Videos

Create video

$ openai videos create

post /videos

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

Parameters

• --prompt: string

  Text prompt that describes the video to generate.

• --input-reference: optional string or ImageInputReferenceParam

  Optional reference asset upload or reference object that guides generation.

• --model: optional string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

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

• --seconds: optional "4" or "8" or "12"

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

• --size: optional "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

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

Returns

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Example

openai videos create \
  --api-key 'My API Key' \
  --prompt x

Response

{
  "id": "id",
  "completed_at": 0,
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message"
  },
  "expires_at": 0,
  "model": "sora-2",
  "object": "video",
  "progress": 0,
  "prompt": "prompt",
  "remixed_from_video_id": "remixed_from_video_id",
  "seconds": "4",
  "size": "720x1280",
  "status": "queued"
}

Create a new video generation job by editing a source video or existing generated video.

$ openai videos edit

post /videos/edits

Create a new video generation job by editing a source video or existing generated video.

Parameters

• --prompt: string

  Text prompt that describes how to edit the source video.

• --video: string or object { id }

  Reference to the completed video to edit.

Returns

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Example

openai videos edit \
  --api-key 'My API Key' \
  --prompt x \
  --video 'Example data'

Response

{
  "id": "id",
  "completed_at": 0,
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message"
  },
  "expires_at": 0,
  "model": "sora-2",
  "object": "video",
  "progress": 0,
  "prompt": "prompt",
  "remixed_from_video_id": "remixed_from_video_id",
  "seconds": "4",
  "size": "720x1280",
  "status": "queued"
}

Create an extension of a completed video.

$ openai videos extend

post /videos/extensions

Create an extension of a completed video.

Parameters

• --prompt: string

  Updated text prompt that directs the extension generation.

• --seconds: "4" or "8" or "12"

  Length of the newly generated extension segment in seconds (allowed values: 4, 8, 12, 16, 20).

• --video: string or object { id }

  Reference to the completed video to extend.

Returns

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Example

openai videos extend \
  --api-key 'My API Key' \
  --prompt x \
  --seconds 4 \
  --video 'Example data'

Response

{
  "id": "id",
  "completed_at": 0,
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message"
  },
  "expires_at": 0,
  "model": "sora-2",
  "object": "video",
  "progress": 0,
  "prompt": "prompt",
  "remixed_from_video_id": "remixed_from_video_id",
  "seconds": "4",
  "size": "720x1280",
  "status": "queued"
}

Create a character from an uploaded video.

$ openai videos create-character

post /videos/characters

Create a character from an uploaded video.

Parameters

• --name: string

  Display name for this API character.

• --video: string

  Video file used to create a character.

Returns

• VideoNewCharacterResponse: object { id, created_at, name }

  • id: string

    Identifier for the character creation cameo.

  • created_at: number

    Unix timestamp (in seconds) when the character was created.

  • name: string

    Display name for the character.

Example

openai videos create-character \
  --api-key 'My API Key' \
  --name x \
  --video 'Example data'

Response

{
  "id": "id",
  "created_at": 0,
  "name": "name"
}

Fetch a character.

$ openai videos get-character

get /videos/characters/{character_id}

Fetch a character.

Parameters

• --character-id: string

  The identifier of the character to retrieve.

Returns

• VideoGetCharacterResponse: object { id, created_at, name }

  • id: string

    Identifier for the character creation cameo.

  • created_at: number

    Unix timestamp (in seconds) when the character was created.

  • name: string

    Display name for the character.

Example

openai videos get-character \
  --api-key 'My API Key' \
  --character-id char_123

Response

{
  "id": "id",
  "created_at": 0,
  "name": "name"
}

List videos

$ openai videos list

get /videos

List recently generated videos for the current project.

Parameters

• --after: optional string

  Identifier for the last item from the previous pagination request

• --limit: optional number

  Number of items to retrieve

• --order: optional "asc" or "desc"

  Sort order of results by timestamp. Use asc for ascending order or desc for descending order.

Returns

• VideoListResource: object { data, first_id, has_more, 2 more }

  • data: array of Video

    A list of items

    • id: string

      Unique identifier for the video job.

    • completed_at: number

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

    • created_at: number

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

    • error: object { code, message }

      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

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

    • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

      The video generation model that produced the job.

      • "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

      The prompt that was used to generate the video.

    • remixed_from_video_id: string

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

    • seconds: string or VideoSeconds

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

      • "4"

      • "8"

      • "12"

    • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

      The resolution of the generated video.

      • "720x1280"

      • "1280x720"

      • "1024x1792"

      • "1792x1024"

    • status: "queued" or "in_progress" or "completed" or "failed"

      Current lifecycle status of the video job.

      • "queued"

      • "in_progress"

      • "completed"

      • "failed"

  • first_id: string

    The ID of the first item in the list.

  • has_more: boolean

    Whether there are more items available.

  • last_id: string

    The ID of the last item in the list.

  • object: "list"

    The type of object returned, must be list.

Example

openai videos list \
  --api-key 'My API Key'

Response

{
  "data": [
    {
      "id": "id",
      "completed_at": 0,
      "created_at": 0,
      "error": {
        "code": "code",
        "message": "message"
      },
      "expires_at": 0,
      "model": "sora-2",
      "object": "video",
      "progress": 0,
      "prompt": "prompt",
      "remixed_from_video_id": "remixed_from_video_id",
      "seconds": "4",
      "size": "720x1280",
      "status": "queued"
    }
  ],
  "first_id": "first_id",
  "has_more": true,
  "last_id": "last_id",
  "object": "list"
}

Retrieve video

$ openai videos retrieve

get /videos/{video_id}

Fetch the latest metadata for a generated video.

Parameters

• --video-id: string

  The identifier of the video to retrieve.

Returns

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Example

openai videos retrieve \
  --api-key 'My API Key' \
  --video-id video_123

Response

{
  "id": "id",
  "completed_at": 0,
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message"
  },
  "expires_at": 0,
  "model": "sora-2",
  "object": "video",
  "progress": 0,
  "prompt": "prompt",
  "remixed_from_video_id": "remixed_from_video_id",
  "seconds": "4",
  "size": "720x1280",
  "status": "queued"
}

Delete video

$ openai videos delete

delete /videos/{video_id}

Permanently delete a completed or failed video and its stored assets.

Parameters

• --video-id: string

  The identifier of the video to delete.

Returns

• VideoDeleteResponse: object { id, deleted, object }

  Confirmation payload returned after deleting a video.

  • id: string

    Identifier of the deleted video.

  • deleted: boolean

    Indicates that the video resource was deleted.

  • object: "video.deleted"

    The object type that signals the deletion response.

Example

openai videos delete \
  --api-key 'My API Key' \
  --video-id video_123

Response

{
  "id": "id",
  "deleted": true,
  "object": "video.deleted"
}

Remix video

$ openai videos remix

post /videos/{video_id}/remix

Create a remix of a completed video using a refreshed prompt.

Parameters

• --video-id: string

  The identifier of the completed video to remix.

• --prompt: string

  Updated text prompt that directs the remix generation.

Returns

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Example

openai videos remix \
  --api-key 'My API Key' \
  --video-id video_123 \
  --prompt x

Response

{
  "id": "id",
  "completed_at": 0,
  "created_at": 0,
  "error": {
    "code": "code",
    "message": "message"
  },
  "expires_at": 0,
  "model": "sora-2",
  "object": "video",
  "progress": 0,
  "prompt": "prompt",
  "remixed_from_video_id": "remixed_from_video_id",
  "seconds": "4",
  "size": "720x1280",
  "status": "queued"
}

Retrieve video content

$ openai videos download-content

get /videos/{video_id}/content

Download the generated video bytes or a derived preview asset.

Streams the rendered video content for the specified video job.

Parameters

• --video-id: string

  The identifier of the video whose media to download.

• --variant: optional "video" or "thumbnail" or "spritesheet"

  Which downloadable asset to return. Defaults to the MP4 video.

Returns

• unnamed_schema_6: file path

Example

openai videos download-content \
  --api-key 'My API Key' \
  --video-id video_123

Domain Types

Image Input Reference Param

• image_input_reference_param: object { file_id, image_url }

  • file_id: optional string

  • image_url: optional string

    A fully qualified URL or base64-encoded data URL.

Video

• video: object { 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

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

  • created_at: number

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

  • error: object { code, message }

    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

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

  • model: string or "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    The video generation model that produced the job.

    • "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

    The prompt that was used to generate the video.

  • remixed_from_video_id: string

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

  • seconds: string or VideoSeconds

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

    • "4"

    • "8"

    • "12"

  • size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

    The resolution of the generated video.

    • "720x1280"

    • "1280x720"

    • "1024x1792"

    • "1792x1024"

  • status: "queued" or "in_progress" or "completed" or "failed"

    Current lifecycle status of the video job.

    • "queued"

    • "in_progress"

    • "completed"

    • "failed"

Video Create Error

• video_create_error: object { code, message }

  An error that occurred while generating the response.

  • code: string

    A machine-readable error code that was returned.

  • message: string

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

Video Seconds

• video_seconds: "4" or "8" or "12"

  • "4"

  • "8"

  • "12"

Video Size

• video_size: "720x1280" or "1280x720" or "1024x1792" or "1792x1024"

  • "720x1280"

  • "1280x720"

  • "1024x1792"

  • "1792x1024"