Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://api.evolink.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kling-v3-image-to-video",
  "prompt": "The person in the scene slowly turns their head and smiles",
  "image_start": "https://example.com/portrait.jpg",
  "duration": 5,
  "quality": "720p"
}
'
{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "kling-v3-image-to-video",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 300,
    "video_duration": 5
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_second",
    "credits_reserved": 270000,
    "user_group": "default"
  }
}

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
default:kling-v3-image-to-video
required

Video generation model name

Available options:
kling-v3-image-to-video
Example:

"kling-v3-image-to-video"

​
image_start
string<uri>
required

First frame image URL for image-to-video generation

Note:

  • At least one of image_start (first frame image URL) and image_end (last frame image URL) is required
  • Image size: up to 10MB
  • Supported formats: .jpg, .jpeg, .png
  • Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1
  • When a first frame is provided, aspect_ratio can be omitted (automatically adapts to image ratio)
  • Image URL must be directly accessible by the server
Example:

"https://example.com/portrait.jpg"

​
image_end
string<uri>

Last frame image URL

Note:

  • At least one of image_start (first frame image URL) and image_end (last frame image URL) is required
  • Last frame requires a first frame
  • Image requirements are the same as image_start
Example:

"https://example.com/night.jpg"

​
prompt
string

Text prompt describing what video to generate

Note:

  • Maximum 2500 characters
  • Can be empty when multi_shot=true and shot_type=customize
  • Use <<<element_1>>> reference syntax to reference elements in the prompt
Maximum string length: 2500
Example:

"The person in the scene slowly turns their head and smiles"

​
negative_prompt
string

Negative prompt describing content you do not want in the video

Example:

"text, watermark"

​
duration
integer
default:5

Video duration in seconds, defaults to 5 seconds

Note:

  • Range: integer from 3 to 15
  • Billing is based on the duration value, longer duration costs more
Required range: 3 <= x <= 15
Example:

5

​
aspect_ratio
enum<string>

Video aspect ratio

Options:

  • 16:9: Landscape video
  • 9:16: Portrait video
  • 1:1: Square video
  • When a first frame image is provided, this can be omitted (automatically adapts to image ratio)
Available options:
16:9,
9:16,
1:1
Example:

"16:9"

​
quality
enum<string>
default:720p

Resolution tier

Options:

  • 720p: Standard quality (std)
  • 1080p: High quality (pro)
Available options:
720p,
1080p
Example:

"720p"

​
sound
enum<string>
default:off

Sound effect control

Options:

  • on: Generate sound effects
  • off: No sound effects
Available options:
on,
off
Example:

"off"

​
model_params
object

Advanced parameters for multi-shot, element control, and watermark

​
callback_url
string<uri>

HTTPS callback URL for task completion

Callback Timing:

  • Triggered when task is completed, failed, or cancelled
  • Sent after billing confirmation

Security Restrictions:

  • HTTPS protocol only
  • Internal IP addresses are prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
  • URL length must not exceed 2048 characters

Callback Mechanism:

  • Timeout: 10 seconds
  • Maximum 3 retries after failure (at 1/2/4 seconds after failure)
  • Callback response format is consistent with task query API
  • 2xx status code is considered successful, other codes trigger retry
Example:

"https://your-domain.com/webhooks/video-task-completed"

Response

Video generation task created successfully

​
created
integer

Task creation timestamp

Example:

1757169743

​
id
string

Task ID

Example:

"task-unified-1757169743-7cvnl5zw"

​
model
string

Actual model name used

Example:

"kling-v3-image-to-video"

​
object
enum<string>

Task type

Available options:
video.generation.task
​
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

​
status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

​
task_info
object

Video task details

​
type
enum<string>

Task output type

Available options:
text,
image,
audio,
video
Example:

"video"

​
usage
object

Usage and billing information