9-second MiniMax H3 vs H3 Max on Sume: 768p and 1080p costs
A 9-second clip is $0.68 on MiniMax H3 at 768p, $0.90 on H3 Max at 768p and $1.80 on H3 Max at 1080p. Only H3 Max has a 1080p tier on Sume.

On Sume a 9-second clip costs $0.675 on MiniMax H3 at 768p, $0.90 on H3 Max at 768p, and $1.80 on H3 Max at 1080p. Only H3 Max lists a 1080p tier. At 480p the two are the same price, $0.5625.
Per-second prices
Both models accept 5 to 15 seconds on Sume, so 9 seconds is in range. Prices are linear in seconds.
| Model | 480p | 768p | 1080p |
|---|---|---|---|
| minimax-h3 | $0.0625 ($0.5625) | $0.075 ($0.675) | not listed |
| minimax-h3-max | $0.0625 ($0.5625) | $0.10 ($0.90) | $0.20 ($1.80) |
The price of Max
At 768p, H3 Max costs 1.33 times H3, a premium of $0.225 on a 9-second clip. At 480p there is no premium, so a draft pass costs the same on either model. Going from H3 Max at 768p to 1080p doubles the cost, $1.80 against $0.90.
A reasonable sequence is a 480p draft at $0.5625, then a 768p or 1080p render of the keeper. Three drafts and one 1080p final cost $3.4875.
Where else H3 Max appears on Sume
Sume also lists MiniMax H3 Max Lip Sync at $0.10 per audio second at 768p, which is a separate job that animates a face to supplied audio. It does not change the generation prices above.
Pin either model with the model field on POST /v1/videos; limits per model come from GET /v1/videos/models. See the Video generation page and verify prices in the catalog before a large run. This page compares list prices and says nothing about output quality.
- Draft at 480p on either; same price.
- Need 1080p: H3 Max is the only one of the two.
- H3 at 768p is the cheaper final if 768p is enough.
Reproduce the numbers
Every Sume price on this page comes from the public catalog at https://api.sume.com/v1/catalog, which needs no API key. Fetch it, find the row for the job or model named in the table, and multiply by your own seconds, characters or image count. Sume bills the list price shown in that row, so the catalog figure is the one that applies to your balance.
All figures on this page are Sume's own, as of 2026-10-09. Prices and limits can change, so re-read the catalog and the linked docs before a large run, and keep the arithmetic in a spreadsheet so you can update it in a minute.
Sources
Related posts
More in Comparisons
- 90-minute webinar live captions: AssemblyAI bills open socket time
AssemblyAI bills streaming by open WebSocket time, not audio sent. A 90-minute webinar is $0.675 on U3.6 Pro Realtime; Sume STT has no live mode.
- A 60-second video from six 10-second clips: H3, Wan 3.0, Seedance
Six 10-second clips make a minute: $4.50 on MiniMax H3, $7.50 on Wan 3.0, $22.68 on Seedance 2 and $34.668 on Seedance 2.5, before retries.
- AssemblyAI diarization +$0.02/hour: a 12-hour panel vs Sume STT
AssemblyAI prices standard diarization at +$0.02 an hour on a $0.21 base. Twelve hours of panel audio is $2.76; Sume STT is $7.20 with no diarization field.
- AssemblyAI Universal-Streaming $0.15 vs 3.6 Pro $0.45: 250 hours
AssemblyAI lists Universal-Streaming at $0.15 an hour and Universal-3.6 Pro Realtime at $0.45, a 3x step. Over 250 session hours it is $37.50 against $112.50.
Written by Sume