Kling AI Video Generation API

Overview

Breaking change (2025-12-19): Added text-to-video type support (multiple models); added sound parameter (V2.6 only, enables audio generation); added aspect_ratio parameter (V2.6 only: 16:9, 9:16, 1:1); added kling-v2-6 model version.
Breaking change (2025-12-10): mode → quality_mode; image → image_urls (array, 1 image); new type field.
Submit via POST https://api.wizzx.ai/api/v1/task/submit/kling-ai; poll with task_id at POST https://api.wizzx.ai/api/v1/task/status.
Required: prompt, type (text-to-video or image-to-video), quality_mode (std/pro), duration (5/10s).
Conditionally required: image_urls (1 image, only for image-to-video).
Optional: model version, sound (V2.6 only), aspect_ratio (V2.6 only), negative prompt, cfg scale (V1.x only), tail frame, static/dynamic masks, camera control, callback, external task id.
Mutual exclusion (image-to-video only): only one of image_tail, dynamic_masks/static_mask, camera_control can be used.

Auth

Header: Authorization: Bearer <your_api_key>

Submit job

Endpoint: POST https://api.wizzx.ai/api/v1/task/submit/kling-ai, Content-Type: application/json

Required

Field	Type	Notes
`prompt`	string	Positive prompt, ≤2500 chars
`type`	string	Generation type: `text-to-video` or `image-to-video`
`quality_mode`	string	Quality mode: `std` (standard) or `pro` (professional)
`duration`	int	Video length: `5` or `10` seconds

Conditionally required

Field	Type	Notes
`image_urls`	[]string	Reference image URLs, exactly 1 image required for `image-to-video`

Optional

Field	Type	Default	Notes
`model_name`	string	`kling-v1`	Model versions (see below)
`aspect_ratio`	string	`16:9`	Video aspect ratio (V2.6 only): `16:9`, `9:16`, `1:1`
`sound`	string	`off`	Generate audio (V2.6 only): `on`, `off`
`image_tail`	string	-	Tail-frame control image URL (image-to-video only); exclusive with brushes/camera
`negative_prompt`	string	-	≤2500 chars
`cfg_scale`	float	0.5	Range [0, 1] (V1.x models only); higher = closer to prompt
`static_mask`	string	-	Static brush mask URL (image-to-video only)
`dynamic_masks`	array	-	Up to 6 groups (image-to-video only); each has `mask` + `trajectories`
`camera_control`	object	-	Camera motion; see details below
`callback_url`	string	-	Optional webhook
`external_task_id`	string	-	Custom task ID

Assets: jpg/jpeg/png, ≤10MB, width/height ≥300px, aspect ratio 1:2.5 ~ 2.5:1. For image-to-video, image_tail, dynamic_masks/static_mask, and camera_control are mutually exclusive feature sets.

Model versions and feature support

Model	text-to-video	image-to-video	sound	aspect_ratio	Description
`kling-v1`	✅	✅	❌	❌	Base version
`kling-v1-5`	❌	✅	❌	❌	Iterative (image-to-video only)
`kling-v1-6`	✅	✅	❌	❌	Iterative version
`kling-v2-1`	❌	✅	❌	❌	High-quality (image-to-video only)
`kling-v2-1-master`	✅	✅	❌	❌	High-quality version
`kling-v2-5-turbo`	✅	✅	❌	❌	Faster turbo version
`kling-v2-6`	✅	✅	✅	✅	Latest, supports sound & aspect_ratio

Example: basic text-to-video (V1)

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cat playing piano",
    "type": "text-to-video",
    "quality_mode": "std",
    "duration": 5
  }'

Example: V2.6 text-to-video with sound

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cat playing piano with pleasant background music",
    "type": "text-to-video",
    "model_name": "kling-v2-6",
    "quality_mode": "std",
    "duration": 5,
    "aspect_ratio": "16:9",
    "sound": "on"
  }'

Example: V2.6 image-to-video

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The astronaut stands up and walks away",
    "type": "image-to-video",
    "image_urls": ["https://example.com/astronaut.jpg"],
    "model_name": "kling-v2-6",
    "quality_mode": "pro",
    "duration": 10,
    "aspect_ratio": "9:16",
    "sound": "off"
  }'

Example: basic image-to-video (V1.x)

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "An astronaut stands up and walks away",
    "type": "image-to-video",
    "image_urls": ["https://example.com/astronaut.jpg"],
    "quality_mode": "std",
    "duration": 5,
    "cfg_scale": 0.5
  }'

Example: pro mode + camera control

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The main character walks through a forest",
    "type": "image-to-video",
    "image_urls": ["https://example.com/forest.jpg"],
    "quality_mode": "pro",
    "duration": 10,
    "model_name": "kling-v2-1-master",
    "camera_control": {
      "type": "forward_up"
    }
  }'

Example: dynamic masks

curl -X POST https://api.wizzx.ai/api/v1/task/submit/kling-ai \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "An astronaut stands up and walks away",
    "type": "image-to-video",
    "image_urls": ["https://example.com/astronaut.jpg"],
    "quality_mode": "std",
    "duration": 5,
    "dynamic_masks": [
      {
        "mask": "https://example.com/mask1.png",
        "trajectories": [
          {"x": 279, "y": 219},
          {"x": 417, "y": 65}
        ]
      }
    ]
  }'

Success response

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a",
    "model_key": "kling-ai",
    "credits_deducted": 230
  },
  "request_id": "d54c66a8-0f0f-439c-bd3a-36f3fd275881"
}

Query status

Endpoint: POST https://api.wizzx.ai/api/v1/task/status
Body:

{
  "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a"
}

Status response

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a",
    "status": "SUCCEEDED",
    "result_urls": [
      "https://cdn.example.com/video.mp4"
    ],
    "error": "",
    "credits_deducted": 230
  },
  "request_id": "499347b1-ff99-4ba2-a977-ad655431919d"
}

Client-visible states: PENDING, QUEUED, PROCESSING, REVIEW_REQUIRED, SUCCEEDED, and FAILED.

Camera control

Camera types

type	Description
`simple`	Simple camera motion, requires `config` parameter
`down_back`	Camera tilts down and moves back
`forward_up`	Camera moves forward and tilts up
`right_turn_forward`	Rotate right then move forward
`left_turn_forward`	Rotate left then move forward

Config parameters (simple type only)

Parameter	Range	Description
`horizontal`	[-10, 10]	Horizontal movement
`vertical`	[-10, 10]	Vertical movement
`pan`	[-10, 10]	Horizontal pan
`tilt`	[-10, 10]	Vertical tilt
`roll`	[-10, 10]	Roll rotation
`zoom`	[-10, 10]	Zoom in/out

simple mode: only one of the six config parameters can be non-zero.

Pricing

Pricing is per second of video generated.

Kling V2.6 (by sound)

Mode	Credits/second	USD/second	vs Official
sound=off	65	$0.065	Save 7%
sound=on	130	$0.13	Save 7%

Official:

0.07/s (no sound),

0.14/s (with sound).

Kling V1.x / V2.x (by quality_mode)

Kling 1.6 / 2.1

Mode	Credits/second	USD/second	vs Official
std	46	$0.046	Save 8%
pro	92	$0.092	Save 8%

Official: std

0.05/s, pro

0.10/s.

Kling 2.1 Master

Mode	Credits/second	USD/second	vs Official
pro	240	$0.24	Save 10%

Official: $0.28/s.

Kling 2.5 Turbo

Mode	Credits/second	USD/second	vs Official
std	36	$0.036	Save 10%
pro	65	$0.065	Save 7%

Official: std

0.04/s, pro

0.07/s.

Example cost calculation

5s video, std mode (Kling 1.6): 46 credits/s x 5s = 230 credits
10s video, pro mode (Kling 2.1): 92 credits/s x 10s = 920 credits
5s video, V2.6 with sound: 130 credits/s x 5s = 650 credits

FAQ

Which models support text-to-video? Models that support text-to-video: kling-v1, kling-v1-6, kling-v2-1-master, kling-v2-5-turbo, kling-v2-6. Note that kling-v1-5 and kling-v2-1 only support image-to-video.
How to generate video with sound? Use kling-v2-6 model and set sound: "on". Note that sound doubles the credit cost.
When is aspect_ratio available? aspect_ratio is only supported by kling-v2-6 model; other models will return an error.
Why was mode renamed to quality_mode? To avoid conflict with new type. type is the generation category; quality_mode is quality level (std/pro).
When is cfg_scale available? cfg_scale is only supported by V1.x models; V2.x models will return an error.
How to use camera control? Set camera_control with a supported type. Camera control works for both text-to-video and image-to-video. simple type uses config with exactly one non-zero field.
Dynamic vs static masks? static_mask sets a fixed region; dynamic_masks add trajectory points for motion control. Only supported for image-to-video.
How long are videos retained? Result URL lifetime can depend on storage configuration and the upstream provider; archive outputs you need to keep.

Getting started

Agent integrations

Video Generation

Image Generation

Kling AI Video Generation API

Overview

Auth

Submit job

Required

Conditionally required

Optional

Model versions and feature support

Example: basic text-to-video (V1)

Example: V2.6 text-to-video with sound

Example: V2.6 image-to-video

Example: basic image-to-video (V1.x)

Example: pro mode + camera control

Example: dynamic masks

Success response

Query status

Status response

Camera control

Camera types

Config parameters (simple type only)

Pricing

Kling V2.6 (by sound)

Kling V1.x / V2.x (by quality_mode)

Kling 1.6 / 2.1

Kling 2.1 Master

Kling 2.5 Turbo

Example cost calculation

FAQ

​Overview

​Auth

​Submit job

​Required

​Conditionally required

​Optional

​Model versions and feature support

​Example: basic text-to-video (V1)

​Example: V2.6 text-to-video with sound

​Example: V2.6 image-to-video

​Example: basic image-to-video (V1.x)

​Example: pro mode + camera control

​Example: dynamic masks

​Success response

​Query status

​Status response

​Camera control

​Camera types

​Config parameters (simple type only)

​Pricing

​Kling V2.6 (by sound)

​Kling V1.x / V2.x (by quality_mode)

​Kling 1.6 / 2.1

​Kling 2.1 Master

​Kling 2.5 Turbo

​Example cost calculation

​FAQ

Overview

Auth

Submit job

Required

Conditionally required

Optional

Model versions and feature support

Example: basic text-to-video (V1)

Example: V2.6 text-to-video with sound

Example: V2.6 image-to-video

Example: basic image-to-video (V1.x)

Example: pro mode + camera control

Example: dynamic masks

Success response

Query status

Status response

Camera control

Camera types

Config parameters (simple type only)

Pricing

Kling V2.6 (by sound)

Kling V1.x / V2.x (by quality_mode)

Kling 1.6 / 2.1

Kling 2.1 Master

Kling 2.5 Turbo

Example cost calculation

FAQ