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

# Kling

> Kling video via OpenAI-style /v1/videos.

# Kling

Call **Kling** through the OpenAI-style async Video API:

| Action | Method | Path |
| - | - | - |
| Create | `POST` | `/v1/videos` |
| Get status | `GET` | `/v1/videos/{task_id}` |
| Download | `GET` | `/v1/videos/{task_id}/content` |

**Host:** `https://api.omniall.ai` · Auth `Authorization: Bearer sk-...`.

## Models

Generation aliases (case-insensitive): `kling-1.0`, `kling-1.5`, `kling-2.0`, `kling-2.1`, `kling-2.5`, `kling-3.0`, `kling-3.0-omni`, `kling-o1`.

Specialty: `kling-identify-face` (lip sync), `kling-avatar-720p`, `kling-avatar-1080p`.

See the [Model Square](https://omniall.ai/pricing). Status responses may show the concrete billing tier.

## Defaults & priority

| Item | Rule |
| - | - |
| Duration | `seconds` > `duration` > metadata duration fields > **5s** |
| Resolution | `output_config.resolution` > `metadata.resolution` > `size` > **720P** |
| Audio | Default **Disabled** (mute) |
| Motion tier | Default **std** |
| T2V aspect | Default **16:9** |

## Scenarios

| Scenario | Key fields |
| - | - |
| Text-to-video | `prompt` + `seconds` + `output_config` |
| Single image | `image` + `prompt` |
| Multi-image | `images[]` (Omni) |
| First / last frame | `image` + `metadata.last_frame_url` |
| Motion control | `scene_type=motion_control` + public `video_url` |
| Avatar | `scene_type=avatar_i2v` or specialty model |
| Lip sync | `scene_type=lip_sync` or `kling-identify-face` |
| Reference video | `metadata.file_infos` |
| Multi-shot | `metadata.ext_info` (JSON **string**) |

Motion control requires a **publicly reachable** reference video URL.


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