Docs/Kling Omni-Video API

Kling Omni-Video API

Multi-modal Visual Language (MVL) video generation -- combine natural language prompts with video, image, and subject references in a single unified endpoint.

Quick Start

Get your API key from the Console

Choose a model (kling-video-o1 or kling-v3-omni)

Send POST request to create task

Poll GET request for video result

Authentication

Add Authorization header with Bearer token to all requests:

Authorization: Bearer YOUR_API_KEY

Available Models

Model	API Name	Features	Price (85% off)
Kling Video O1	`kling-video-o1`	3-10s, MVL Multi-modal, Audio, Per-Second	From $0.0064/s
Kling V3 Omni	`kling-v3-omni`	3-15s, MVL Multi-modal, Audio, Keep Sound, Per-Second	From $0.0064/s

Detailed Pricing (85% off)

Kling Video O1

Mode	Audio	$/s
std	-	$0.0633
std	on	$0.0956
pro	-	$0.0853
pro	on	$0.1280

Kling V3 Omni

Mode	Audio	Keep Sound	$/s
std	-	-	$0.0633
std	-	on	$0.0853
std	on	-	$0.0956
pro	-	-	$0.0853
pro	-	on	$0.1059
pro	on	-	$0.1280

Endpoints

POST/api/v1/video/generations

Create a Kling Omni-Video generation task. Uses the unified omni-video endpoint (POST /kling/v1/videos/omni-video) under the hood.

GET/api/v1/video/generations?task_id=xxx

Query task status and get video URL

Request Parameters

Common Parameters

modelrequiredstring

"kling-video-o1" or "kling-v3-omni"

promptstring

Text prompt (max 2500 chars). Describes the desired video content.

image_listarray

Array of { image_url, type }. type: "first_frame" or "end_frame".

video_listarray

Array of { video_url, refer_type, keep_original_sound }. refer_type: "feature" or "base". keep_original_sound: "yes" or "no".

element_listarray

Array of { element_id }. Subject references for consistent characters/objects.

modestring

"std" (standard) or "pro" (high quality). Default: "std"

durationstring

O1: "3" to "10". V3 Omni: "3" to "15". Default: "5"

soundstring

"on" or "off". Enable audio generation. Default: "off"

aspect_ratiostring

"16:9", "9:16", or "1:1"

callback_urlstring

Webhook URL for completion notification

Advanced Parameters

multi_shotboolean

Enable multi-shot video generation

shot_typestring

Camera shot type control

multi_promptstring

Multi-segment prompt for scene transitions

watermark_infoobject

{ enabled: true/false } - Generate watermarked version

Code Examples

curl -X POST https://apimodels.app/api/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-video-o1",
    "prompt": "A girl dancing on the beach at sunset, cinematic lighting",
    "mode": "std",
    "duration": "5",
    "aspect_ratio": "16:9"
  }'

Response Format

Create Task Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "pending",
    "model": "kling-video/kling-video-o1"
  }
}

Success Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "completed",
    "model": "kling-video/kling-video-o1",
    "resultUrls": ["https://...video.mp4"],
    "createTime": 1705123450000,
    "completeTime": 1705123500000
  }
}

Failed Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "failed",
    "model": "kling-video/kling-video-o1",
    "failMsg": "Content policy violation"
  }
}

Task States

pendingTask queued, waiting to process

processingVideo is being generated

completedVideo generation successful

failedVideo generation failed

Error Codes

400Bad Request - Missing or invalid parameters

401Unauthorized - Invalid API key

402Payment Required - Insufficient credits

404Not Found - Task ID not found

500Internal Server Error

Important Notes

*Video files are stored for 7 days, download promptly
*Omni-Video uses a single unified endpoint -- no need to choose between text-to-video and image-to-video
*At least one of prompt, image_list, or video_list must be provided
*O1 supports 3-10s duration, V3 Omni supports 3-15s duration, both priced per second
*Audio generation is available for both models (set sound: "on")
*Use video_list with refer_type: "base" for video editing/re-creation
*Poll every 5-10 seconds to check status

Try in Playground Get API Key

Model

API Name

Features

Price (85% off)

Kling Video O1

kling-video-o1

3-10s, MVL Multi-modal, Audio, Per-Second

From $0.0064/s

Kling V3 Omni

kling-v3-omni

3-15s, MVL Multi-modal, Audio, Keep Sound, Per-Second

From $0.0064/s

Mode

Audio

$/s

std

$0.0633

std

$0.0956

pro

$0.0853

pro

$0.1280

Mode

Audio

Keep Sound

$/s

std

$0.0633

std

$0.0853

std

$0.0956

pro

$0.0853

pro

$0.1059

pro

$0.1280

Request Parameters

Common Parameters

modelrequiredstring

"kling-video-o1" or "kling-v3-omni"

promptstring

Text prompt (max 2500 chars). Describes the desired video content.

image_listarray

Array of { image_url, type }. type: "first_frame" or "end_frame".

video_listarray

Array of { video_url, refer_type, keep_original_sound }. refer_type: "feature" or "base". keep_original_sound: "yes" or "no".

element_listarray

Array of { element_id }. Subject references for consistent characters/objects.

modestring

"std" (standard) or "pro" (high quality). Default: "std"

durationstring

O1: "3" to "10". V3 Omni: "3" to "15". Default: "5"

soundstring

"on" or "off". Enable audio generation. Default: "off"

aspect_ratiostring

"16:9", "9:16", or "1:1"

callback_urlstring

Webhook URL for completion notification

Code Examples

curl -X POST https://apimodels.app/api/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-video-o1",
    "prompt": "A girl dancing on the beach at sunset, cinematic lighting",
    "mode": "std",
    "duration": "5",
    "aspect_ratio": "16:9"
  }'

Response Format

Create Task Response

{ "code": 200, "msg": "success", "data": { "taskId": "clxxx...", "state": "pending", "model": "kling-video/kling-video-o1" } }

Success Response

{ "code": 200, "msg": "success", "data": { "taskId": "clxxx...", "state": "completed", "model": "kling-video/kling-video-o1", "resultUrls": ["https://...video.mp4"], "createTime": 1705123450000, "completeTime": 1705123500000 } }

Failed Response

{ "code": 200, "msg": "success", "data": { "taskId": "clxxx...", "state": "failed", "model": "kling-video/kling-video-o1", "failMsg": "Content policy violation" } }

Important Notes

*Video files are stored for 7 days, download promptly

*Omni-Video uses a single unified endpoint -- no need to choose between text-to-video and image-to-video

*At least one of prompt, image_list, or video_list must be provided

*O1 supports 3-10s duration, V3 Omni supports 3-15s duration, both priced per second

*Audio generation is available for both models (set sound: "on")

*Use video_list with refer_type: "base" for video editing/re-creation

*Poll every 5-10 seconds to check status