VideoEditRequest schema

Field	Type and description
`model` Required	string Video editing model identifier.
`video` Required	string Source video file for editing. `format: "binary"`
`prompt`	string Text prompt describing the edit (required for text_prompt mode).
`mask`	string Mask video for region-based editing (mask_video mode). `format: "binary"`
`mask_url`	string Public HTTPS URL to the mask video (alternative to uploading mask binary). `format: "uri"`
`key_points`	string JSON-encoded string representing an array of key-point objects for key_points mode. Each object must have numeric `x`, `y` coordinates and a `type` of either `"positive"` or `"negative"`. Example: `"[{\"x\":100,\"y\":200,\"type\":\"positive\"}]"` The route calls JSON.parse() on this field before forwarding.
`frame_index`	integer Frame index for key_points editing mode. `default: 0`
`auto_trim`	boolean Whether to auto-trim the output video. `default: false`
`preserve_audio`	boolean Whether to preserve the original audio track in the output. `default: true`
`background_color`	string Background fill color (background_color mode). CSS color name or hex value. `default: "White"`
`desired_increase`	integer Upscale factor for upscale_factor mode. Only 2 or 4 are accepted; other values are coerced to 2. Allowed values: `[2,4]` `default: 2`
`output_container_and_codec`	string Output container and codec string.