9-second AI video API: Omni takes 9 s, Veo does not

Yes: nine seconds works on Sume. Gemini Omni Flash 1.1 accepts 3-10 s, MiniMax H3 and H3 Max accept 5-15 s, Wan 3.0 accepts 2-30 s, and Kling 3 and the Seedance 2 family accept 4-15 s. Google's Veo 3.1 documents a longest clip of 8 s, so a 9 s request cannot be made there (read 2026-10-04, Veo docs).

Which models accept 9 seconds

Gemini's own Omni API page lists 16:9 and 9:16 with resolutions from 360p to 4K, and the Sume catalog mirrors the two ratios (read 2026-10-04). Nine seconds sits one second under the Omni ceiling, which makes it the longest single-shot Omni can produce.

Nine seconds is Omni's longest clip

If you want the cheapest model that can still reach 9 s, Omni at 360p is the draft tier. Move up to 720p for the final render. Because the default Auto duration is 8 s, a 9 s request must be sent explicitly; see what each model reserves when you omit duration.

Past 10 s, Omni is out and you need H3, H3 Max, Wan or Seedance.

What a 9 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.

Nine seconds of Omni at 720p bills $1.13; at 360p it bills $0.34. Wan at 720p bills $1.13.

Check 9 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 9 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 = 9
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"])