11-second AI video API: what works past Omni's 10 s cap

An 11 second clip rules out Gemini Omni Flash 1.1, whose Sume range is 3-10 s. Everything else with a longer ceiling accepts it: MiniMax H3 and H3 Max (5-15 s), Wan 3.0 (2-30 s), Kling 3 and the Seedance 2 family (4-15 s) and Seedance 2.5 (4-30 s).

Which models accept 11 seconds

MiniMax's H3 launch post says clips run up to 15 s (read 2026-10-04), and the Sume catalog lists the same 5-15 s window for both H3 ids. Wan and Seedance 2.5 go to 30 s.

Auto and pinned ids over 10 seconds

The Auto router's create controls default to 3-10 s clips at 16:9 or 9:16, so an 11 s job is the point where you should pin a model rather than rely on Auto. The stored post on Auto versus a pinned model past 10 s walks through that choice.

Google's Omni page documents extension in 10 s steps up to 40 s total (read 2026-10-04, Omni docs), but that is a Google feature. Sume's catalog entry for Omni is a single 3-10 s generation.

What a 11 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.

Eleven seconds at the H3 768p rate bills $0.83; Wan at 720p bills $1.38; H3 Max at 1080p bills $2.20.

Check 11 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 11 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 = 11
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"])