward, reflections on wet asphalt",
"duration": 10,
"resolution": "1080p",
"aspect_ratio": "16:9"
}'What about sound?
Kling 3 has a generate_audio toggle, and the price difference is $0.70 for 10 seconds. Omni Flash 1.1 and H3 Max always return audio. If you only want ambience, that is already included on those two.
Sources
Related posts
More in Models
- New AI video models since February 2026: dates and which Sume lists
Kling 3.0, Seedance 2.5, MiniMax H3 and LTX-2.5 launched in 2026. Release dates, length limits and which of them Sume's video catalog lists today.
- Omni Flash edit on Sume: what editing a 6 s and a 30 s clip costs
Editing a clip with Omni Flash on Sume bills per output second at the resolution you pick: $0.75 for 6 s at 720p, up to $3.75 for a 30 s hint. How it is priced.
- Retired AI model id to Sume id: GPT Image, Gemini and Sora lookup
One lookup table that maps retired gpt-image-1, gemini-2.5-flash-image and sora-2 ids to Sume ids, with dates, so a failing call tells you what to switch to.
- Seedance 2.5 API: Seed blog says soon, BytePlus says live
Two ByteDance pages disagree on Seedance 2.5 API access. Here is what each says, and the seedance-2.5 id that runs on Sume's video router today.
Written by Sume