FLUX 3 Video HD $0.17/s vs Sume Wan 3.0 at 720p: a 12-second clip
A 12-second clip costs $2.04 at FLUX 3 Video's HD rate and $1.50 on Sume's wan-3.0 at 720p. Resolution names differ, so read the table before choosing.

A 12-second text-to-video clip at FLUX 3 Video's HD rate of $0.17 per second costs $2.04. The same 12 seconds on Sume's wan-3.0 at 720p costs $1.50 ($0.125 x 12). The two price lists do not use the same resolution labels, so this is a cost comparison, not a quality or pixel-for-pixel one.
Sume does not list FLUX 3 Video. The comparison is useful if you are deciding whether a FLUX 3 Video quote is in the same range as the video models Sume does list.
The numbers for 12 seconds
Black Forest Labs publishes per-second rates for FLUX 3 Video by resolution tier. Sume's rates come from its public catalog and are the provider list price times 1.25. All figures below are for one 12-second clip with default options and no extras.
| Model and tier | Rate per second | 12-second clip | Where it is listed |
|---|---|---|---|
| FLUX 3 Video, Draft | $0.06 | $0.72 | Black Forest Labs |
| FLUX 3 Video, HD | $0.17 | $2.04 | Black Forest Labs |
| FLUX 3 Video, FHD | $0.29 | $3.48 | Black Forest Labs |
| Sume wan-3.0, 480p | $0.0625 | $0.75 | Sume catalog |
| Sume wan-3.0, 720p | $0.125 | $1.50 | Sume catalog |
| Sume wan-3.0, 1080p | $0.25 | $3.00 | Sume catalog |
| Sume seedance-2.5, 720p | $0.5778 | $6.9336 | Sume catalog |
What is and is not comparable
BFL labels its tiers HD, FHD, QHD and UHD. The pricing page excerpt read for this post does not state pixel dimensions for those labels, so do not assume HD means 720p. Sume's tiers are named by pixel height: 480p, 720p and 1080p for wan-3.0.
Wan 3.0 on Sume accepts 2 to 30 seconds, so a 12-second clip is inside the valid range and the price is linear in duration. FLUX 3 Video also lists a Draft mode at $0.06 per second, which is slightly below Sume's lowest wan-3.0 rate of $0.0625 per second (about 4% higher).
How to decide
If the clip must come from FLUX 3 Video, buy it from Black Forest Labs; Sume cannot route to it. If the goal is a 12-second clip at a predictable price, the Sume rates above apply the same arithmetic at any duration inside 2 to 30 seconds: rate times seconds.
To see which Sume video models take your duration, resolution and aspect ratio before you submit, call GET /v1/videos/models. The Video generation docs list the discovery fields.
Scaling the same arithmetic
Because both price lists are per second, you can scale the 12-second example to any length. A 30-second clip, the top of wan-3.0's range on Sume, costs 30 x $0.125 = $3.75 at 720p and 30 x $0.17 = $5.10 at FLUX 3 Video HD. A 2-second clip, the bottom of wan-3.0's range, is $0.25 on Sume at 720p.
- Sume: rate x seconds, valid from 2 to 30 seconds for wan-3.0.
- FLUX 3 Video: rate x seconds for the tier you pick; Video Continuation is priced separately at $0.41 per second for HD.
- Neither figure includes retries; budget for the rejected takes you expect.
Sources
Related posts
More in Comparisons
- Forty 2K thumbnails: Nano Banana 2.1 $6.00 or Nano Banana Pro $7.50
Forty 2K images cost $6.00 on Nano Banana 2.1 and $7.50 on Pro. The 40-image bill at 0.5K, 1K, 2K and 4K, and when Pro is worth the gap.
- 14 4K posters: FLUX.3 vs Nano Banana 2.1 vs GPT Image 2.5 on Sume
FLUX.3 4K is $0.607 per image on Black Forest Labs. Sume does not list it. 14 posters cost $8.50 there, $2.80 on Nano Banana 2.1 and $3.12 on GPT Image 2.5.
- Gemini 3.8 Flash TTS vs Sume TTS: break-even is 47 characters
Gemini 3.8 Flash TTS costs $0.00225 per 10 seconds of audio; Sume TTS costs $0.0475 per 1,000 characters. They tie at about 47 characters per 10 seconds.
- Gemini Live Avatar custom avatars are allowlist-only; Sume is $0.95
Gemini 3.8 Live Avatar went GA on 2026-09-24 with custom avatars restricted to an allowlist. On Sume a photo avatar is $0.95 with no allowlist step.
Written by Sume