{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/octen-ai/json-schema/octen-ai-video-generation-request-schema.json",
  "title": "VideoGenerationRequest",
  "description": "JSON request body for the Video Generation API.",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/octen-ai-videos-api-openapi.yml#/components/schemas/VideoGenerationRequest",
  "type": "object",
  "required": [
    "model",
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "enum": [
        "minimax/minimax-h3",
        "bytedance/seedance-2.5",
        "google/veo-3.1",
        "google/veo-3.1-fast",
        "google/veo-3.1-lite"
      ],
      "description": "The model to use."
    },
    "prompt": {
      "type": "string",
      "description": "The text description of the video."
    },
    "duration": {
      "type": "integer",
      "description": "Video length in seconds. When omitted, the model default applies."
    },
    "resolution": {
      "type": "string",
      "enum": [
        "480p",
        "720p",
        "768p",
        "1080p",
        "2K"
      ],
      "description": "Output resolution. When omitted, the model default applies."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16",
        "21:9",
        "adaptive"
      ],
      "description": "Aspect ratio. `adaptive` lets the model follow the input. When omitted, the model default applies."
    },
    "frame_images": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/VideoFrameImage"
      },
      "description": "Images to use as the first and last frames of the video."
    },
    "input_references": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/VideoInputReference"
      },
      "description": "Reference images that guide generation without locking specific frames."
    },
    "generate_audio": {
      "type": "boolean",
      "default": true,
      "description": "Whether to generate audio along with the video."
    },
    "seed": {
      "type": "integer",
      "description": "Random seed, for more reproducible results."
    },
    "extra_params": {
      "type": "object",
      "additionalProperties": true,
      "description": "Vendor-specific parameters, passed through to the upstream model without validation. Keys that duplicate a unified parameter, or that control upstream storage, notification, sample count, or platform behavior, are rejected."
    }
  },
  "$defs": {
    "VideoFrameImage": {
      "type": "object",
      "required": [
        "image",
        "frame_type"
      ],
      "properties": {
        "image": {
          "type": "string",
          "description": "Image URL or base64 data."
        },
        "frame_type": {
          "type": "string",
          "enum": [
            "first_frame",
            "last_frame"
          ],
          "description": "Whether the image is the first or the last frame."
        }
      }
    },
    "VideoInputReference": {
      "type": "object",
      "required": [
        "image"
      ],
      "properties": {
        "image": {
          "type": "string",
          "description": "Image URL or base64 data."
        }
      }
    }
  }
}