Use this in the request body model field.
Video APIActive
ltx-2 API
Generate AI videos with LTX-2 19B via API in One. 4 modes: text-to-video, image-to-video, lipsync, and control. Up to 1080p, 5–20s. 20–512 credits per video.
The currently implemented BFF route.
Input types: text, image, video, audio
Keys are managed by the shared dashboard.
This route does not require webhook handling.
Live capabilities
These capabilities come from the current model config and backend route. Unreleased APIs are not listed.
4 specialized modes in one model
4 specialized modes in one model
Lipsync from audio input
Lipsync from audio input
Video control with pose/depth/canny
Video control with pose/depth/canny
Up to 1080p and 20 seconds
Up to 1080p and 20 seconds
Request format
Clients call same-origin API routes; the server BFF forwards to the matching Worker.
MethodEndpointCreditsPurpose
POST/api/v1/videos/generations24 creditsLTX-2 19B — advanced AI video generation with text-to-video, image-to-video, lipsync, and control modes. Up to 1080p, 5–20 seconds.
Parameters
promptstringText description (required for text-to-video and image-to-video)
OptionaltypestringMode: "text-to-video", "image-to-video", "lipsync", or "control"
OptionalimagestringImage URL for image-to-video mode
OptionalaudiostringAudio URL for lipsync mode
Optionalaudio_durationnumberAudio duration in seconds for lipsync (5–20)
OptionalvideostringVideo URL for control mode
Optionalvideo_durationnumberVideo duration for control mode (5–20)
OptionalmodestringControl mode: "pose", "depth", or "canny"
Optionalaudio_modestringAudio mode for control: "preserve", "generate", or "none"
OptionalresolutionstringOutput resolution: "480p", "720p", or "1080p"
Optional · Default 720paspect_ratiostringAspect ratio: "16:9" or "9:16" (text-to-video only)
Optional · Default 16:9durationnumberVideo duration in seconds (5–20)
Optional · Default 5seednumberRandom seed for reproducibility (-1 for random)
Optional · Default -1Example request
curl -X POST https://apiin.one/api/v1/videos/generations \
-H "Authorization: Bearer aio_your_api_key" \
-H "Content-Type: application/json" \
--data-raw '{
"model": "ltx-2",
"prompt": "A cat playing piano in a jazz bar, cinematic lighting",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5
}'Models on the same endpoint
These live models use the same implemented BFF endpoint and can be switched by changing the model field.
grok-videovideo · 24 credits/api/v1/videos/generations
seedance-1-5-provideo · 28 credits/api/v1/videos/generations
hailuo-2-3video · 30 credits/api/v1/videos/generations
wan-2-6video · 80 credits/api/v1/videos/generations
pixverse-5-6video · 90 credits/api/v1/videos/generations
kling-3video · 300 credits/api/v1/videos/generationsIntegration flow
These steps use the current live route and shared account system; login, payment, orders, credits, and profile remain shared.
Create a shared API key
Create a key in the existing dashboard. Top-up, orders, credit balance, and profile stay in the shared console.
Call the real endpoint
Send a request with the endpoint, model id, and parameters shown on this page. /api/v1/videos/generations
Poll task status
Async media and tool jobs use /api/v1/tasks/{task_id}; chat models return a direct response.
Task status route
After creating image, video, audio, or tool tasks, poll the real task endpoint for results.
GET/api/v1/tasks/{task_id}Check generation task status and result.Pricing
20–512 credits per video (~$0.20–$5.12)
Base cost$0.24
Credits24
BillingSuccessful requests
Use cases
These workflows are supported by the current model and backend node.
Generate high-quality videos from text prompts
Animate images into video with image-to-video mode
Create lipsync videos by combining audio with AI video
Apply pose/depth/edge control to existing video
FAQ
How much does LTX-2 cost?
Credits depend on mode, resolution, and duration. Text/image-to-video: 20–76 credits. Lipsync: 32–256 credits. Control: 64–512 credits.
What modes does LTX-2 support?
Four modes: text-to-video, image-to-video, lipsync (audio+video), and control (pose/depth/canny). Specify with the "type" parameter.
What resolutions are supported?
480p, 720p, and 1080p. Higher resolutions cost more credits.