Skip to main content
LightricksAug 11, 2026

LTX Video 2.5 Pro

ltx-2-5-pro-text-to-videoAnonymizedOpen weights

LTX Video 2.5 Pro is the quality-focused tier of Lightricks’ open-weight LTX-2.5. This text-to-video variant generates 6-, 8- or 10-second clips at up to 1080p, with optional audio.

from$0.132
per second of video
1080p
max resolution, 2 sizes
10s
longest clip, from 6s
Mode

Same prompt, other models

Every video model renders the same reference prompts, so their clips line up side by side. Hover a clip to play it.

Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K

Pricing

Billed per clip in USD, by length and resolution. Each resolution is drawn to scale.

Price per clip by length and resolution, with audio
720p1080p
6s clip$0.79$1.12
8s clip$1.06$1.50
10s clip$1.32$1.87

Audio on or off costs the same. Quoted from POST /video/quote on Nov 19, 2026. Prices can change, so quote a job before you queue it.

Estimate a batch

Resolution
Length
Audio
$0.79per 6s clip
$7.90for 10 clips

Against other video models

How it comparesamong 59 video models
Price per secondcheaper than 24%$0.132
Longest cliplonger than 9%10s

Further right is better. Hover a dot for its model.

Capabilities

2 modes, each with its own model ID.

Text to videoltx-2-5-pro-text-to-video
Takes prompt
Image to videoltx-2-5-pro-image-to-video
Takes prompt and image
Audioaudio: true | false

Aspect ratios

16:99:16

Specs

Model ID
ltx-2-5-pro-text-to-video
Mode
Text to video
Endpoint
POST /api/v1/video/queue
Resolutions
720p, 1080p
Lengths
6s, 8s, 10s
Aspect ratios
16:9, 9:16
Audio
Optional, on by default
Inputs
Prompt
Prompt limit
2,500 characters
Privacy
Anonymized
Added
Aug 11, 2026

Quickstart

Video is asynchronous: queue a job, then poll for the clip.

  1. 1QuotePOST /video/quoteOptional. Prices the job in USD without charging for it.
  2. 2QueuePOST /video/queueChecks and charges the job, then returns a queue_id at once.
  3. 3RetrievePOST /video/retrievePoll it with the queue_id until the video is ready.
# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ltx-2-5-pro-text-to-video",
"prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
"duration": "6s",
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": true
}'

# 2. Poll until the MP4 is ready (JSON with the status until then)
curl https://api.venice.ai/api/v1/video/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "ltx-2-5-pro-text-to-video", "queue_id": "<queue_id>" }' --output video.mp4

# If the queue response has a download_url, retrieve only reports the
# status: download the MP4 from that URL once it is COMPLETED.
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelltx-2-5-pro-text-to-videoRequired
promptUp to 2,500 charactersRequired
duration6s | 8s | 10sRequired
resolution720p | 1080pOptional
aspect_ratio16:9 | 9:16Required
audiotrue | falseDefault true