> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ltx.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ltx.io/_mcp/server.

# Supported Models

> Explore all supported LTX models for text-to-video, image-to-video, and other generation tasks. Learn their capabilities and best use cases.

The LTX API offers video generation powered by **LTX-2.5** and **LTX-2.3** — portrait and landscape video up to 4K, cinematic frame rates, and first-to-last frame control. Pass the model ID in the `model` field of your request.

#### [LTX-2.5](/models/ltx-2-5)

Fast and Pro variants. Portrait and landscape video up to 4K at cinematic frame rates (24 fps and 48 fps). Stronger prompt adherence and finer detail in texture, faces, and typography, plus [automatic duration](/models/ltx-2-5#automatic-duration) — let the model choose the clip length from your prompt.

#### [LTX-2.3](/models/ltx-2-3)

Portrait and landscape video up to 4K. Cinematic frame rates (24/48 fps), first-to-last frame control for [image-to-video](/api-documentation/api-reference/async-video-generation/submit-image-to-video), and sharp detail with accurate prompt handling.

## Endpoint compatibility

Not every endpoint supports every model.

| Endpoint       | ltx-2-5-fast | ltx-2-5-pro | ltx-2-3-fast | ltx-2-3-pro |
| -------------- | ------------ | ----------- | ------------ | ----------- |
| text-to-video  | ✓            | ✓           | ✓            | ✓           |
| image-to-video | ✓            | ✓           | ✓            | ✓           |
| audio-to-video | ✓            | ✓           | —            | ✓           |
| retake         | —            | —           | —            | ✓           |
| extend         | —            | —           | —            | ✓           |

Supported resolutions, frame rates, and durations differ per model — see [LTX-2.5](/models/ltx-2-5#support-matrix) and [LTX-2.3](/models/ltx-2-3#support-matrix).

## Pricing

For per-second pricing by model and resolution, see the [Pricing](/pricing) page.