17-second AI video API: only Wan and Seedance 2.5 clear 15 s

For a 17 second text-to-video or image-to-video generation on Sume, use Wan 3.0 or Seedance 2.5. Every other generator in the catalog stops at 15 s or earlier. Higgsfield Genjutsu and H3 Max Recast also go beyond 15 s, but their length is the length of the source video you give them.

Which models accept 17 seconds

ByteDance's Seedance 2.5 page says it generates up to 30 s in a single generation, with an option to extend twice (read 2026-10-04). The Sume catalog lists 4-30 s for Seedance 2.5, and 2-30 s for Wan 3.0.

The 15 second wall

Kling 3, Seedance 2, 2 Fast, 2 Mini, Grok Imagine 1.5, H3 and H3 Max all top out at 15 s. A 17 s request against any of them returns a validation error, and nothing is reserved. See the stored ceilings comparison for the full list.

Wan's reference limits are generous at this length: up to 10 images, 5 videos and 5 audio clips, with the video and audio totals each capped at 15 s.

What a 17 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.

Seventeen seconds of Wan bills $1.07 at 480p, $2.13 at 720p and $4.25 at 1080p. Seedance 2.5 is token priced, so read its pricing_skus row.

Check 17 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 17 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 = 17
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"])