POST
https://octopusx.ai
/
v1
/
video
/
create
Create Video
curl --request POST \
  --url https://octopusx.ai/v1/video/create \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "images": [
    "<string>"
  ],
  "model": "<string>",
  "orientation": "<string>",
  "prompt": "<string>",
  "size": "<string>",
  "duration": 123,
  "watermark": true,
  "private": true,
  "style": "<string>",
  "storyboard": true
}
'
{
  "id": "sora-2:task_01k9008rhbefnt3rb1g9szxdwr",
  "status": "pending",
  "status_update_time": 1762010621323
}

​
Create Video

The Sora unified video entry point uses POST /v1/video/create, and the request body is JSON. Unlike OpenAI-format Sora video generation, this API uses fields such as images, orientation, size, and duration, and supports Sora-specific options such as watermark, private, style, and storyboard.
  • The route entry point is POST /v1/video/create.
  • Reference images are passed as a list of URLs in the images array; text-to-video can pass an empty array.
  • A common model example is sora-2; use the model actually available in the current channel as the standard.
  • After a successful submission, the task id and status are returned; use Query Task to poll for results later.

​
Method and Path

POST /v1/video/create

​
Request Example

curl -X POST https://octopusx.ai/v1/video/create \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "images": [],
    "model": "sora-2",
    "orientation": "portrait",
    "prompt": "make animate",
    "size": "large",
    "duration": 15,
    "watermark": false,
    "private": true,
    "storyboard": false
  }'

​
Response Example

{
  "id": "sora-2:task_01k9008rhbefnt3rb1g9szxdwr",
  "status": "pending",
  "status_update_time": 1762010621323
}
The full response may also include fields such as object, model, progress, created_at, size, and detail, and its structure is consistent with the OpenAI VIDEO response format.

​
Authentication

Authorization: Bearer YOUR_API_KEY

​
Body

​
images
array<string>
required
List of reference image links. Text-to-video can pass [].
​
model
string
required
Model name, for example sora-2.
​
orientation
string
required
Frame orientation. portrait means vertical, and landscape means horizontal.
​
prompt
string
required
Prompt.
​
size
string
required
Output specification. small generally corresponds to 720p.
​
duration
integer
required
Video duration in seconds. The default is often 10; optional values are 10, 15, and 25 (sora-2-pro supports longer durations).
​
watermark
boolean
Whether to keep the watermark. The default is true: the system will first try to generate without a watermark, and may fall back to a watermark if that fails. Passing false forces no watermark; if a watermark-removal error occurs, it may automatically retry.
​
private
boolean
Whether to hide the video. When true, the video will not be published and remix will not be available; the default is false.
​
style
string
Video style, available only for supported models such as sora_video2. Optional values include thanksgiving, comic, news, selfie, nostalgic, and anime.
​
storyboard
boolean
Whether to use a storyboard to achieve finer-grained control over video generation details.

​
Response

​
id
string
Task ID, passed as the id parameter in subsequent queries.
​
status
string
Task status. Common values include pending, queued, processing, completed, failed, and cancelled.
​
status_update_time
integer
The most recent status update time (Unix timestamp).
​
object
string
Object type; some responses use video.
​
model
string
The actual model used.
​
progress
string | integer
Task progress.
​
detail
object
Submission details, usually including the echoed input field.