Skip to main content
POST
/
v1
/
videos
/
generations
gemini-omni-flash-video-edit API
curl --request POST \
  --url https://api.evolink.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-omni-flash-video-edit",
  "prompt": "Make the lighting in the scene warmer and keep everything else unchanged",
  "video_urls": [
    "https://example.com/source.mp4"
  ]
}
'
{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "gemini-omni-flash-video-edit",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": false,
    "estimated_time": 60
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_token",
    "credits_reserved": 102.34,
    "user_group": "default"
  }
}

Authorizations

​
Authorization
string
header
required

##All endpoints require authentication using a Bearer Token##

Get your API Key:

Visit the API Key management page to obtain your API Key

Add it to the request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
required

Model name, fixed to gemini-omni-flash-video-edit

Available options:
gemini-omni-flash-video-edit
Example:

"gemini-omni-flash-video-edit"

​
prompt
string
required

Text prompt for video editing, describing the desired editing effect, supports both English and Chinese

Usage tips:

  • Describe the elements to change and the parts to keep unchanged (e.g. "make the lighting warmer and keep everything else unchanged")
  • Write negative requirements directly into the prompt (e.g. No dialogue, no text on screen); this model does not provide a separate negative prompt parameter
Example:

"Make the lighting in the scene warmer and keep everything else unchanged"

​
video_urls
string<uri>[]

Array of videos to edit; only 1 is supported

Input requirements:

  • Currently only HTTP/HTTPS video URLs are supported
  • Format: mp4
  • Duration: no more than 10 seconds
Required array length: 1 element
Example:
["https://example.com/source.mp4"]
​
callback_url
string<uri>

HTTPS callback URL to notify when the task completes

Callback timing:

  • Triggered when the task completes (completed), fails (failed), or is cancelled (cancelled)
  • Sent after billing is confirmed

Security restrictions:

  • HTTPS protocol only
  • Callbacks to internal IP addresses are forbidden (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
  • Up to 3 retries on failure (retried 1s / 2s / 4s after each failure respectively)
  • The callback body format matches the response of the task query endpoint
  • A 2xx status code from the callback URL is treated as success; other status codes trigger a retry
Example:

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

Response

Video task created successfully

​
created
integer

Task creation timestamp

Example:

1757169743

​
id
string

Task ID

Example:

"task-unified-1757169743-7cvnl5zw"

​
model
string

The model name actually used

Example:

"gemini-omni-flash-video-edit"

​
object
enum<string>

The specific type of the task

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

Detailed video task information

​
type
enum<string>

The output type of the task

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

"video"

​
usage
object

Usage and billing information