14-second AI video API: one Sume request or stitched extensions

On Sume a 14 second clip is a single request with MiniMax H3, H3 Max, Wan 3.0, Kling 3 or Seedance. Google's Veo 3.1 has no 14 s option; its docs describe extending a clip by 7 s, up to 20 times, at 720p only (read 2026-10-04).

Which models accept 14 seconds

The table shows the models that accept 14 s in one go. Every row except Omni (which stops at 10 s) is available.

One generation versus extension chains

Chaining extensions has a cost beyond price: each step starts from the previous clip's last frames, so style and motion can drift. A single request keeps the shot continuous, and the catalog tells you before submit whether the length is allowed.

If you do need to go beyond what one request allows, the stored post on extending past 30 seconds covers the options.

What a 14 second request costs

Sume bills the provider list price times 1.25, rounded up to the next cent. The amount is reserved when you submit and refunded if the job fails, so a rejected or failed clip does not cost you. The /v1/videos/models descriptor lists the billable rate in pricing_skus, which is the field to trust over any number in a blog post.

A 14 s clip bills $1.75 on Wan at 720p, $1.05 on H3 at 768p and $1.96 on Kling 3 with audio off.

Check 14 seconds against the live catalog

Duration support lives in the catalog, not in this page. Each entry on GET /v1/videos/models carries supported_durations, which is every whole second from the model minimum to its maximum, so one membership test answers the question. This script lists every model that accepts 14 s, with its resolutions and billable rates.

Set SUME_API_KEY first. See the Video Generation docs for the request and polling lifecycle.

import os
import requests

N = 14
resp = requests.get(
    "https://api.sume.com/v1/videos/models",
    headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
    timeout=30,
)
resp.raise_for_status()
for m in resp.json()["data"]:
    if N in m["supported_durations"]:
        print(m["id"], m["supported_resolutions"], m["pricing_skus"])