LTX-2.3 Fast. Video with sound from six cents a second.
Lightricks' LTX-2.3 on fal's fast endpoint renders clips with native audio from a prompt, an opening frame, or a first and end frame, in 16:9 or 9:16. Its lowest tier is 1080p, which fal lists at 6 cents a second.
- 6, 8, 10, 12, 14, 16, 18 or 20 second clips
- 16:9 and 9:16
- Native audio
- First and last frame control
- 1080p, 1440p or 4K
- 1440p and 4K up to 10 seconds
- Runs on fal
LTX-2.3 is a video model from Lightricks, and this is fal's fast endpoint for it. Treza runs it through fal because OpenRouter does not carry LTX. It takes a prompt, a first frame, or a first and an end frame, and renders 1080p, 1440p or 4K in 16:9 or 9:16, with native audio you can switch off. At 1080p a clip runs from 6 seconds up to 20 in steps of 2; at 1440p and 4K it stops at 10.
fal listed it on 2026-10-26 at 6 cents a second at 1080p, 12 at 1440p and 24 at 4K, with or without sound, so a 20 second 1080p take is $1.20 of provider cost. For comparison, OpenRouter lists Veo 3.1 Lite at 8 cents a second for 1080p with sound, in clips of up to 8 seconds. Treza quotes the list price plus its credit markup before a run, and a failed generation costs nothing. It runs on the canvas, in the Video Generation node, and through any pipeline you publish as an API. Chat does not run it; there, ask for Veo 3.1 Lite.
Six cents a second at 1080p
fal's list price for its lowest tier, sound included. A 6 second 1080p clip is 36 cents of provider cost before Treza's markup.
Up to 20 seconds at 1080p
Even lengths from 6 seconds up to 20 in one take at 1080p. 1440p and 4K clips stop at 10 seconds.
Sound on or off, same price
Native audio comes with the clip, and a switch on the node turns it off. fal bills the same either way.
First and end frames
Open on an image, or add an end frame and the clip makes the transition between the two, in 16:9 or 9:16.
What to make with LTX-2.3 Fast
Real prompts, and what comes back. Every one runs as a node on the Treza canvas.
“A 20 second single take: a lighthouse at dusk as its beam begins to turn, waves below, 16:9”
A long beat with the sound of the sea, in one generation.
“Start on this storefront photo (attached): people walk past, slow dolly forward, 8 seconds”
Life added to a still, opening on your frame.
“First frame: a bare room. End frame: the same room furnished (both attached)”
A before and after, as one transition.
“A barista pours steamed milk into a latte, slow push-in, 9:16, 6 seconds”
A vertical beat for Shorts and Reels.
“The keeper, re-rendered at 4K for a large screen, 10 seconds”
The top tier, for the clip that plays biggest.
“A forest path in morning fog, audio off, to sit under a voiceover”
A silent take, ready for narration.
LTX-2.3 Fast is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with LTX-2.3 Fast
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
LTX-2.3 Fast as an API, priced per clip
The LTX-2.3 Fast API
Build a pipeline with LTX-2.3 Fast on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
LTX-2.3 Fast pricing
Prepaid credits, no subscription. Each clip is charged at LTX-2.3 Fast's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
LTX-2.3 Fast, answered
What is LTX-2.3 Fast?
LTX-2.3 Fast is Lightricks' LTX-2.3 video model on fal's fast endpoint. It turns a prompt, a first frame, or a first and end frame into a clip with native audio at 1080p, 1440p or 4K, up to 20 seconds at 1080p. Treza runs it in the Video Generation node, and fal lists it from 6 cents a second.
What does LTX-2.3 Fast cost?
fal lists 6 cents a second at 1080p, 12 cents at 1440p and 24 cents at 4K, with or without sound, so a 10 second 1080p clip is 60 cents of provider cost. Treza bills the length you set at that rate, quotes it plus its credit markup before a run, and a failed generation costs nothing.
What is the difference between LTX-2.3 Fast and LTX-2.5 Fast?
LTX-2.3 Fast starts at 1080p and lists less at every tier the two share: 6 cents a second at 1080p, 12 at 1440p and 24 at 4K, against 13, 19 and 30 for LTX-2.5 Fast. LTX-2.5 Fast also has a 720p tier, at 9 cents. Both add sound, take a first and end frame, and run up to 20 seconds at 1080p.
Is LTX-2.3 Fast cheaper than Veo 3.1 Lite at 1080p?
With sound, on list price, yes: fal lists LTX-2.3 Fast at 6 cents a second at 1080p and OpenRouter lists Veo 3.1 Lite at 8. Silent, Veo 3.1 Lite lists 5. Veo 3.1 Lite renders 4, 6 or 8 seconds and runs in chat; LTX-2.3 Fast renders up to 20 seconds at 1080p and runs on the canvas.
Can I use LTX-2.3 Fast in chat?
It runs on the canvas, in the Video Generation node. In chat, ask for Veo 3.1 Lite.
How much does LTX-2.3 Fast cost on Treza?
Treza uses prepaid credits with no subscription. Each clip is charged at LTX-2.3 Fast's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call LTX-2.3 Fast through an API?
Yes. Build a pipeline that uses LTX-2.3 Fast and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.