LTX-2.5 Explained (2026): specs, list price, what it is good for, where to use it
Lightricks' in-house video model family powering LTX Studio; the current release is LTX-2.5, with open weights and an API.
Specs
| Segment length | 6–20 s on the API: Fast up to 20 s at 1080p and 10 s at 1440p/4K; Pro up to 10 s; Extend and Retake on Pro |
| Resolution | 720p / 1080p / 1440p / 4K, 25 or 50 fps |
| Audio | Joint audio-video generation; audio-to-video |
| References | Casting references; Elements in LTX Studio |
| Intra-segment cuts | Native multi-shot in one generation (vendor claim); LTX Studio's storyboard layer on top |
| List price | API per second: Fast $0.09 (720p), $0.13 (1080p), $0.19 (1440p), $0.30 (4K); Pro $0.12 / $0.17 / $0.25 / $0.39. Inside LTX Studio, subscription credits |
| Where to use | LTX Studio, LTX API, open weights |
LTX-2.5 vs other video models: seconds per generation
Good for / caveats
Good for
Narrative shorts with shot-level control
Caveats
Pro tier capped at 10 s per generation; episode structure needs a platform layer
Available in
FAQ
How much does LTX-2.5 cost?
API per second: Fast $0.09 (720p), $0.13 (1080p), $0.19 (1440p), $0.30 (4K); Pro $0.12 / $0.17 / $0.25 / $0.39. Inside LTX Studio, subscription credits
How long can one LTX-2.5 generation be?
6–20 s on the API: Fast up to 20 s at 1080p and 10 s at 1440p/4K; Pro up to 10 s; Extend and Retake on Pro · 720p / 1080p / 1440p / 4K, 25 or 50 fps
Is LTX-2.5 good for AI short drama?
Good for: Narrative shorts with shot-level control. Caveat: Pro tier capped at 10 s per generation; episode structure needs a platform layer.
How do I use LTX-2.5 without coding?
Through platforms that expose it: LTX Studio
Sources
Official pages opened while writing; current pricing and features are always as shown on the vendor site.
- https://ltx.io/api — LTX-2.5
- https://ltx.io/model — LTX-2.5
- https://ltx.io/studio/pricing — LTX-2.5