Micro-drama season of 40 one-minute episodes: cost by Sume model
Micro-dramas are rising on TikTok, Reels and Shorts. Forty 60-second episodes in 9:16 priced on Omni, Wan, Kling, MiniMax H3 and Seedance, with the catches.

Micro-dramas are reported to be rising across TikTok, Reels and Shorts (Heyorca, read 2026-10-07). A season of 40 episodes at 60 seconds each is 2,400 seconds of vertical footage. The model you choose changes the bill by a factor of three, and changes how many cuts a viewer sees.
All prices are billed rates (list x 1.25, rounded up per job) for 9:16, with no retakes. Retakes multiply every figure.
One episode and the season
| Setup | Jobs per episode | One episode | 40 episodes |
|---|---|---|---|
| Wan 3.0, 720p, 2 x 30 s | 2 | $7.50 | $300.00 |
| Omni Flash, 720p, 6 x 10 s | 6 | $7.50 | $300.00 |
| MiniMax H3, 768p, 4 x 15 s | 4 | $4.52 | $180.80 |
| Kling 3, silent, 4 x 15 s | 4 | $8.40 | $336.00 |
| Kling 3, audio on, 4 x 15 s | 4 | $12.60 | $504.00 |
| Omni Flash, 1080p, 6 x 10 s | 6 | $11.28 | $451.20 |
What a micro-drama needs from the model
Dialogue is the point of the format, so audio matters first. Omni Flash and MiniMax H3 always generate sound, and both take reference images, which is how you keep two actors looking the same from scene to scene. Omni Flash accepts up to 10 reference images and 3 reference clips of 3 seconds each; MiniMax H3 takes up to 9 images, 3 videos and 3 audio clips. Kling 3 in the Sume catalog accepts no reference input, so a character can drift between its clips.
Cut count is the other side of the cost. Six Omni clips per episode means five cuts per minute, which suits a fast micro-drama. Two Wan clips per episode means one cut, which suits a single long scene. Either way, plan scene breaks at the clip boundaries so the seams read as edits and not as glitches.
Keep faces stable across 40 episodes
Generate one hero still per character, host it at a public HTTPS URL, and pass it in input_references on every job. On Omni Flash refer to it in the prompt as <IMAGE_REF_0>. Re-use the same still for the whole season; a new photo each week is a new actor.
{
"model": "gemini-omni-flash-1.1",
"prompt": "<IMAGE_REF_0> sits in a parked car at night and says: 'You knew.' Close-up, rain on the glass.",
"duration": 10,
"resolution": "720p",
"aspect_ratio": "9:16",
"input_references": [
{"type": "image_url", "image_url": {"url": "https://example.com/lead-actress.png"}}
]
}Sources
Related posts
More in Use cases
- Microscope-style science clip with Gemini Omni Flash: prompt and cost
Google's own Omni 1.1 demo prompt is a diatom micrograph. Here is how to write one, draft it at 360p, and what 8 seconds costs on Sume at each resolution.
- Midday to golden hour in a video: Omni edit or first/last frame
Change the time of day in a clip you already have. When a Gemini Omni Flash edit fits, when first and last frames fit, and what a 6-second pass costs on Sume.
- Mobile pet groomer reel from one photo: Seedance 2.5 image-to-video
Turn one photo of a groomed dog into a vertical reel clip with Seedance 2.5 on Sume: first-frame input, 4 to 30 seconds, native audio, async job.
- Monthly investor update video with an AI avatar: 60 s per job
An avatar update longer than 60 seconds has to be split. How to cut a monthly investor or board update into three jobs, keep one presenter, and price it.
Written by Sume