2K
text, image, audio
video
Not listed
About this model
LTX-2.5 Fast is an accelerated endpoint for Lightricks' LTX-2.5 video generation model. Designed for high-speed text-to-video and image-to-video workflows, it trades a degree of rendering fidelity for significantly faster inference speeds. It supports up to 20-second clips, 4K resolution output, and native synchronized audio generation, making it ideal for rapid prototyping and high-throughput production.
Input modalities
text
Accepted as model input
image
Accepted as model input
audio
Accepted as model input
Providers
Available routing options for this model through OneInfer.
Video generation
$0.0900 / second
Video generation
$0.1300 / second
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Video generation1280x720 · 720p · 6–20s · 16:9 | $0.0900 / second |
| Video generation720x1280 · 720p · 6–20s · 9:16 | $0.0900 / second |
| Video generation1920x1080 · 1080p · 6–20s · 16:9 | $0.1300 / second |
| Video generation1080x1920 · 1080p · 6–20s · 9:16 | $0.1300 / second |
| Video generation2560x1440 · 1440p · 6–10s · 16:9 | $0.1900 / second |
| Video generation1440x2560 · 1440p · 6–10s · 9:16 | $0.1900 / second |
| Video generation3840x2160 · 4k · 6–10s · 16:9 | $0.3000 / second |
| Video generation2160x3840 · 4k · 6–10s · 9:16 | $0.3000 / second |
Performance
Published evaluation results associated with this model.
API example
curl -X POST https://api.oneinfer.ai/v1/ula/generate-video \
-H "Authorization: Bearer YOUR_JWT_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"provider": "lightricks",
"model": "Lightricks/LTX-2.5-Fast",
"prompt": "A red fox running through a snowy forest",
"resolution": "1280x720",
"aspect_ratio": "16:9",
"duration": 5,
"generate_audio": false,
"camera_fixed": false,
"service_tier": "default"
}'