> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ekly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Video

> Text-to-video, image-to-video, reference video and extensions.

Everything goes through one endpoint, `POST /v1/videos`; the body decides the path. Video models
declare **modes** such as text-to-video, image-to-video (a `first_frame`, sometimes a `last_frame`),
reference-to-video (`reference_images`, `reference_videos`, `reference_audios`) and video edit.
`GET /v1/models/{id}` lists each model's modes with the required and optional inputs, allowed values,
resolution tiers and a ready-to-send `example_request` per mode. The pages under **Video models**
in the sidebar show the same, one per model.

| You want | Start with |
| - | - |
| Cinematic clips from a prompt or a still | `seedance-2-5-fal` (480p/720p/1080p) |
| Native audio with the picture | `minimax-h3-max-fal` |
| Long, controllable prompts | `wan-3.0-fal` |
| Continue a clip you already made | `POST /v1/videos` with `source_generation_id` |
| Make a character move like a reference video | `POST /v1/videos` with a motion-control model, `character_image` and `motion_video` |

Price depends on resolution and duration, so estimate with the same `duration_seconds` and `tier`
you will send. Reference inputs take asset ids from [Uploads](/uploads) or an earlier output; the
catalog's duration and frame-rate rules are checked before any credit is reserved.

Model-specific prompting guides: [Seedance 2](https://ekly.ai/guides/seedance-2-prompting),
[Kling](https://ekly.ai/guides/kling-prompting), [LTX 2](https://ekly.ai/guides/ltx-2-prompting).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.