Max video length in seconds: five platforms vs Sume's 900 and 1800
TikTok API 600 s, Shorts 180 s, Pinterest 900 s, X 1200 s, LinkedIn 1800 s. Sume trims 900 s and renders 1800 s timelines, so only some fit in one job.

In seconds the published maxima are 180 for YouTube Shorts, 600 for the TikTok API, 900 for Pinterest, 1200 for a default X account and 1800 for LinkedIn. Sume's Timeline 1.0 accepts an audio spine up to 1800 s, which equals LinkedIn's 30 minutes, and video trim cuts at most 900 s, which equals Pinterest's 15 minutes. Everything shorter has to be limited by you.
| Platform | Stated maximum | Seconds | Fits one Sume Timeline render? | Fits one Sume trim? |
|---|---|---|---|---|
| YouTube Shorts | 3 minutes | 180 | Only if the spine is 180 s or less | Only if 180 s or less |
| TikTok API | 10 minutes | 600 | Only if 600 s or less | Only if 600 s or less |
| Pinterest (video ads page) | 15 minutes | 900 | Yes | Yes, exactly at the cap |
| X, default account | 20 minutes | 1200 | Yes | No, trim output stops at 900 |
| 30 minutes | 1800 | Yes, exactly at the cap | No |
What the cells mean
Timeline has no platform preset: it renders whatever audio.duration_seconds you send, from 1 to 1800. The platform limit is therefore a number you check yourself. X also has Premium and verified accounts at 125 minutes, and TikTok notes that individual users may have lower limits than the API.
Trim is for cutting one source: the source may be up to 1800 s and the output 0.2 to 900 s. A keyframe trim is a stream copy that can begin a GOP early, so use the default exact precision when the cut point matters.
Check length before you pay
POST /v1/timeline-1.0/plan is an unbilled compile preflight. It returns duration_seconds and segment_count without creating a job, so you can compare the number with the table before you render. The helper below does the comparison from a plan response.
LIMITS = {"shorts": 180, "tiktok": 600, "pinterest": 900,
"x": 1200, "linkedin": 1800}
def fits(duration_seconds):
return {name: duration_seconds <= cap for name, cap in LIMITS.items()}
print(fits(240))Sources
Related posts
More in Comparisons
- Qwen Image 2.1 Pro vs Turbo: price, steps and rate limits
Turbo is 8 steps at $0.016 per image; Pro is $0.04 with a 20 RPM cap. Both are on Alibaba Model Studio; Sume lists neither yet.
- Qwen Image 2.1 Turbo $0.016 vs Sume Qwen Image: 100 images
Alibaba lists qwen-image-2.1-turbo at $0.016 and pro at $0.04 per image (Singapore). Sume offers qwen-image at 2.5 cents and qwen-image-max at 9.4.
- Qwen Image 2.1 Turbo vs FLUX.2 pro vs Seedream 5 Lite: price per image
Vendor list prices are $0.016 (Qwen Turbo, Singapore), $0.03 (FLUX.2 pro) and $0.035 (Seedream 5.0 Lite). Sume lists the last two.
- Qwen Image Max vs Qwen Image 2.1 Pro: $0.075 on fal, $0.04 on Alibaba
Qwen Image Max is $0.075 per image on fal and $0.09375 on Sume; Alibaba lists 2.1 Pro at $0.04. They are different models, so compare with care.
Written by Sume