> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Video Watermark Remover > Remove watermarks and logos from an existing video, including marks that move around the frame such as the Sora logo. Watermark regions are detected on every frame and filled in with matching background. The resolution and the original audio track are kept, and the result is an MP4. **Pricing** — per second of the **source video** (USD at $0.02/token): | tokens/s | USD/s | |---|---| | 1 | $0.02 | ⚠️ There is no `duration` parameter. The source video is measured server-side and the whole clip is processed; the measured length, rounded up to whole seconds, is what you are charged for. For example, a 10.2-second clip is billed as 11 seconds: - 11 tokens - = $0.22 **Limits** — requests outside these are rejected before any tokens are deducted: | | limit | |---|---| | `video_url` | `https://` only, up to 100MB, av1 is not supported | | Length | 1-60s | | Resolution | up to 1080p (shorter side at most 1080 pixels) | **Output:** same resolution as the source, original audio preserved. The frame rate is capped at 30fps: a faster source keeps an even subset of its frames (60fps becomes 30fps, 50fps becomes 25fps), so the duration and the audio stay in sync. Slower sources keep their own frame rate. **Processing time:** slower than real time — expect roughly 3 minutes for a 10-second 30fps clip. Use `custom_callback_url` rather than tight polling for longer clips. `detection_prompt` and `max_bbox_percent` work the same way as in the image Watermark Remover: name the mark (for example `Sora logo`) when the default `watermark` misses it, and keep `max_bbox_percent` low so a false positive cannot erase a large part of the frame. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the result. ## OpenAPI ````yaml api-reference/video-generations/openapi-video-watermark-remover.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Video Watermark Remover description: Video Watermark Remover version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: Video Watermark Remover description: >- Remove watermarks and logos from an existing video, including marks that move around the frame such as the Sora logo. Watermark regions are detected on every frame and filled in with matching background. The resolution and the original audio track are kept, and the result is an MP4. **Pricing** — per second of the **source video** (USD at $0.02/token): | tokens/s | USD/s | |---|---| | 1 | $0.02 | ⚠️ There is no `duration` parameter. The source video is measured server-side and the whole clip is processed; the measured length, rounded up to whole seconds, is what you are charged for. For example, a 10.2-second clip is billed as 11 seconds: - 11 tokens - = $0.22 **Limits** — requests outside these are rejected before any tokens are deducted: | | limit | |---|---| | `video_url` | `https://` only, up to 100MB, av1 is not supported | | Length | 1-60s | | Resolution | up to 1080p (shorter side at most 1080 pixels) | **Output:** same resolution as the source, original audio preserved. The frame rate is capped at 30fps: a faster source keeps an even subset of its frames (60fps becomes 30fps, 50fps becomes 25fps), so the duration and the audio stay in sync. Slower sources keep their own frame rate. **Processing time:** slower than real time — expect roughly 3 minutes for a 10-second 30fps clip. Use `custom_callback_url` rather than tight polling for longer clips. `detection_prompt` and `max_bbox_percent` work the same way as in the image Watermark Remover: name the mark (for example `Sora logo`) when the default `watermark` misses it, and keep `max_bbox_percent` low so a false positive cannot erase a large part of the frame. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the result. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - video-watermark-remover description: Model name. Must be `video-watermark-remover`. video_url: type: string format: uri description: >- Source video URL. Must be an `https://` link that is publicly reachable. Up to 100MB, 1-60s long, at most 1080p (shorter side 1080 pixels or less); av1 is not supported. The whole clip is processed and its measured duration is the billing basis. detection_prompt: type: string maxLength: 200 default: watermark description: >- What to detect and remove, in English. Defaults to `watermark`. Naming the mark (for example `Sora logo`) improves detection of small or low-contrast watermarks. max_bbox_percent: type: number exclusiveMinimum: 0 maximum: 100 default: 10 description: >- Largest region to remove, as a percentage of the frame area. Detected regions above this size are treated as false positives and left untouched. Defaults to `10`. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - video_url example: model: video-watermark-remover video_url: https://your-cdn.com/clip.mp4 detection_prompt: Sora logo responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 11 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 11 '2': summary: Video too long value: code: -1 msg: Max video duration is 60 seconds, got 75s. '3': summary: Resolution above 1080p value: code: -1 msg: >- Video resolution 3840x2160 is not supported. Max supported: 1080p. '4': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ````