APIMODELSAPIMODELS
All
Models/LTX 2.5 Pro
Lightricks

LTX 2.5 Pro API

ltx-2.5-pro

LTX 2.5 Pro is the tier of Lightricks' LTX-2.5 video model that Lightricks tunes for visual fidelity and stable motion: it turns a prompt or a still image into a finished 6, 8 or 10 second shot with sound at 720p or 1080p, through one API call and without your own GPUs. Call ltx-2.5-pro from $0.108/s at 720p, 10% below Lightricks' API list price; failed tasks are not charged.

Text to VideoImage to Video (First Frame)720p / 1080p6 / 8 / 10s24 / 25 / 48 / 50 fpsNative AudioSeedFrom $0.108/s
720p · per second$0.108
1080p · per second$0.153
720p · 6s$0.648
720p · 10s$1.08
1080p · 6s$0.918
1080p · 10s$1.53
API Docs

Generate Video

Limits: 720p or 1080p only (no 1440p, no 4K) · 6, 8 or 10 s · one first-frame image (JPG, PNG or WEBP, up to 10 MB), no last frame, reference images or video input · no audio-to-video on Pro (use LTX 2.5 Fast) · sound is always generated · not every request succeeds, and failed tasks are not charged.
Mode: Text-to-video(chosen from your inputs: prompt only, or + first frame)
Estimated price: $1.53= $0.153/s × 10 s (1080p)

Result

Generated video will appear here

Provide URLs and click Generate

The LTX-2.5 Tier for Final Renders

Lightricks describes Pro as tuned for visual fidelity and motion stability, and Fast for speed and cost. Both take the same request fields

Text or a First Frame

A prompt alone is text-to-video; add image_url and the clip opens on that image and keeps its aspect ratio

720p or 1080p, 6 / 8 / 10 Seconds

At 24, 25, 48 or 50 fps. Text-to-video takes 16:9, 9:16, 1:1, 3:2 or 2:3

Sound on Every Clip

Audio is generated together with the picture; there is nothing to switch on

10% Below the ltx.io List Price

$0.108 per second at 720p and $0.153 at 1080p, against $0.12 and $0.17 on Lightricks’ API pricing page

Limits, Stated Plainly

No audio-to-video, 1440p or 4K on Pro here (use LTX 2.5 Fast for audio and 1440p), no last frame or reference images. Failed tasks are not charged

LTX 2.5 Pro API: final-render LTX-2.5 shots with sound, from $0.108 per second

LTX 2.5 Pro is the LTX-2.5 tier that Lightricks tunes for visual fidelity and motion stability: it turns a prompt or one still image into a 6, 8 or 10 second shot at 720p or 1080p, with sound generated alongside the picture.

Use it for the take you keep, such as a product hero shot, an opening scene or an ad cut, after the prompt is settled.

On APIMODELS the LTX 2.5 Pro API is the model id ltx-2.5-pro on POST /v1/video/generations, from $0.108 per second at 720p, 10% below Lightricks’ list price; a failed task is not charged.

Model ID
ltx-2.5-pro
Modes
Text · image to video
Resolution
720p · 1080p
Length
6 · 8 · 10 s
Price
from $0.108/s

LTX 2.5 Pro examples: two real clips from our tests

Each clip is one LTX 2.5 Pro request at 720p, 6 seconds, run once on 20 November 2026 and shown as it came back. Open a card for the exact prompt and the input image.

Each LTX 2.5 Pro clip cost $0.648; the dialogue came back in 65 seconds and the photo-to-video clip in 104 seconds, queue included. Both lines of dialogue came out word for word, with the faces framed closer than on LTX 2.5 Fast; the cook and the customer still share one table rather than a counter. From the mug photo, Pro moved the camera a little more than Fast but did not orbit, and the soundtrack is almost silent.

Two-person dialogue with sound1280×720 · 6sLine: Last bowl of the night, on the house. / You say that every night.
Prompt (exact text sent)
Static medium shot inside a tiny ramen shop at night, steam rising from a pot behind the counter, warm paper lanterns overhead. A cook in his fifties with a white headband wipes the counter, looks up at a young woman sitting across from him and says, "Last bowl of the night, on the house." She laughs and replies, "You say that every night." Sound: broth simmering, light rain on the window, their two voices.
Product photo to video1280×720 · 6sReference imagesProduct photo to video — reference image 1
Prompt (exact text sent)
Steam rises gently from the mug, warm morning sunlight slowly moves across the oak table, and the camera orbits slowly to the right around the mug. Sound: quiet cafe ambience and birds outside the window.

How to use the LTX 2.5 Pro API in 3 steps

  1. Send the prompt, and an image if you have one

    An LTX 2.5 Pro request is POST /v1/video/generations with model ltx-2.5-pro and a prompt. Add image_url to open the shot on your own frame; leave aspect_ratio out in that case.

  2. Choose 720p or 1080p and 6, 8 or 10 seconds

    Any of 24, 25, 48 or 50 fps works at either resolution, and the price only depends on resolution and seconds: 8 seconds at 1080p is $1.224.

  3. Poll or wait for the callback

    The task is asynchronous: poll GET /v1/video/generations?task_id= until state is completed, or pass callback_url, then download data.resultUrls[0] within 30 days.

Image-to-video request
curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ltx-2.5-pro",
    "prompt": "The perfume bottle on the marble counter catches the morning light as the camera slowly arcs to the right; a soft piano note rings out.",
    "image_url": "https://example.com/bottle.jpg",
    "resolution": "1080p",
    "fps": 24,
    "duration": 8
  }'

What LTX 2.5 Pro is used for

LTX 2.5 Pro is for final shots of up to 10 seconds; each scenario below has its own limit.

Image to video

Product hero shot from a still

LTX 2.5 Pro turns an approved product photo in image_url into a hero shot; describe one slow camera move and the ambient sound. 10 seconds at 1080p is $1.53.

Limit: printed text and logos can still drift, so check the frames before the ad goes out.

image_url
Text to video

An opening or establishing shot

LTX 2.5 Pro builds an opener from a prompt that names the place, the light and one camera move; 1:1, 3:2 and 2:3 are there for formats beyond 16:9 and 9:16.

Limit: 10 seconds is the ceiling on Pro; a longer opener has to be cut from several clips or made on Fast.

aspect_ratio
Image to video

Bringing a key visual to life

Use a finished illustration or render as the first frame and ask for subtle motion such as hair, cloth or particles, so the composition holds.

Limit: no last frame, so the shot cannot be forced back to the original layout at the end.

image_url
Workflow

The final take after drafts on Fast

LTX 2.5 Pro renders the take you keep: settle the prompt on ltx-2.5-fast, then send the same body with model ltx-2.5-pro and a duration of 6, 8 or 10.

Limit: a Fast draft at 12 seconds or more, or at 1440p, has no Pro equivalent here.

ltx-2.5-fastltx-2.5-pro
Text to video

A vertical 9:16 ad cut

LTX 2.5 Pro renders a vertical ad cut when you set aspect_ratio 9:16 and keep the prompt to one product, one action and one line of voice-over; 6 seconds at 1080p is $0.918.

Limit: the voice and music are generated with the picture, so a fixed brand jingle or a recorded voice-over has to be laid on in editing, or the clip made on Fast with audio_url.

aspect_ratio

Who LTX 2.5 Pro is for, and who it is not for

Good fit

Final shots of 10 seconds or less

It suits ad cuts, product shots and openers where Lightricks’ fidelity tier is worth about 31% more per second than Fast at 1080p.

Good fit

Apps that offer a "high quality" option

It takes the same fields as ltx-2.5-fast, so a quality switch in your product is one model string.

Not a fit

Voice or music driven clips

LTX 2.5 Pro has no audio-to-video here. Use ltx-2.5-fast, which keeps your track as the soundtrack.

Not a fit

Anything longer than 10 seconds or above 1080p

LTX 2.5 Pro stops at 10 seconds and 1080p here. Fast goes to 20 seconds and 1440p; Lightricks’ own API offers Pro up to 4K.

LTX 2.5 Pro vs LTX 2.5 Fast vs LTX 2.3 on apimodels.app

LTX 2.5 ProLTX 2.5 FastLTX 2.3
Model idltx-2.5-proltx-2.5-fastltx-2.3
ModesText, first-frame image to videoText, first-frame image, audio to videoText, one image to video
Resolution720p, 1080p720p, 1080p, 1440p480p, 720p, 1080p
Length6, 8 or 10 s6–20 s in even steps (6, 8 or 10 at 1440p or 48 / 50 fps)Text 5–15 s, image 5–20 s
Frame rate24, 25, 48, 50 fps24, 25, 48, 50 fpsNot selectable
Aspect ratio (text-to-video)16:9, 9:16, 1:1, 3:2, 2:316:9, 9:16, 1:1, 3:2, 2:316:9, 9:16
Audio-to-videoNoYesNo
SeedYesYesNo
Price per second$0.108 / $0.153 (720p / 1080p)$0.081 / $0.117 / $0.171 (720p / 1080p / 1440p)$0.02 / $0.04 / $0.045 (480p / 720p / 1080p)
10 s at 1080p$1.53$1.17$0.45

Source: request rules and prices on apimodels.app, 2026-11-20. The quality difference between Pro and Fast is Lightricks’ positioning; we have not published our own comparison yet.

Why use LTX 2.5 Pro here: apimodels.app vs the LTX API and fal.ai

Three ways to run LTX-2.5 Pro, compared on capability rows only; the other two are stronger on several of them.

apimodels.appLTX API (Lightricks)fal.ai
Highest resolution (Pro)1080p4K1080p
Audio-to-video on ProNoYesYes
Last frameNoYes (last_frame_uri)Yes (end_image_url)
Silent outputNoYes (generate_audio false)Yes (generate_audio false)
Frame rates24, 25, 48, 5024, 25, 48, 5024, 25, 50
Text-to-video aspect ratios16:9, 9:16, 1:1, 3:2, 2:316:9, 9:16, 1:1, 3:2, 2:316:9, 9:16
Same key for other modelsYesLTX models onlyYes

Checked on 2026-11-20 on docs.ltx.io (LTX-2.5 support matrix, image-to-video and audio-to-video references) and fal.ai’s LTX-2.5 Pro model pages. Pick Lightricks’ API for Pro at 1440p or 4K, Pro audio-to-video or a last frame; pick apimodels.app for 48 fps and five aspect ratios on one key you already use for other models.

LTX 2.5 Pro limits and pricing, in numbers

ResolutionPer second6 s8 s10 sLightricks list price
720p$0.108$0.648$0.864$1.08$0.12/s
1080p$0.153$0.918$1.224$1.53$0.17/s

LTX 2.5 Pro inputs: a prompt of 1–5,000 characters; one first frame in JPG, PNG or WEBP up to 10 MB. Not available on Pro here: audio-to-video, 1440p, 4K, last frame, reference images and video input; requests with them return a 400 and are not charged.

LTX 2.5 Pro success is not 100%: content review or a busy upstream can fail a task, and failed tasks are not charged. Results are kept for 30 days.

How long it takes: in our tests on 20 November 2026, LTX 2.5 Pro returned 6-second 720p clips in 65 and 104 seconds, queue included. Two runs, not a guarantee; 1080p, longer clips and busy hours take longer.

Sources

Checked on 2026-11-20. Lightricks’ statements on this page are the vendor’s claims; prices are apimodels.app prices.

TL;DR LTX 2.5 Pro is a Lightricks video generation model, callable via APIMODELS' unified API (model name `ltx-2.5-pro`). Pricing: 720p · per second: $0.108, 1080p · per second: $0.153, 720p · 6s: $0.648, 720p · 10s: $1.08, 1080p · 6s: $0.918, 1080p · 10s: $1.53. One API key for all image / video / LLM / audio models.

About LTX 2.5 Pro

LTX 2.5 Pro is a Video Generation API provided by Lightricks. LTX 2.5 Pro is the higher-fidelity tier of LTX-2.5, the open-weights video and audio model Lightricks released in August 2026; Lightricks describes Pro as tuned for visual fidelity and motion stability, for final and commercial-grade renders, while Fast is for speed and cost. On APIMODELS it is the model id ltx-2.5-pro on POST /v1/video/generations, from $0.108 per second at 720p, 10% below Lightricks' API list price, and failed tasks are not charged. Two modes, picked from your inputs: a prompt alone is text-to-video, and a prompt plus one first-frame image in image_url is image-to-video, where the clip opens on that image and keeps its aspect ratio. Every clip comes with sound generated together with the picture. Output is 720p or 1080p (the default) at 24, 25, 48 or 50 fps, and 6, 8 or 10 seconds long (10 by default). Text-to-video takes aspect_ratio 16:9, 9:16, 1:1, 3:2 or 2:3, and seed (0 to 2147483647) is optional. Billing is per second of output: $0.108 at 720p and $0.153 at 1080p, so 6 seconds at 720p is $0.648, 10 seconds at 720p $1.08 and 10 seconds at 1080p $1.53; Lightricks lists $0.12 and $0.17. Frame rate does not change the price. Against LTX 2.5 Fast on this site, Pro costs about 31% more per second at 1080p ($0.153 against $0.117) and stops at 10 seconds and 1080p, while Fast reaches 20 seconds, 1440p and audio-to-video. Lightricks' own API also offers Pro at 1440p and 4K and Pro audio-to-video; those are not available on APIMODELS, and a request with audio_url on ltx-2.5-pro returns a 400 before anything is charged. Other limits: no last frame, no reference images and no video input; one first frame in JPG, PNG or WEBP up to 10 MB; prompts up to 5,000 characters. A common way to use the pair is to try prompts on Fast and render the chosen shot on Pro; both take the same field names, so switching is one model string. Not every request succeeds: content review or a busy upstream can fail a task, and failed tasks are not charged. The API is asynchronous: the create call returns a task id, then you poll GET /v1/video/generations?task_id= until the state is completed, or pass callback_url. Result files are kept for 30 days. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: 720p · per second: $0.108, 1080p · per second: $0.153, 720p · 6s: $0.648, 720p · 10s: $1.08, 1080p · 6s: $0.918, 1080p · 10s: $1.53.

Related model: LTX 2.5 Fast — the speed tier of the same model — adds 1440p, clips up to 20 seconds and audio-to-video, from $0.081/s

Related model: LTX-2.3 — the previous LTX — 480p / 720p / 1080p in 16:9 or 9:16, 5-20 seconds, from $0.02/s

Key Features

  • The LTX-2.5 Tier for Final Renders -- Lightricks describes Pro as tuned for visual fidelity and motion stability, and Fast for speed and cost. Both take the same request fields
  • Text or a First Frame -- A prompt alone is text-to-video; add image_url and the clip opens on that image and keeps its aspect ratio
  • 720p or 1080p, 6 / 8 / 10 Seconds -- At 24, 25, 48 or 50 fps. Text-to-video takes 16:9, 9:16, 1:1, 3:2 or 2:3
  • Sound on Every Clip -- Audio is generated together with the picture; there is nothing to switch on
  • 10% Below the ltx.io List Price -- $0.108 per second at 720p and $0.153 at 1080p, against $0.12 and $0.17 on Lightricks’ API pricing page
  • Limits, Stated Plainly -- No audio-to-video, 1440p or 4K on Pro here (use LTX 2.5 Fast for audio and 1440p), no last frame or reference images. Failed tasks are not charged

Use Cases

Marketing Videos

Quickly generate brand promotion videos for ad campaigns and social media marketing.

Social Media Content

Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.

Product Demos

Generate product feature demonstrations and tutorials to improve user conversion.

Educational Content

Produce course explanations, knowledge explainers, and training videos at an affordable price.

Why APIMODELS

  • Unified API -- One API key to access all models, no need to register on multiple platforms
  • Transparent Pricing -- Pay-as-you-go with per-call pricing published on every model page, ideal for indie developers and startups
  • Instant Access -- Start right after signup; pay by card, PayPal, Alipay or USDT
  • Full Documentation -- Detailed API docs with code examples in cURL, Python, and Node.js

Frequently Asked Questions

What is the difference between APIMODELS and the official Lightricks API?

APIMODELS offers the same LTX 2.5 Pro model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.

What is LTX 2.5 Pro, and how do I call it through an API?

LTX 2.5 Pro is the tier of Lightricks' LTX-2.5 (released 11 August 2026) that Lightricks tunes for visual fidelity and motion stability, meant for final renders. On apimodels.app it is the model id ltx-2.5-pro: POST https://api.apimodels.app/v1/video/generations with your API key and {"model": "ltx-2.5-pro", "prompt": "...", "resolution": "1080p", "duration": 8}, then poll GET /v1/video/generations?task_id= until state is completed, or pass callback_url. Add image_url to start the clip from your own first frame. No Lightricks account is needed; the full parameter list is on /docs/ltx-2-5.

LTX API pricing: Fast vs Pro (Lightricks) ↗

How much does LTX 2.5 Pro cost per second?

$0.108 per second at 720p and $0.153 at 1080p, 10% below Lightricks' list price for ltx-2-5-pro ($0.12 and $0.17). Clips are 6, 8 or 10 seconds, so the full range is $0.648 (6 s at 720p) to $1.53 (10 s at 1080p); 6 seconds at 1080p is $0.918. Frame rate and mode do not change the rate, and failed tasks are not charged.

LTX API pricing (Lightricks) ↗

LTX 2.5 Pro vs LTX 2.5 Fast: is Pro worth it?

Pick Pro when the clip is a final shot of 10 seconds or less at 720p or 1080p and you want the tier Lightricks positions for fidelity and stable motion; it costs about 31% more per second than Fast at 1080p ($0.153 against $0.117). Pick Fast for anything longer than 10 seconds, for 1440p, for audio-to-video, or for the many tries it takes to settle a prompt. Both take the same fields, so the usual pattern is to explore on ltx-2.5-fast and switch the model string for the take you keep. In our tests on the same dialogue and photo prompts, Pro framed faces closer and moved the camera a little more, but it was not a clear step up from Fast, and it took 65 to 104 seconds against 41 to 73.

Our test clips: LTX 2.5 vs Seedance 2.0 (apimodels.app blog) ↗

LTX 2.5 Pro vs MiniMax H3: how do they compare?

On apimodels.app LTX 2.5 Pro makes 6, 8 or 10 second clips at 720p or 1080p and 24 to 50 fps, from a prompt or one first-frame image, with sound generated alongside. MiniMax H3 makes 5–15 second clips at 768P or native 2K and accepts up to 9 reference images, 3 reference videos and 3 reference audio clips besides the prompt. So H3 covers longer clips and multi-reference control, while LTX 2.5 Pro is the simpler request when one prompt or one opening frame defines the shot. In our same-prompt dialogue test, MiniMax H3 at 768P staged the scene more faithfully than LTX 2.5 Pro (H3 kept the counter between the two speakers, Pro sat them at one table), but it took 4.1 minutes against 65 seconds.

Our same-prompt test: LTX 2.5 vs MiniMax H3 (apimodels.app blog) ↗

Can LTX 2.5 Pro do image-to-video or lip sync?

Image-to-video, yes: put one JPG, PNG or WEBP (up to 10 MB) in image_url, leave aspect_ratio out, and the clip opens on that image in its shape. Lip sync and audio-to-video, no: Lightricks' own API offers audio-to-video on Pro, but on apimodels.app it runs on ltx-2.5-fast only, and an audio_url sent to ltx-2.5-pro returns a 400 before anything is charged. For a talking or singing clip, send the portrait and the audio to ltx-2.5-fast.

How should I prompt LTX 2.5 Pro?

The same way as any LTX-2.5 model: Lightricks' prompting guide asks for one paragraph in the present tense that moves from the shot and setting to the action, the camera and the sound, with dialogue in quotes. Because Pro clips stop at 10 seconds, keep it to one or two beats; a crowded scene with many characters reads worse than a focused one. For image-to-video, describe what moves rather than what the picture already shows. Prompts can be up to 5,000 characters.

LTX prompting guide (Lightricks docs) ↗

What are the limits of LTX 2.5 Pro here?

720p or 1080p only (no 1440p or 4K on APIMODELS), 6, 8 or 10 seconds, no audio-to-video, no last frame, no reference images and no video input; requests with these return a 400 and are not charged. One first frame in JPG, PNG or WEBP up to 10 MB, prompts up to 5,000 characters, aspect_ratio only for text-to-video. Not every task succeeds: content review or a busy upstream can fail one, and failed tasks are not charged. Results are kept for 30 days.

What can LTX 2.5 Pro do?

LTX 2.5 Pro supports: Text to Video, Image to Video (First Frame), 720p / 1080p, 6 / 8 / 10s, 24 / 25 / 48 / 50 fps, Native Audio, Seed, From $0.108/s. See the APIMODELS docs for full parameters and call examples.

Can I use the LTX 2.5 Pro API from any country, including mainland China?

Yes. APIMODELS does not restrict access by country: the site and the API answer requests from anywhere, and apimodels.app and api.apimodels.app are reachable directly from mainland China without a proxy. You call LTX 2.5 Pro with one APIMODELS key, so you do not need a separate account with the model's developer.

What payment methods are supported? Can I pay with PayPal or crypto?

Yes to both. You can top up with a card (Visa, Mastercard and others, through Stripe), PayPal, Alipay, or USDT on TRON (TRC20) or BNB Smart Chain (BEP20). Card, PayPal and Alipay top-ups are credited immediately; USDT is credited once the transfer confirms on-chain. Auto top-up is optional, and a $50 top-up adds a $1 bonus ($3 on a $100 top-up). The balance is in USD and billed per use, with no subscription.

Related models

Need prompts?

We curate copy-ready prompt libraries — every entry shows its full text and a sample result, ready to adapt.