Watermark Removal API

Overview

Use the asynchronous Watermark Removal API for large images or batch processing. Submit the source image first, receive a task_id, and use that task_id to retrieve the final cleaned image when processing is complete.

1. Before you begin

You need two things: an API key, and a funded API balance.

1. Click Get API Key in the card above to generate a key instantly.
2. Click Add Balance to fund your account — billed in USD, and separate from your kaze.ai web credits.
3. Buying at volume? Contact sales for discounted rates.

2. Pricing

Billed per processed image. Each submitted image costs $0.10.

3. Make a request

This single step covers the full Watermark Removal flow: submit the image, optionally include a smear mask, save the returned task_id, and poll the result endpoint.

Submit a removal task

Create an asynchronous watermark removal task. Send every request with Authorization: Bearer <API_KEY> and Content-Type: application/json.

curl --location --request POST 'https://api-srv.kaze.ai/api/ext/v1/submit_watermark_removal' \
  --header 'Authorization: Bearer <API_KEY>' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "image_url": "https://example.com/image.png"
  }'

Smear mask guidance

To ensure accurate watermark removal, provide a smear mask when you need to restrict editing to a specific area.

• The smear mask should use the same image size as the original.
• Use any color except pure black or pure white to draw the brush strokes over areas to be edited.
• All other areas should be pure black or pure white; those regions will be left unchanged.

Submit response

After a successful submission, the API returns a task_id. Use it with the result query endpoint to retrieve the final image.

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "xxxxxxx"
  }
}

Query the result

Use task_id to check the processing state and retrieve completed image URLs.

curl --location --request POST 'https://api-srv.kaze.ai/api/ext/v1/get_task_result' \
  --header 'Authorization: Bearer <API_KEY>' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "task_id": "aaabbbccc"
  }'

Result status

The response includes data.status, which may be:

• processing: In progress, check again later.
• success: Completed, result is in images.
• failed: Failed, check err_msg.
• timeout: Timed out, same as failed.

{
  "message": "success",
  "data": {
    "status": "processing/success/failed/timeout",
    "images": [
      {
        "url": "https://example.com/image.png"
      }
    ]
  }
}

Status codes