MiniMax H3 Max 1080p: a latent refinement from native 768p
MiniMax H3 Max on Sume offers 480p, 768p and 1080p. The 1080p tier is a latent refinement from native 768p. What that means for price and output checks.

MiniMax H3 Max can return 1080p on Sume, but Sume's docs describe that tier as a latent refinement from native 768p: the clip is generated at 768p and refined, not rendered natively at 1080p. Ask for it with model: "minimax-h3-max" and resolution: "1080p"; minimax-h3 refuses 1080p.
Sume facts are from its Video generation and Video Router docs and pricing code; vendor listings from fal's page and MiniMax's API docs, read 2026-09-29.
What does 1080p cost?
Per output second, higher than 768p. Sume bills the provider list × 1.25, plus the 5.5% agent fee by default.
| Resolution | 10 seconds |
|---|---|
| 480p | $0.63 |
| 768p | $1.00 |
| 1080p | $2.00 |
Do the vendors list 1080p for H3 Max?
fal's model page lists 480p, 768p and 1080p for H3 Max. MiniMax's own API docs list only 480P and 768P for it. Sume lists 1080p for minimax-h3-max and documents it as the refinement described above.
How should I check a 1080p clip?
Look at the opening frames. Sume's catalog notes for H3 Max say some 1080p image-to-video outputs have a crop jump after the first two frames. Only when you confirm one, the notes suggest starting the clip at its first stable frame (2/24 seconds for the 24 fps clips observed). Inspect the raw clip before you trim anything.
Should I use 768p instead?
If the delivery target is a phone or a feed, 768p may be enough and costs less per second. Use 1080p when the platform or client requires it. Compare a 768p and a 1080p clip of the same prompt before you commit a batch.
Sources
Related posts
More in Models
- MiniMax H3 Max lip sync API: a still plus audio, 5 to 14.8 seconds
Sume runs MiniMax H3 Max lip sync at POST /v1/minimax/h3-max/lip-sync: send a still and Sume-hosted audio of 5 to 14.8 seconds. Body, resolutions and price.
- AI video with native stereo sound: MiniMax H3 audio through the API
MiniMax H3 generates native stereo sound in the same pass as the video. On Sume audio is always on, generate_audio false is refused, and audio steers.
- MiniMax H3 open weights on Hugging Face: what is in the release
MiniMax H3 has a model card on Hugging Face: two checkpoints, a 33B-parameter Transformer, a community license and a 4-GPU serving example. What to check first.
- AI video editing with a text prompt: MiniMax H3 and Sume's edit path
MiniMax H3 is described as editing existing video from instructions. What the vendor says, what Sume's H3 ids accept, and the id with an edit field.
Written by Sume