H3 Max lip sync resolutions on Sume: 480p, 768p, 1080p, no 2K

Sume's H3 Max lip sync offers 480p, 768p (default) and 1080p, no 2K. At the documented list times 1.25 that is $0.0625, $0.10 or $0.20 per second.

5 min readSume
All posts

Sume's MiniMax H3 Max lip sync takes resolution of 480p, 768p (default) or 1080p, and refuses 2K. The doc's provider list is $0.05, $0.08 and $0.16 per second (fal page, 2026-09-22), and Sume bills ceil(duration_seconds) times that times 1.25, which works out to $0.0625, $0.10 and $0.20 per second. A 5 second clip at 768p reserves $0.50.

From docs/api/minimax-h3-max-lip-sync.md on origin/main b28f3b0 (read 2026-10-13); the per-second Sume figures are the doc's formula applied to its list rates.

H3 Max lip sync per second, list times 1.25 (read 2026-10-13)
ResolutionProvider list per secondSume per second5 s clip14.8 s clip (billed as 15 s)
480p$0.05$0.0625$0.3125$0.9375
768p (default)$0.08$0.10$0.50$1.50
1080p$0.16$0.20$1.00$3.00

Is the amount reserved or captured?

Both: the API reserves it at admit, captures it on completion and refunds it on failure. POST /v1/generation/admission-preview accepts the public id minimax/h3-max/lip-sync so you can see the amount first. The rate card id is fal_minimax_h3_max_lip_sync_2026-09-22.

Why would I pick 480p?

Cost and drafts: a 480p pass is 37.5% cheaper than 768p per second. Review the lip movement at 480p, then render the approved audio at 1080p. Keep the audio_url the same file so the waveform matches; the reservation uses duration_seconds, which must stay between 5 and 14.8.

Sources

Related posts

More in Pricing

All Pricing posts

Written by Sume