Name: ayushunleashed MiniMax-Remover Video Object Removal API
Brand: magicapi
SKU: api-magicapi-object-removal-video-fast-ayushunleashed-minimax-remover
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Video Object Removal API (ayushunleashed MiniMax-Remover)

## Overview
MiniMax-Remover removes objects from a video. Its developer describes it as fast.

Send the source `video` and a `mask` video in which white areas mark the objects to remove. The model fills those areas with the surrounding background and returns the URL of one MP4 video. Output size, frame rate and frame count follow the source video unless you set them.

## Features
- **Mask-based removal**: white areas in the `mask` video mark what to remove, so you control exactly which object goes.
- **Mask expansion**: `mask_dilation_iterations` (1 to 20, default `8`) grows the mask before removal to catch object edges and shadows.
- **Speed or quality**: `num_inference_steps` (1 to 50, default `6`). Its developer suggests 6 for fast, 8 for balanced and 12 for high quality.
- **Keep or change the format**: `width`, `height`, `fps` and `num_frames` default to `-1`, which keeps the source values. Width and height are scaled down to at most 1920 px if needed.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Clean up footage**: remove a stray object, prop or passer-by from a shot.
2. **Product and property videos**: take clutter out of a room or product clip.
3. **Content editing**: remove an element from a clip before reusing it in another edit.
4. **Automated pipelines**: pair it with a segmentation step that produces mask videos, then remove the masked objects in bulk.

## Visual Examples
### Example Input
- `video`: a 3 second still-camera clip of a room. [Watch the input video](https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-w15-input-api-market.mp4)
- `mask`: the matching mask video, white over the vase on the table. [Watch the mask video](https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-mask-w15-input-api-market.mp4)

The other fields were sent at their defaults (`num_inference_steps` `6`, `mask_dilation_iterations` `8`, and `-1` for `width`, `height`, `fps` and `num_frames`).

### Example Output
The same room with the vase removed from the table. [Watch the example output](https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-output-kakwtswe-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `video` | string (URL) | Yes | none |  | Video URL. The video with the objects to remove. |
| `mask` | string (URL) | Yes | none |  | Mask video URL. White areas mark the objects to remove. |
| `num_frames` | integer | No | `-1` | `-1` or more | Number of frames to process (-1 = same as the original video) |
| `height` | integer | No | `-1` | `-1` or more | Output video height (-1 = same as the original video, scaled down to at most 1920 px if needed) |
| `width` | integer | No | `-1` | `-1` or more | Output video width (-1 = same as the original video, scaled down to at most 1920 px if needed) |
| `fps` | integer | No | `-1` | `-1` or more | Output video frame rate (-1 = same as the original video) |
| `num_inference_steps` | integer | No | `6` | `1` to `50` | Number of denoising steps. Higher is slower and better quality: 6 = fast, 8 = balanced, 12 = high quality |
| `mask_dilation_iterations` | integer | No | `8` | `1` to `20` | How many times the mask is expanded before removal. Higher values remove more thoroughly around the object edges |
| `seed` | integer | No | none |  | Random seed for reproducible results. Leave it out for a random seed |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.029 per API unit.
- **1 API unit = 1 request with up to 25 seconds of processing.** Most requests cost one unit ($0.029). A request that needs more processing time is billed one more unit for each started 25-second block, so 26 to 50 seconds is 2 units ($0.058).
- Processing time grows with video length, resolution and `num_inference_steps`.
- **Example cost**: the example request processed for 13.8 seconds, so it used 1 API unit and cost $0.029.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/object-removal-video-fast-ayushunleashed-minimax-remover`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/object-removal-video-fast-ayushunleashed-minimax-remover/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "f486e4c1469ce3d5042ad74ab06b16138ae228ddb49b54ce050a14cb2f1beb58",
    "input": {
      "video": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-w15-input-api-market.mp4",
      "mask": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-mask-w15-input-api-market.mp4",
      "fps": -1,
      "width": -1,
      "height": -1,
      "num_frames": -1,
      "num_inference_steps": 6,
      "mask_dilation_iterations": 8
    }
  }'
```

Response (201 Created):
```json
{
  "id": "kakwtswetsrmw0d1mvhtzh9trw",
  "version": "f486e4c1469ce3d5042ad74ab06b16138ae228ddb49b54ce050a14cb2f1beb58",
  "status": "starting",
  "created_at": "2026-11-04T14:08:13.526Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/object-removal-video-fast-ayushunleashed-minimax-remover/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "kakwtswetsrmw0d1mvhtzh9trw",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-output-kakwtswe-api-market.mp4",
  "error": null,
  "created_at": "2026-11-04T14:08:13.526Z",
  "started_at": "2026-11-04T14:08:34.061448026Z",
  "completed_at": "2026-11-04T14:08:47.900170106Z"
}
```

`output` is a single URL string pointing to the MP4 video with the masked objects removed.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `video` or `mask`, or a `num_inference_steps` outside 1 to 50.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/object-removal-video-fast-ayushunleashed-minimax-remover";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "f486e4c1469ce3d5042ad74ab06b16138ae228ddb49b54ce050a14cb2f1beb58", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "video": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-w15-input-api-market.mp4",
  "mask": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-mask-w15-input-api-market.mp4",
  "fps": -1,
  "width": -1,
  "height": -1,
  "num_frames": -1,
  "num_inference_steps": 6,
  "mask_dilation_iterations": 8
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/object-removal-video-fast-ayushunleashed-minimax-remover"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "f486e4c1469ce3d5042ad74ab06b16138ae228ddb49b54ce050a14cb2f1beb58", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "video": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-w15-input-api-market.mp4",
    "mask": "https://blog.api.market/wp-content/uploads/2026/11/minimax-remover-room-mask-w15-input-api-market.mp4",
    "fps": -1,
    "width": -1,
    "height": -1,
    "num_frames": -1,
    "num_inference_steps": 6,
    "mask_dilation_iterations": 8
}))
```

## FAQ
- **How do I make the mask video?**
  - Make it from the same clip: paint the objects to remove white in every frame and leave everything else black, so the white areas line up with the object as it moves.
- **Part of the object is still visible. What can I change?**
  - Raise `mask_dilation_iterations` (up to 20) so the mask covers the object's edges, or make the mask itself larger.
- **How do I get better quality?**
  - Raise `num_inference_steps`. Its developer suggests 8 for balanced and 12 for high quality. More steps take longer, which can add API units on long videos.
- **What size is the output?**
  - The same width, height, frame rate and frame count as the source video, unless you set `width`, `height`, `fps` or `num_frames`. Width and height are scaled down to at most 1920 px if needed.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that both URLs point to videos, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Remove objects from videos with MiniMax-Remover: send a video and a mask video, get back an MP4 with the masked objects removed. $0.029 per request, pay as you go.