LTX-2.3 makes 9:16 clips up to 20 s; what Sume offers instead
fal lists LTX-2.3 with portrait 9:16 and up to 20 seconds. Sume's catalog has no LTX row; Wan 3.0 and Seedance 2.5 reach 30 s, Kling 15 s.

The fal LTX-2.3 page lists clips up to 20 seconds, portrait 9:16 output, resolutions of 1080p, 1440p and 2160p, 24 or 48 frames per second, and native audio (read 2026-10-04). If you want a vertical clip for Reels or Shorts and you searched for LTX, the question is whether you can call it on Sume.
You cannot. Sume's GET /v1/videos/models catalog lists the models the Video Router serves, and LTX is not among them. The video generation docs describe that endpoint, and the catalog in the repository carries no LTX row. A request with an LTX model id fails as an unknown model, so check the live list before wiring it into a script.
Nearest vertical options
Wan 3.0 and Seedance 2.5 both clear LTX's 20 seconds. If you want 4K, gemini-omni-flash-1.1 is the only row above that lists it, but its clips stop at 10 seconds.
| Model | Longest clip | Top resolution | Audio |
|---|---|---|---|
| LTX-2.3 (fal page) | 20 s | 2160p | Native |
| wan-3.0 | 30 s | 1080p | Per model row |
| seedance-2.5 | 30 s | See catalog | Per model row |
| kling-3 | 15 s | 1080p | Per model row |
| gemini-omni-flash-1.1 | 10 s | 4K | Per model row |
List the rows yourself
import os
import requests
resp = requests.get(
"https://api.sume.com/v1/videos/models",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
)
for m in resp.json()["data"]:
if "9:16" in m["supported_aspect_ratios"]:
print(m["id"], max(m["supported_durations"]))The script prints each model that lists 9:16 and its longest whole-second duration, which is the number to compare against LTX's 20.
Sources
Related posts
More in Models
- Luma's 2026 timeline: Ray3.14, Ray3.2, Scenes and Variants
Luma shipped Ray3.14 in January, Ray3.2 in June, Scenes in August and Variants on Oct 1, 2026. What each added, and why to pin model ids.
- Lyria 3.5 blocks artist-voice prompts: how to write briefs that pass
Google's Lyria 3.5 docs note that prompts asking for specific artist voices are blocked. Describe the sound instead, then run it through the Sume Music Router.
- MAI-Transcribe-2-Streaming or a batch STT job: which fits?
MAI-Transcribe-2-Streaming returns first partials in just over 100 ms. Sume's speech-to-text is a batch job up to 10 minutes at $0.01 per minute.
- Can I use MAI-Voice-2.1 audio commercially? What Microsoft says
Microsoft's MAI voices page says it holds full licensing rights for commercial use, the service is in public preview with no SLA, and cloning is gated.
Written by Sume