OpenAI Video Format

This page overview

OpenAI Video Format

Use the OpenAI video generation API to generate videos. It supports models such as Sora, and you can also use the OpenAI video format to call Kling, Jimeng, and vidu.

Generate Video

API Endpoint

POST /v1/videos

Request Headers

Parameter	Type	Required	Description
Authorization	string	Yes	User authentication token (Bearer: sk-xxxx)
Content-Type	string	Yes	multipart/form-data

Request Parameters

Parameter	Type	Required	Description
prompt	string	Yes	Text prompt describing the video to generate
model	string	No	Video generation model, defaults to sora-2
seconds	string	No	Video duration in seconds, defaults to 4 seconds
size	string	No	Output resolution, in widthxheight format, defaults to 720x1280
input_reference	file	No	Optional image reference used to guide generation

Request Example

curl https://你的4All API服务器地址/v1/videos \
  -H "Authorization: Bearer sk-xxxx" \
  -F "model=sora-2" \
  -F "prompt=A calico cat playing a piano on stage"

Response Format

200 - Successful Response

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "status": "queued",
  "progress": 0,
  "created_at": 1712697600,
  "size": "1024x1808",
  "seconds": "8",
  "quality": "standard"
}

Response Field Descriptions

Field	Type	Description
id	string	Video task ID
object	string	Object type, fixed as “video”
model	string	Name of the model used
status	string	Task status (queued: queued, processing: in progress, completed: done, failed: failed)
progress	integer	Processing progress (0-100)
created_at	integer	Creation timestamp
size	string	Video resolution
seconds	string	Video duration in seconds
quality	string	Video quality

Query Video

Query the status and result of a video generation task by task ID

API Endpoint

GET /v1/videos/{video_id}

Path Parameters

Parameter	Type	Required	Description
video_id	string	Yes	Video task ID

Request Example

curl 'https://你的4All API服务器地址/v1/videos/video_123' \
  -H "Authorization: Bearer sk-xxxx"

Response Format

200 - Successful Response

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "status": "completed",
  "progress": 100,
  "created_at": 1712697600,
  "size": "1024x1808",
  "seconds": "8",
  "quality": "standard",
  "url": "https://example.com/video.mp4"
}

Response Field Descriptions

Field	Type	Description
id	string	Video task ID
object	string	Object type, fixed as “video”
model	string	Name of the model used
status	string	Task status (queued: queued, processing: in progress, completed: done, failed: failed)
progress	integer	Processing progress (0-100)
created_at	integer	Creation timestamp
size	string	Video resolution
seconds	string	Video duration in seconds
quality	string	Video quality
url	string	Video download link (when completed)

Get Video Task Status

Get detailed information about a video generation task by task ID

API Endpoint

GET /v1/videos/{video_id}

Path Parameters

Parameter	Type	Required	Description
video_id	string	Yes	Identifier of the video task to retrieve

Request Example

curl 'https://你的4All API服务器地址/v1/videos/video_123' \
  -H "Authorization: Bearer sk-xxxx"

Response Format

200 - Successful Response

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "status": "completed",
  "progress": 100,
  "created_at": 1712697600,
  "completed_at": 1712698000,
  "expires_at": 1712784400,
  "size": "1024x1808",
  "seconds": "8",
  "quality": "standard",
  "remixed_from_video_id": null,
  "error": null
}

Response Field Descriptions

Field	Type	Description
id	string	Unique identifier for the video task
object	string	Object type, fixed as “video”
model	string	Name of the model used to generate the video
status	string	Current lifecycle status of the video task
progress	integer	Approximate completion percentage of the generation task
created_at	integer	Unix timestamp in seconds when the task was created
completed_at	integer	Unix timestamp in seconds when the task completed, if completed
expires_at	integer	Unix timestamp in seconds when the downloadable asset expires, if set
size	string	Resolution of the generated video
seconds	string	Duration of the generated video clip in seconds
quality	string	Video quality
remixed_from_video_id	string	If this video is a remix, the identifier of the source video
error	object	Object containing error information if generation fails

Get Video Content

Download the completed video content

API Endpoint

GET /v1/videos/{video_id}/content

Path Parameters

Parameter	Type	Required	Description
video_id	string	Yes	Identifier of the video to download

Query Parameters

Parameter	Type	Required	Description
variant	string	No	Type of downloadable asset to return, defaults to MP4 video

Request Example

curl 'https://你的4All API服务器地址/v1/videos/video_123/content' \
  -H "Authorization: Bearer sk-xxxx" \
  -o "video.mp4"

Response Format

200 - Successful Response

Returns the video file stream directly, with Content-Type set to video/mp4

Response Header Descriptions

Field	Type	Description
Content-Type	string	Video file type, usually video/mp4
Content-Length	string	Video file size in bytes
Content-Disposition	string	File download information

Error Responses

400 - Invalid Request Parameters

{
  "error": {
    "message": "Invalid request parameters",
    "type": "invalid_request_error",
    "code": "invalid_parameter"
  }
}

401 - Unauthorized

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

403 - Forbidden

{
  "error": {
    "message": "Insufficient permissions",
    "type": "permission_error",
    "code": "insufficient_permissions"
  }
}

429 - Rate Limit Exceeded

{
  "error": {
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

500 - Internal Server Error

{
  "error": {
    "message": "Internal server error",
    "type": "server_error",
    "code": "internal_error"
  }
}