AI video price per frame at 24 fps: Wan, Omni, H3 Max, Veo Lite
A 24 fps second is 24 frames. Price per frame: Veo 3.1 Lite $0.0021, Sume Wan 3.0 480p $0.0026, H3 Max 768p $0.0042, Wan and Omni 720p $0.0052.
Divide the per-second price by 24 and you get the cost of one frame: about a fifth of a cent for Veo 3.1 Lite at 720p, and about half a cent for Sume's Wan 3.0 or Gemini Omni Flash at 720p. AI video is billed per output second, so the frame count only matters if you think in frames.
Price per frame, model by model
Per-frame figures below divide the per-second price by 24. Sume prices are the billed rate (provider list x 1.25), read from the rate card and the catalog; the Veo figure is Google's published Lite price.
| Model | Per second | Per frame | Per 240-frame (10 s) clip |
|---|---|---|---|
| Veo 3.1 Lite 720p (Google list) | $0.05 | $0.002083 | $0.50 |
| Wan 3.0 480p (Sume) | $0.0625 | $0.002604 | $0.62 |
| MiniMax H3 Max 768p (Sume) | $0.10 | $0.004167 | $1.00 |
| Wan 3.0 720p (Sume) | $0.125 | $0.005208 | $1.25 |
| Gemini Omni Flash 720p (Sume) | $0.125 | $0.005208 | $1.25 |
Why Veo Lite is cheapest per frame
Google lists Veo 3.1 Lite at $0.05 per second at 720p and $0.08 at 1080p on the Gemini API pricing page. Veo is not a Sume model, so the Sume rows show what the same 10 seconds costs on the models Sume does ship.
What changes with resolution
Sume's per-frame price grows with resolution on every model, so quote the frame price together with the resolution. Wan 3.0 is $0.0625 per second at 480p, $0.125 at 720p and $0.25 at 1080p, per the Video Router docs and the live catalog.
Use the live catalog for your own table
Do not hard-code these numbers. Read GET /v1/catalog and divide by your frame rate; the API reference lists the endpoint, and the rate card shows the same prices on a page.
Sources
Related posts
More in Pricing
- AI video price per minute table, next to Sume's per-model SKUs
A Hedra table from Artificial Analysis lists AI video at $6.00 to $20.16 a minute. How to read it, and where Sume prints its own per-model SKUs.
- Audio and video API dates to calendar: Oct 12, Nov 11, end of 2026
ElevenLabs v4's 72% discount ends Oct 12, Seedance 1.5 Pro retires Nov 11, Gemini 3.8 Flash TTS pricing runs to year end. A dated table and a countdown script.
- Batch APIs discount 50%: what a Sume bulk run changes instead
OpenAI, Anthropic and Gemini each document a 50% batch discount. Sume docs describe no batch price: a bulk queue controls throughput, not the rate.
- Black Friday finals: Seedance 2.5 at 720p or 1080p for 20 clips
A 5-second Seedance 2.5 clip is $2.889 at 720p and $7.10775 at 1080p. For 20 finals that is $57.78 against $142.16. Worth it only for hero placements.
Written by Sume