POST
https://octopusx.ai
/
v1
/
videos
Kling Video Generation
curl --request POST \
  --url https://octopusx.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "seconds": "<string>",
  "size": "<string>",
  "image": "<string>",
  "metadata": {},
  "metadata.output_config": {},
  "metadata.scene_type": "<string>",
  "metadata.motion_level": "<string>",
  "metadata.offpeak": true,
  "metadata.last_frame_url": "<string>",
  "metadata.video_url": "<string>",
  "metadata.file_infos": "<string>",
  "metadata.ext_info": "<string>"
}
'
{
  "id": "video_123",
  "task_id": "video_123",
  "object": "video",
  "model": "kling-3.0-omni-720p-ref-audio",
  "status": "queued",
  "progress": 0,
  "created_at": 1712697600
}

​
Kling Video Generation

Kling uses POST /v1/videos to submit tasks, with JSON submission as the primary method.
  • The route entry is POST /v1/videos.
  • JSON submission is currently used.
  • Supports multiple scenarios, including text-to-video, image-to-video, and first-and-last-frame video generation.
  • Extended parameters, including output configuration and scenario type, are passed through the metadata field.
  • After a successful submission, the task id and status are returned, and the result is later polled via Task Status Query.

​
Supported Models

  • Kling-3.0-Omni: Kling 3.0 all-in-one version
  • Kling-2.6: Kling 2.6 version
  • Kling-2.5: Kling 2.5 version

​
Method and Path

POST /v1/videos

​
Request Example

curl -X POST https://octopusx.ai/v1/videos \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Kling-3.0-Omni",
    "prompt": "Cyberpunk city night scene, the camera slowly pushes in",
    "seconds": "5",
    "metadata": {
      "output_config": {
        "resolution": "720P",
        "aspect_ratio": "16:9"
      }
    }
  }'

​
Scenario Examples

​
Text-to-Video

{
  "model": "Kling-3.0-Omni",
  "prompt": "Cyberpunk city night scene, the camera slowly pushes in",
  "seconds": "5",
  "metadata": {
    "output_config": {
      "resolution": "720P",
      "aspect_ratio": "16:9"
    }
  }
}

​
Image-to-Video

{
  "model": "Kling-3.0-Omni",
  "prompt": "Make the character walk forward and smile",
  "image": "https://example.com/character.png",
  "seconds": "5",
  "metadata": {
    "output_config": {
      "resolution": "1080P",
      "aspect_ratio": "9:16"
    }
  }
}

​
First-and-Last-Frame Video Generation

{
  "model": "Kling-3.0-Omni",
  "prompt": "In a silent system space, the character is illuminated by a blue panel",
  "seconds": "15",
  "size": "720x1280",
  "metadata": {
    "output_config": {
      "duration": 15,
      "resolution": "720P",
      "aspect_ratio": "9:16",
      "audio_generation": "Enabled"
    },
    "last_frame_url": "https://example.com/last-frame.png"
  }
}

​
Motion Control

{
  "model": "Kling-3.0-Omni",
  "prompt": "The character waves hello",
  "image": "https://example.com/character.png",
  "seconds": "5",
  "metadata": {
    "scene_type": "motion_control",
    "motion_level": "pro",
    "output_config": {
      "resolution": "1080P",
      "aspect_ratio": "16:9"
    }
  }
}

​
Response Example

Note: The model field in the response may include a billing-spec suffix (such as 720p-ref-audio), which differs from the model name passed in the request. 
{
  "id": "video_123",
  "task_id": "video_123",
  "object": "video",
  "model": "kling-3.0-omni-720p-ref-audio",
  "status": "queued",
  "progress": 0,
  "created_at": 1712697600
}

​
Authentication

Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
required
Model name. For example, Kling-3.0-Omni, Kling-2.6, Kling-2.5.
​
prompt
string
required
Prompt. The text description for video generation, supporting both Chinese and English.
​
seconds
string
Video duration. For example, 5, 10, 15.
​
size
string
Video size. Fast size input, for example 720x1280.
​
image
string
Reference image. Reference image URL.
​
metadata
object
Metadata. A container for extended parameters. It is recommended to place all upstream native parameters in metadata.
​
metadata.output_config
object
Output configuration. It is recommended to place all native parameters in output_config.
  • duration: duration (seconds)
  • resolution: resolution (720P, 1080P)
  • aspect_ratio: aspect ratio (16:9, 9:16, 1:1)
  • audio_generation: audio generation (Enabled, Disabled)
​
metadata.scene_type
string
Scene type. Examples: motion_control (motion control), avatar_i2v (digital human generation), lip_sync (lip sync), template_effect (template effects).
​
metadata.motion_level
string
Motion level. Examples: std (standard), pro (professional, used for motion control billing tiers).
​
metadata.offpeak
boolean
Whether off-peak billing is used. true: generate video off-peak; false: generate video immediately.
​
metadata.last_frame_url
string
Last frame in first-and-last-frame generation. Specify the tail-frame image URL when generating a first-and-last-frame video.
​
metadata.video_url
string
Reference video URL.
​
metadata.file_infos
string
File information. Native FileInfos passthrough (advanced usage).
​
metadata.ext_info
string
Extended information. Native ExtInfo string passthrough (advanced usage).

​
Response

​
id
string
Task ID.
​
task_id
string
Task ID (same as id).
​
object
string
Fixed to video.
​
model
string
Model name.
​
status
string
Task status. Common values include queued, processing, completed, failed, cancelled.
​
progress
integer
Progress percentage (0-100).
​
created_at
integer
Creation time (Unix timestamp).