OpenAI API 参考（字段级）

For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.

Create video

post /videos

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

Body Parameters

• prompt: string

  Text prompt that describes the video to generate.

• input_reference: optional ImageInputReferenceParam

  Optional reference object that guides generation. Provide exactly one of image_url or file_id.

  • file_id: optional string

  • image_url: optional string

    A fully qualified URL or base64-encoded data URL.

• model: optional VideoModel

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

  • string

  • "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 2 more

    • "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.

  • "4"

  • "8"

  • "12"

• size: optional VideoSize

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

  • "720x1280"

  • "1280x720"

  • "1024x1792"

  • "1792x1024"

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 or 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 or 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.

    • misalignment: optional object \{ detailed_explanation, error_type, steer \}

      • detailed_explanation: optional string

        The public explanation for this block.

      • error_type: optional string or "potentially_unintended_data_transfer" or "potentially_unintended_data_access" or "potentially_unintended_destructive_activity" or "other"

        An optional classification; clients must accept additional values.

        • string

        • SafetyAlertErrorType = "potentially_unintended_data_transfer" or "potentially_unintended_data_access" or "potentially_unintended_destructive_activity" or "other"

          An optional classification; clients must accept additional values.

          • "potentially_unintended_data_transfer"

          • "potentially_unintended_data_access"

          • "potentially_unintended_destructive_activity"

          • "other"

      • steer: optional object \{ message \}

        An optional public continuation instruction.

        • message: string

          The public continuation instruction.

  • expires_at: number or null

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

  • model: VideoModel

    The video generation model that produced the job.

    • string

    • "sora-2" or "sora-2-pro" or "sora-2-2025-10-06" or 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.

    • "video"

  • progress: number

    Approximate completion percentage for the generation task.

  • prompt: string or null

    The prompt that was used to generate the video.

  • remixed_from_video_id: string or null

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

  • seconds: string

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

  • size: VideoSize

    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

curl https://api.openai.com/v1/videos \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
          "prompt": "x"
        }'

Response

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

Example

curl https://api.openai.com/v1/videos \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "model=sora-2" \
  -F "prompt=A calico cat playing a piano on stage"

Response

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