Create video

videos.create() -> Video

POST/videos

Create a new video generation job from a prompt and optional reference assets.

ParametersExpand Collapse

prompt: str

Text prompt that describes the video to generate.

maxLength32000

minLength1

input_reference: Optional[FileTypes]

Optional image reference that guides generation.

model: Optional[VideoModelParam]

The video generation model to use (allowed values: sora-2, sora-2-pro). Defaults to sora-2.

Accepts one of the following:

str

Literal["sora-2", "sora-2-pro", "sora-2-2025-10-06", 2 more]

Accepts one of the following:

"sora-2"

"sora-2-pro"

"sora-2-2025-10-06"

"sora-2-pro-2025-10-06"

"sora-2-2025-12-08"

seconds: Optional[VideoSeconds]

Clip duration in seconds (allowed values: 4, 8, 12). Defaults to 4 seconds.

Accepts one of the following:

"4"

"8"

"12"

size: Optional[VideoSize]

Output resolution formatted as width x height (allowed values: 720x1280, 1280x720, 1024x1792, 1792x1024). Defaults to 720x1280.

Accepts one of the following:

"720x1280"

"1280x720"

"1024x1792"

"1792x1024"

ReturnsExpand Collapse

class Video: …

Structured information describing a generated video job.

id: str

Unique identifier for the video job.

completed_at: Optional[int]

Unix timestamp (seconds) for when the job completed, if finished.

created_at: int

Unix timestamp (seconds) for when the job was created.

error: Optional[VideoCreateError]

Error payload that explains why generation failed, if applicable.

code: str

A machine-readable error code that was returned.

message: str

A human-readable description of the error that was returned.

expires_at: Optional[int]

Unix timestamp (seconds) for when the downloadable assets expire, if set.

model: VideoModel

The video generation model that produced the job.

Accepts one of the following:

str

Literal["sora-2", "sora-2-pro", "sora-2-2025-10-06", 2 more]

Accepts one of the following:

"sora-2"

"sora-2-pro"

"sora-2-2025-10-06"

"sora-2-pro-2025-10-06"

"sora-2-2025-12-08"

object: Literal["video"]

The object type, which is always video.

progress: int

Approximate completion percentage for the generation task.

prompt: Optional[str]

The prompt that was used to generate the video.

remixed_from_video_id: Optional[str]

Identifier of the source video if this video is a remix.

seconds: VideoSeconds

Duration of the generated clip in seconds.

Accepts one of the following:

"4"

"8"

"12"

size: VideoSize

The resolution of the generated video.

Accepts one of the following:

"720x1280"

"1280x720"

"1024x1792"

"1792x1024"

status: Literal["queued", "in_progress", "completed", "failed"]

Current lifecycle status of the video job.

Accepts one of the following:

"queued"

"in_progress"

"completed"

"failed"

Create video

from openai import OpenAI

client = OpenAI()
video = client.videos.create(
    prompt="A calico cat playing a piano on stage",
)
print(video.id)

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "status": "queued",
  "progress": 0,
  "created_at": 1712697600,
  "size": "1024x1792",
  "seconds": "8",
  "quality": "standard"
}

Returns Examples

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "status": "queued",
  "progress": 0,
  "created_at": 1712697600,
  "size": "1024x1792",
  "seconds": "8",
  "quality": "standard"
}