24 exercise demo clips on MiniMax H3: 5 s each, $9.00 at 768p
A fitness app with 24 exercises at 5 seconds each costs $9.00 on MiniMax H3 at 768p, $7.50 at 480p and $12.00 on H3 Max, priced on Sume. Body and limits.

Twenty-four exercise demos at the 5-second MiniMax minimum cost 24 x $0.375 = $9.00 on MiniMax H3 at 768p, or $7.50 at 480p, on Sume. The same set on H3 Max at 768p is $12.00.
Five seconds is the shortest legal clip on either MiniMax model, so a short demo is also the cheapest one. Prices come from the Sume price tool (read 2026-10-09).
Price of the 24-clip set
Redoing four weak clips adds 4 x $0.375 = $1.50 at H3 768p, so a realistic budget for the set is $10.50.
| Model | Resolution | Rate per second | One clip | 24 clips |
|---|---|---|---|---|
| MiniMax H3 | 480p | $0.0625 | $0.3125 | $7.50 |
| MiniMax H3 | 768p | $0.075 | $0.375 | $9.00 |
| MiniMax H3 Max | 768p | $0.10 | $0.50 | $12.00 |
One body per exercise
Start from a photo of the person in the start position and describe the movement. Keep the prompt to one repetition, since 5 seconds fits one or two.
{
"model": "minimax-h3",
"prompt": "One slow bodyweight squat, hands in front, steady camera, plain studio",
"image_url": "https://example.com/squat-start.jpg",
"resolution": "768p",
"duration": 5,
"aspect_ratio": "9:16",
"mode": "async"
}If the demos run longer
Five seconds fits one clean repetition. If you want a two-repetition demo, the table shows the cost of 8 and 10 seconds.
| Length | One clip | 24 clips |
|---|---|---|
| 5 s | $0.375 | $9.00 |
| 8 s | $0.60 | $14.40 |
| 10 s | $0.75 | $18.00 |
Limits and gotchas
Generated bodies can show wrong form. A person who knows the exercise should review every clip before it reaches users.
- Duration 5-15 seconds. Four seconds is refused.
- Use 768p, not 720p: MiniMax prices native 768p.
- Audio is native and always on, so mute the clips in the app if the demos should be silent.
- Name the Idempotency-Key after the exercise, such as
demo-squat-v1, so a re-run does not bill a second clip.
Sources
Related posts
More in Use cases
- Fix one wrong sentence in a voice-over: 130 characters, not 3,000
Redoing a 130-character sentence costs $0.006175 in Sume TTS plus a $0.01 audio join. Re-synthesizing the 3,000-character script costs $0.1425.
- Cap a Format run at $4: generation_spend_cap_usd on a before/after ad
Set generation_spend_cap_usd to 4 on a Sume Format run so a before/after ad cannot spend more than $4. What failure looks like and how to read the receipt.
- Four Music 1.0 takes for a 45-second explainer: $0.50 total
Generate four candidate music beds for a 45-second explainer on Sume Music 1.0 at $0.125 flat each, $0.50 total, with a seven-axis brief to narrow the takes.
- Game teaser in 15 seconds: H3 Max start and end frame for $1.50
A 15-second teaser from two key-art frames costs $1.50 on MiniMax H3 Max at 768p on Sume. The image_url and end_image_url body, the 1080p price and the checks.
Written by Sume