Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

Lightricks logo

LTX 2.5 Fast

LTX 2.5 Fast generates video with native audio from text or start and end frames.

Price is per video output second, rounded up.
Offering
Price
480p
$0.003
720p
$0.006
1080p
$0.01

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

LTX 2.5 Fast

LTX 2.5 Fast is Lightricks’ speed-oriented video model. Lightricks is the Israeli company behind Facetune; LTX is their video line. This variant generates from a text prompt, or from a start frame and an optional end frame, with native audio.

Output tiers are 512p, 768p, and 1088p — the catalog’s 480p, 720p, and 1080p rows. Minimum duration is 6 seconds. There is no uploaded audio reference and no identity pack of stills.

What it's good for

A fast cinematic shot, especially when you already have opening and closing stills and want the motion between them. Also B-roll and establishing shots that only need six seconds or more of one idea. Audio is generated with the clip, not cloned from a track you upload.

Model ID

lightricks/ltx-2.5-fast

Output Type

Video

Pricing

From $0.003/s

Provider

Lightricks

Hosting

Protoface

LTX 2.5 Fast

LTX 2.5 Fast is Lightricks’ speed-oriented video model. Lightricks is the Israeli company behind Facetune; LTX is their video line. This variant generates from a text prompt, or from a start frame and an optional end frame, with native audio.

Output tiers are 512p, 768p, and 1088p — the catalog’s 480p, 720p, and 1080p rows. Minimum duration is 6 seconds. There is no uploaded audio reference and no identity pack of stills.

What it's good for

A fast cinematic shot, especially when you already have opening and closing stills and want the motion between them. Also B-roll and establishing shots that only need six seconds or more of one idea. Audio is generated with the clip, not cloned from a track you upload.