# AI Text Watermark and Metadata Removal API

Originally published at https://gifi.ai/ai-watermark-remover-api.

Gifi exposes the same inspect, clean, and rewrite pipeline used by the web app. Text cleaning returns named Unicode and punctuation changes. File cleaning reports each metadata action. Rewriting changes prose but never claims to certify a private detector.

## Endpoints

| Method | Path            | Job                                                |
| ------ | --------------- | -------------------------------------------------- |
| POST   | /api/v1/inspect | Inspect text without spending a credit             |
| POST   | /api/v1/clean   | Remove named Unicode or file metadata              |
| POST   | /api/v1/rewrite | Generate new wording for a statistical text signal |
| GET    | /api/v1/usage   | Read plan, credit, and rate-limit status           |

## Example

```sh
curl -X POST https://gifi.ai/api/v1/inspect \
  -H "Authorization: Bearer $GIFI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Text to inspect"}'
```

## Supported input

Text, PNG, JPEG, WebP, SVG, HTML, Markdown, PDF, DOCX, and ODT. Unsupported or incomplete cleaning paths are refused rather than returned as clean.

## Limits

- No API response certifies that text will pass or fail a vendor detector.
- C2PA soft binding can re-link a cleaned file to a remote manifest.
- Visible or pixel-embedded watermarks, audio, and video are outside the API scope.

Read the [complete API reference](https://gifi.ai/docs.md), [connect over MCP](https://gifi.ai/agents.md), or [see pricing](https://gifi.ai/pricing.md).