Video Models
Generate video from text and image inputs.
On this page
Overview
Video models generate short-form video from text descriptions or reference images. Available models are based on the LTX architecture.
Available models
| Slug | Capability | Pricing |
|---|---|---|
| ltx-2-distilled | Text-to-Video | 10 credits/second |
| ltx-2-3-distilled | Text/Image-to-Video | 10 credits/second |