Kling Video
Kling Video Overview
Organize Kling's OpenAI-format interfaces by model series.
Kling Videos
The Kling video series uses the OpenAI-compatible /v1/videos interface and supports text-to-video, image-to-video, multiple reference images, first-and-last-frame, motion control, digital avatars, and lip sync.
OpenAI Format
| Purpose | Method | Path |
|---|---|---|
| Submit a video generation task | POST | /v1/videos |
| Query task status and results | GET | /v1/videos/{task_id} |
| Fetch the generated video content | GET | /v1/videos/{task_id}/content |
Video Generation
POST /v1/videos, submit a Kling video task.
Task Status Query
GET /v1/videos/{task_id}, query task status and results.
Supported Models
| Model | Description | Duration Options (seconds) |
|---|---|---|
Kling-3.0-Omni | Kling 3.0 all-in-one edition | 5, 10, 15 (default 5) |
Kling-3.0 | Kling 3.0 | 5, 10 (default 5) |
Kling-2.6 | Kling 2.6 | 5, 10 (default 5) |
Kling-2.5 | Kling 2.5 | 5, 10 (default 5) |
Kling-2.1 | Kling 2.1 | 5, 10 (default 5) |
Kling-2.0 | Kling 2.0 | 5, 10 (default 5) |
Kling-1.6 | Kling 1.6 | 5, 10 (default 5) |
Kling-O1 | Kling O1 | 5, 10 (default 5) |
Composite billing model names can also be passed directly as model; the gateway restores the upstream model name and fills in the parameters: kling-3.0-omni-1080p-ref-audio (1080P · with reference · with sound), kling-2.6-motion-pro-1080p (motion control · pro tier), kling-avatar-720p (digital avatar), kling-identify-face (lip sync). Kling-O3 and Kling-Mini are not preset yet.
Scene Types
| Scene Type | Description | Key Conditions |
|---|---|---|
motion_control | Motion control | A video reference is required |
avatar_i2v | Digital avatar | Billed as the avatar scene (kling-avatar-720p) |
lip_sync | Lip sync | Billed at 5 seconds if shorter (kling-identify-face) |
template_effect | Template effects | Vidu scene |
Parameter Description
Basic Parameters (Top Level)
| Field | Type | Description |
|---|---|---|
model | string | Model name (base model or composite billing model) |
prompt | string | Prompt |
seconds | string | integer | Video duration in seconds; top level takes priority; default 5 |
duration | string | integer | Duration compatibility field; effective when top-level seconds is absent |
size | string | Quick size (720P / 1080P or WxH) |
image | string | Single reference / first-frame image (URL or file ID) |
images | array<string> | Multiple reference images (up to 3) |
metadata Parameters
| Field | Type | Description |
|---|---|---|
output_config | object | Output configuration (maps to upstream AigcVideoOutputConfig) |
scene_type | string | Scene type (motion_control / avatar_i2v / lip_sync / template_effect) |
motion_level | string | Motion control tier std / pro (billing tier) |
offpeak | boolean | Whether off-peak billing is enabled |
last_frame_url | string | Last frame of a start/end frame pair (URL) |
last_frame_file_id | string | Last frame of a start/end frame pair (file ID) |
video_url | string | Reference video URL (required for motion control) |
file_infos | array<object> | Native FileInfos passthrough (up to 3 items) |
ext_info | string | Native ExtInfo string passthrough |
output_config Parameters
| Field | Type | Description |
|---|---|---|
resolution | string | Resolution 720P / 1080P, default 720P |
aspect_ratio | string | Aspect ratio 16:9 / 9:16 / 1:1 (default 16:9 for text-to-video) |
duration | float | Generation duration (seconds); Kling supports 5 / 10 |
audio_generation | string | Enabled / Disabled |
person_generation | string | AllowAdult / Disallowed |
input_compliance_check | string | Enabled / Disabled |
output_compliance_check | string | Enabled / Disabled |
enhance_switch | string | Enabled / Disabled |
storage_mode | string | Permanent / Temporary, default Temporary |
media_name | string | Output media name (max 64 characters) |
class_id | integer | Class ID, default 0 |
expire_time | string | Expiration time (ISO 8601) |
frame_interpolate | string | Enabled / Disabled (Vidu) |
logo_add | string | Enabled / Disabled (Vidu) |
Parameter Rules
- Duration priority: top-level
seconds> top-levelduration>metadata.seconds/metadata.duration/metadata.video_duration> default5 - Resolution priority:
output_config.resolution> top-levelsize> default720P motion_controlrequires a video reference (video_urlor afile_infosentry withCategory=Video)FileInfosis limited to 3 items; top-level images do not support base64 data URIslip_syncis billed at 5 seconds when shorter than 5 seconds
Featured Capabilities
| Feature | Description |
|---|---|
| Motion control | scene_type: motion_control, precisely control motion from a reference video; tiers std / pro |
| Digital avatar | scene_type: avatar_i2v, generate digital avatar videos |
| Lip sync | scene_type: lip_sync, synchronized lip syncing with audio and video |
| Off-peak billing | offpeak: true, generate during off-peak hours for lower cost |
| Start/end frames | image + last_frame_url, control the start and end frames |
| Multiple reference images | Top-level images (≤3) or native file_infos passthrough |