LTX-2.5 AI
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. Released August 2026. Try it online in the Studio or call it from code, up to 68% below the official price.
- Developer
- Lightricks
- LTX family
- Released
- August 2026
- Output
- 1080p
- 1–8 s · audio
- From
- $0.0285/s
- 720p
Try it
Try LTX-2.5 AI now
Runs on your balance at the price on the button; failed runs are refunded. Results are saved to your account.
What it is
What is LTX-2.5?
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.
Capabilities
What LTX-2.5 can do
A few cents / s
720p or 1080p, sound included
Seconds to render
Synchronous, near real-time
Audio included
Optional soundtrack
Open weights
LTX-2 Community License
Examples
LTX-2.5 examples
Prompts you can load into the Studio and try.
Drone shot over a turquoise river winding through a pine forest, morning mist, birdsong
A chef flips a pancake in slow motion in a sunny kitchen, sizzling pan
Neon-lit Tokyo alley in the rain, a cat walks past puddles, distant traffic hum
Use cases
What people use LTX-2.5 for
- Concepts and b-roll
- Scenes, establishing shots and storyboards from a written description.
- Animating stills
- Product shots, characters or artwork brought to life from a first frame.
- Clips with sound
- Dialogue, effects and ambience generated with the picture, at no extra cost.
How it compares
LTX-2.5 vs similar models
LTX-2.5 vs Veo 3.1 Lite
LTX-2.5
- Lower price: $0.0285/s vs $0.0375/s at 720p (24% less).
- Higher maximum resolution: 1080p vs 720p.
- Audio included at no extra cost.
Veo 3.1 Lite
- First and last frame control for image-to-video.
Where to use it
Three ways to use LTX-2.5
In the Studio
No code: write a prompt, pick the settings, generate. The price is shown before you run.
Through the API
One key and one request shape for every model; poll the generation or get a webhook.
FAQ
LTX-2.5 AI questions
LTX-2.5 is Lightricks' open-weights model. CheaperGen provides API access to the open weights, run on GPU inference for open-source models, and does not own the model. Trademarks belong to their respective owners.