Grok Imagine Video on Sume: the cents-per-job ladder, 4 to 15 seconds
Grok Imagine Video 1.5 bills $0.0125 per second, rounded up to the cent per job. Every length from 4 to 15 seconds, and why a 5-second clip costs 7 cents.

Grok Imagine Video 1.5 is the cheapest video row in the Sume catalog: a flat provider list rate of $0.01 per second (pricing note dated 2026-06-29 in the repo), sold at list x 1.25, or $0.0125 per second. It works from a still image only, 4 to 15 seconds, at 480p or 720p.
Sume rounds each job up to the whole cent. At these amounts the rounding is visible, and it changes the effective per-second price by length.
The ladder
| Length | Exact billed | Charged | Cents per second |
|---|---|---|---|
| 4 s | 0.0500 | $0.05 | 1.25 |
| 5 s | 0.0625 | $0.07 | 1.40 |
| 6 s | 0.0750 | $0.08 | 1.33 |
| 7 s | 0.0875 | $0.09 | 1.29 |
| 8 s | 0.1000 | $0.10 | 1.25 |
| 9 s | 0.1125 | $0.12 | 1.33 |
| 10 s | 0.1250 | $0.13 | 1.30 |
| 11 s | 0.1375 | $0.14 | 1.27 |
| 12 s | 0.1500 | $0.15 | 1.25 |
| 13 s | 0.1625 | $0.17 | 1.31 |
| 14 s | 0.1750 | $0.18 | 1.29 |
| 15 s | 0.1875 | $0.19 | 1.27 |
How to read it
A 4-second clip is exactly 5 cents and costs the least per second at 1.25 cents. A 5-second clip is $0.0625 exactly, so it rounds up to 7 cents, which is 1.40 cents per second. The worst case is any length where the exact price lands just over a whole cent. Between 4 and 15 seconds the effective rate stays between 1.25 and 1.40 cents per second, so the rounding never costs more than a small fraction of a cent per second on a single clip.
Nothing here changes with resolution: the catalog lists one flat rate for 480p and 720p, so choose 720p unless you need to save bandwidth. Output length follows duration, an integer between 4 and 15. There is no aspect ratio field; the clip takes its shape from the image you pass, so crop to 9:16 first for a vertical Short.
A batch
Fifty 6-second clips cost 50 x $0.08 = $4.00. At 1,000 clips of 6 seconds the bill is $80. Grok Imagine has no text-to-video and no audio in the Sume catalog, so if you need sound add it afterwards or pick another row.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"grok-imagine-video-1.5","prompt":"Gentle parallax, the lamp flickers","duration":6,"resolution":"720p","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/room.png"},"frame_type":"first_frame"}]}'Sources
Related posts
More in Pricing
- H3 at 480p is only 17% cheaper than 768p, so draft on Wan instead
MiniMax H3 bills $0.0625 a second at 480p and $0.075 at 768p on Sume. Drafting there saves 17 percent; a Wan 480p draft costs the same rate.
- H3 Max lip sync at 14.8 s bills 15 s: $1.50 at 768p, $3.00 at 1080p
A 14.8-second line is the longest MiniMax H3 Max lip sync accepts on Sume. It rounds up to 15 billed seconds: $1.50 at 768p, $3.00 at 1080p, $0.9375 at 480p.
- MiniMax H3 Max API price: Sume 1.25x vs the fal list
H3 Max costs $0.0625 to $0.20 per second on Sume (list x 1.25). Per-clip and per-100-clip math against fal's listed $0.05 per second.
- HappyHorse 1.0 at 1080p: $0.28 on fal, $0.24 on Alibaba, Sume options
HappyHorse 1.0 costs $0.28 a second at 1080p on fal and $0.24 on Alibaba Cloud Singapore. HappyHorse is not a Sume id; here are the 1080p rows that are.
Written by Sume