LTX-2.5 Pro
Lightricks' quality-focused video model for making 720p or 1080p clips from text, images, or audio with native sound.
Lightricks' quality-focused video model for making 720p or 1080p clips from text, images, or audio with native sound.
Plain-English overview
LTX-2.5 Pro is the higher-fidelity member of the LTX-2.5 family. It supports text-to-video, image-to-video, and audio-to-video, and can produce multishot clips with sound instead of requiring a separate audio-generation pass.
The API uses a clear per-second price that changes with resolution. Supported durations are deliberately constrained, so it is easiest to budget when a project is planned as a sequence of six-, eight-, or ten-second shots.
Category comparison
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
Pricing & comparisons
Set your usage. Your estimate updates as you type.
Example: 8-second, 720p clips with audio. Models that do not support these settings will not receive an estimate.
LTX-2.5 Pro
Lightricks
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Availability
Generally available through the LTX API in Pro text-, image-, and audio-to-video workflows.
The public model guide does not enumerate a processing-country list; account and enterprise terms determine region and capacity.
Check live availabilityData and training
The reviewed public LTX model and pricing guides do not state one complete endpoint-specific retention or training-use commitment. Verify current account and enterprise terms for sensitive media.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Lightricks' quality-focused video model for making 720p or 1080p clips from text, images, or audio with native sound. LTX-2.5 Pro is the higher-fidelity member of the LTX-2.5 family. It supports text-to-video, image-to-video, and audio-to-video, and can produce multishot clips with sound instead of requiring a separate audio-generation pass.
LTX-2.5 Pro was released on August 11, 2026 according to the cited provider materials.
Generally available through the LTX API in Pro text-, image-, and audio-to-video workflows. The access routes listed in this guide are LTX.
$0.12/s at 720p · $0.17/s at 1080p. LTX lists the same Pro rate for text-to-video, image-to-video, and audio-to-video. Optional services and future tiers can add cost.
Generally available through the LTX API in Pro text-, image-, and audio-to-video workflows. The public model guide does not enumerate a processing-country list; account and enterprise terms determine region and capacity.
The reviewed public LTX model and pricing guides do not state one complete endpoint-specific retention or training-use commitment. Verify current account and enterprise terms for sensitive media. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
OpenAI's legacy synced-audio video model for short text- or image-guided clips—still documented, but approaching a permanent API shutdown.
Open full comparisonGoogle's preview video model for text-, image-, and video-guided generation with native audio and output options up to 4K.
Open full comparisonGoogle's lower-cost Veo 3.1 variant for quickly creating short video clips with native audio and output options up to 4K.
Open full comparisonRunway's flagship developer video model for text- and image-guided clips, with professional formats and a predictable credit-per-second base rate.
Open full comparisonKuaishou's Pro video model delivered through fal for multi-shot text/image generation, optional native audio, references, and clips up to 15 seconds.
Open full comparisonA cost-conscious Kling model on fal for fluid five- or ten-second clips generated from text or a starting image.
Open full comparisonSpaceXAI's current video model for turning text, images, or references into short clips with optional generated speech and sound.
Open full comparisonByteDance's current audiovisual model for coherent clips up to 30 seconds, with native sound, long-form storytelling, rich references, and targeted editing.
Open full comparisonAlibaba's unified video family for creating short clips with sound from text, a starting image, or a reference video.
Open full comparisonLTX's speed-optimized video model for text, image, or audio input, native sound, automatic duration, and output up to 4K.
Open full comparisonLTX's mature full-workflow video model for generation plus Retake, Extend, Reframe, native audio, and first-to-last-frame control.
Open full comparison