Cheap AI video drafts: which models start at 480p or lower on Sume
Seedance, Wan 3.0, MiniMax H3 and Grok Imagine start at 480p, Gemini Omni Flash at 360p, Kling 3 at 720p. Where a draft is possible before a 1080p final.
Gemini Omni Flash 1.1 has the lowest rung in Sume's video catalog at 360p; Seedance 2.5, the Seedance 2.0 rows, Wan 3.0, MiniMax H3, MiniMax H3 Max, Grok Imagine and Genjutsu start at 480p; Kling 3 starts at 720p, so it has no draft tier. Draft on the lowest rung, then rerun only the prompts that worked.
Lowest and highest resolution per model
Resolution steps change price. Wan 3.0 lists at $0.05, $0.10 and $0.20 per second at 480p, 720p and 1080p (list price on 2026-08-24, subject to change), so a 1080p clip is four times a 480p one at list before Sume's multiplier.
| Model id | Lowest | Highest |
|---|---|---|
| gemini-omni-flash-1.1 | 360p | 4K |
| seedance-2.5 and Seedance 2.0 rows | 480p | 1080p |
| wan-3.0 | 480p | 1080p |
| minimax-h3 | 480p | 768p native (2K and 4K upscales priced if requested) |
| minimax-h3-max | 480p | 1080p (latent refinement from native 768p) |
| grok-imagine-video-1.5 | 480p | 720p |
| kling-3 | 720p | 1080p |
A draft is a new take, not a preview
None of the v1 video models accepts a seed, so a 1080p rerun of a 480p draft generates a different clip. Treat the draft as a test of the prompt and the composition, then accept that the final needs its own review.
If you want the final to look like the draft, use the draft frame you like as the first frame of the final request on a model that takes one.
Sume's multiplier
The docs state that Sume bills provider list times 1.25 on every model and reserves on submit. The live price is in the pricing block of the model list, so quote from there before a batch.
Sources
Related posts
More in Models
- AI video audio by model: toggle, always on, or none on Sume
Seedance, Wan 3.0 and Kling 3 let you switch audio; MiniMax H3 and Gemini Omni Flash always make it; Grok Imagine has none. What each row does.
- How to choose an AI video model: five questions before you pin one
Length, resolution, audio, start image and references decide the model, not the leaderboard. Five questions mapped to Sume's video catalog.
- Which AI video models can't do text-to-video? Rows that need a source
Grok Imagine Video 1.5, Genjutsu Motion Transfer and H3 Max Recast refuse a prompt-only request. What each needs, and which rows accept text alone.
- AI video reference limits: how many images and clips per model
Reference image and reference video caps for Wan 3.0, MiniMax H3, Gemini Omni Flash, Genjutsu and H3 Max Recast on Sume, in one table with the odd limits.
Written by Sume