LTX-2.5 API
Open-weights 1080p video with sound — rendered in seconds, for a few cents a second
Try LTX-2.5
Runs on your balance at the price shown on the button. Results are saved to your account.
1080p (1920×1080) or 720p (1280×720), landscape.
Length of the generated clip in seconds (1–8s). You pay per second.
Create a free account with Google or email — pay only for what you generate.
Your video will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
What is LTX-2.5?
LTX-2.5 from Lightricks generates 1–8 second 720p or 1080p videos with a synchronized soundtrack from text or a first frame, in a few seconds and at a fraction of the usual per-second price.
Fast and sharp
LTX-2.5 is Lightricks' newest open video model: native 1080p, smooth motion and an optional soundtrack, rendered so fast that an 8-second 1080p clip comes back in seconds.
For iteration and volume
At a few cents per second it suits storyboards, social loops, B-roll and any pipeline that needs many clips.
LTX-2.5 pricing
Pay per second of video. No subscription. Failed generations are refunded automatically.
| Tier | Official price | Cheaper Gen. | You save |
|---|---|---|---|
720p 16:9 · 24 fps | $0.022/s | −76% | |
1080p 16:9 · 24 fps | $0.044/s | −66% |
- Official price: LTX API list price for ltx-2-5-fast ($0.09 / s at 720p, $0.13 / s at 1080p; docs.ltx.io/pricing). Prices verified 2026-10-16.
Specifications
- Resolutions
- 720p · 1080p (16:9)
- Duration
- 1–8 s
- Frame rate
- 24 fps
- Audio
- Optional (included)
- Released
- Aug 11, 2026
Use LTX-2.5 via API
One request to start a job, one to fetch the result. Same shape for every model.
import os, time, requests
API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}
# 1. Submit the job
job = requests.post(f"{API}/run/lightricks/ltx-2.5/text-to-video", headers=headers, json={
"prompt": "A lighthouse keeper climbs a spiral staircase with a lantern as a storm hits the windows, thunder and rain",
"resolution": "1080p",
"duration": 6
}).json()
# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
time.sleep(3)
job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()
print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])Example prompts
Hit “Try it” to load a prompt into the playground above.
LTX-2.5 FAQ
Related models

Veo3.1 Lite
Text · Image → Video
The lowest-cost Veo — native audio from a few cents a second

Seedance2.0 Mini
Text · Image · Reference → Video
The lowest-cost Seedance for drafts and high volume

PixVerseV6
Text · Image · Reference → Video
Creator-favorite effects and styles, from 2 cents a second
LTX-2.5 is developed by Lightricks. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI
