Seedance 2.0 Mini, Fast, Standard or 2.5: which tier for ad drafts
On Sume the Seedance tiers price per 1,000 video tokens: Mini is half of Standard, Fast is 80%, and 2.5 is about 53% above Standard. Mini is the draft tier.

Use seedance-2-mini for ad drafts: its list rate is $0.007 per 1,000 video tokens, half of seedance-2 at $0.014, and the cap is the same 15 seconds at 480p to 1080p. seedance-2-fast is $0.0112, 80% of Standard, and seedance-2.5 is $0.0214, about 53% above Standard, but it runs 4 to 30 seconds.
Seedance rows are billed on video tokens, not seconds, so the right way to compare tiers is the ratio, and the way to know a dollar figure is to run one job and read usage.cost. List rates are from the Sume catalog and the Video Router guide, read 2026-10-05; Sume bills them times 1.25.
The four Seedance rows
Every Seedance row on Sume takes text, first and last frame, and image, video and audio references.
| Model id | List per 1,000 video tokens | Share of Standard | Clip length | Resolutions |
|---|---|---|---|---|
| seedance-2-mini | $0.0070 | 50% | 4 to 15 s | 480p, 720p, 1080p |
| seedance-2-fast | $0.0112 | 80% | 4 to 15 s | 480p, 720p, 1080p |
| seedance-2 | $0.0140 | 100% | 4 to 15 s | 480p, 720p, 1080p |
| seedance-2.5 | $0.0214 | 153% | 4 to 30 s | 480p, 720p, 1080p |
A draft-to-final ladder
Draft hooks on Mini at 480p, shortlist the two you like, and rerun the same prompt on Standard or 2.5 at the final resolution. Tokens scale with resolution and length, so a 480p draft of the same length is a small share of the final.
Because no Sume video model accepts seed, the final is a new take, not a sharper copy of the draft. Treat the draft as a test of prompt, framing and pacing, and expect the hero shot to differ.
- Mini for volume: 20 or 40 hook drafts.
- Fast when Mini misses the motion you want and you still need speed.
- Standard for the 15-second final.
- 2.5 when the final must run past 15 seconds, up to 30.
Request
Change only model and resolution between draft and final.
import os, time, requests
H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
payload = {
"model": "seedance-2-mini",
"prompt": "Handheld close-up of a hand pouring cold brew over ice, condensation on the glass",
"duration": 5,
"resolution": "480p",
"aspect_ratio": "9:16",
}
job = requests.post("https://api.sume.com/v1/videos", headers=H, json=payload).json()
while True:
time.sleep(30)
s = requests.get(job["polling_url"], headers=H).json()
if s["status"] in ("completed", "failed", "cancelled"):
break
print(s["status"], s.get("unsigned_urls"), s.get("usage"))Sources
Related posts
More in Models
- Seedance output size in pixels: what 720p 9:16 or 1080p 21:9 means
Pixel dimensions Sume uses for Seedance by resolution and aspect ratio: 720p 16:9 is 1280x720, 1080p 21:9 is 2205x945, 480p 9:16 is 496x864.
- Seedream 4.5 edit with n=4 returns one image on Sume
On Sume, a Seedream 4.5 call with reference images is an edit and always asks the provider for one image, so n=4 does not give four takes. Use four calls.
- Seedream 5.0 Flash takes 14 references; Sume seedream-5-lite takes 10
Seedream 5.0 Flash lists up to 14 input references on OpenRouter. Sume's catalog caps references at 10 and lists seedream-5-lite, not Flash.
- Sound-on Reels product spot in one call: Omni Flash, 8 s, $1.00
Reels default to sound on. Omni Flash 1.1 returns synced audio: 8 s at 720p is $1.00 on Sume, against $3.27 for a silent clip plus voice and music.
Written by Sume