Skip to content
Primary navigation

Suggested
API Dashboard
API Reference
Videos

Create video

client.videos.create(VideoCreateParams { prompt, input_reference, model, 2 more } body, RequestOptionsoptions?): Video { id, completed_at, created_at, 10 more }
POST/videos

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

ParametersExpand Collapse
body: VideoCreateParams { prompt, input_reference, model, 2 more }
prompt: string

Text prompt that describes the video to generate.

maxLength32000
minLength1
input_reference?: Uploadable | ImageInputReferenceParam { file_id, image_url }

Optional reference asset upload or reference object that guides generation.

One of the following:
Uploadable
ImageInputReferenceParam { file_id, image_url }
file_id?: string
image_url?: string

A fully qualified URL or base64-encoded data URL.

maxLength20971520
model?: VideoModel

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

One of the following:
(string & {})
"sora-2" | "sora-2-pro" | "sora-2-2025-10-06" | 2 more
"sora-2"
"sora-2-pro"
"sora-2-2025-10-06"
"sora-2-pro-2025-10-06"
"sora-2-2025-12-08"
seconds?: VideoSeconds

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

One of the following:
"4"
"8"
"12"
size?: VideoSize

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

One of the following:
"720x1280"
"1280x720"
"1024x1792"
"1792x1024"
ReturnsExpand Collapse
Video { id, completed_at, created_at, 10 more }

Structured information describing a generated video job.

id: string

Unique identifier for the video job.

completed_at: number | null

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

created_at: number

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

error: VideoCreateError { code, message } | null

Error payload that explains why generation failed, if applicable.

code: string

A machine-readable error code that was returned.

message: string

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

expires_at: number | null

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

model: VideoModel

The video generation model that produced the job.

One of the following:
(string & {})
"sora-2" | "sora-2-pro" | "sora-2-2025-10-06" | 2 more
"sora-2"
"sora-2-pro"
"sora-2-2025-10-06"
"sora-2-pro-2025-10-06"
"sora-2-2025-12-08"
object: "video"

The object type, which is always video.

progress: number

Approximate completion percentage for the generation task.

prompt: string | null

The prompt that was used to generate the video.

remixed_from_video_id: string | null

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

seconds: (string & {}) | VideoSeconds

Duration of the generated clip in seconds. For extensions, this is the stitched total duration.

One of the following:
(string & {})
VideoSeconds = "4" | "8" | "12"
One of the following:
"4"
"8"
"12"
size: VideoSize

The resolution of the generated video.

One of the following:
"720x1280"
"1280x720"
"1024x1792"
"1792x1024"
status: "queued" | "in_progress" | "completed" | "failed"

Current lifecycle status of the video job.

One of the following:
"queued"
"in_progress"
"completed"
"failed"

Create video

import OpenAI from 'openai';

const openai = new OpenAI();

const video = await openai.videos.create({ prompt: 'A calico cat playing a piano on stage' });

console.log(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"
}