Name: ton731 Floorplan Recognition Floorplan Segmentation API
Brand: magicapi
SKU: api-magicapi-floorplan-image-segmentation-ton731-floorplan-recognition
Availability: InStock
Author: API Market

Shashank Agarwal

# 🏠 Floorplan Segmentation API (ton731 Floorplan Recognition)

## Overview
Floorplan Recognition by ton731 reads a floor plan image and segments it into walls, doors, the entry door, windows and kitchen zones with a deep learning model. It then returns the contour of every element and the center lines of doors and windows as JSON.

Send one floor plan `image` (JPEG or PNG). Each request returns one JSON string with a list of polygons per element type.

## Features
- **Element classes**: `wall`, `door`, `entry_door`, `window` and `kitchen`, each returned as a list of polygons.
- **Center lines**: `door_center_line`, `entry_door_center_line` and `window_center_line` give a two-point line through each door, entry door and window.
- **Structured output**: every polygon is a list of `[x, y]` points, ready to draw, measure or convert into vector or CAD geometry.
- **One input**: the only field is `image`; there are no settings to tune.

## Use Cases
1. **Floor plan digitization**: turn a raster floor plan into wall, door and window geometry.
2. **Real estate tools**: detect openings and walls in listing floor plans for viewers, editors or room-layout tools.
3. **Interior and renovation apps**: use the wall contours and door positions as the starting layout for furniture or renovation planning.
4. **Data pipelines**: count doors and windows or extract wall outlines from batches of plans, one request per plan.

## Visual Examples
### Example Input
![Floor plan drawing used as the example input](https://blog.api.market/wp-content/uploads/2026/11/floorplan-recognition-plan-w15-input-api-market.png)

```json
{
  "image": "https://blog.api.market/wp-content/uploads/2026/11/floorplan-recognition-plan-w15-input-api-market.png"
}
```

### Example Output
`output` is a JSON string. Parsed, it looks like this (the `wall` and `door` lists are shortened to their first polygon; the real response has 3 wall polygons and 2 doors):

```json
{
  "wall": [
    [[280, 335], [280, 343], [458, 343], [458, 336], [457, 335]]
  ],
  "door": [
    [[662, 394], [661, 395], [642, 395], [642, 403], [681, 403], [682, 402], [682, 397], [681, 396], [681, 395], [678, 395], [677, 394]]
  ],
  "entry_door": [
    [[461, 343], [461, 345], [460, 346], [454, 346], [454, 366], [453, 367], [453, 377], [464, 377], [464, 363], [463, 362], [463, 347], [462, 346], [462, 344]]
  ],
  "window": [
    [[453, 301], [453, 307], [454, 308], [454, 332], [459, 332], [461, 334], [462, 334], [462, 333], [463, 332], [463, 315], [464, 314], [464, 302], [454, 302]]
  ],
  "kitchen": [],
  "door_center_line": [
    [[642, 398], [718, 398]],
    [[201, 339], [280, 339]]
  ],
  "entry_door_center_line": [
    [[458, 377], [458, 343]]
  ],
  "window_center_line": [
    [[458, 301], [458, 334]]
  ]
}
```

The example plan has no kitchen zone, so `kitchen` is an empty list.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Floorplan image to segment (JPEG or PNG) |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0023 per API unit.
- **1 API unit = 1 request with up to 19 seconds of processing.** A request that processes for longer bills one more unit for each started 19-second block (for example, 30 seconds of processing is 2 units, $0.0046).
- **Example cost**: the example request above processed for 10.4 seconds: 1 unit, $0.0023.
- **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/floorplan-image-segmentation-ton731-floorplan-recognition`

### 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/floorplan-image-segmentation-ton731-floorplan-recognition/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "6d9285b49483724cfa20294f80f711ca32fc1c488bb98ca01f0499651d966773",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/11/floorplan-recognition-plan-w15-input-api-market.png"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "2n52887zf9rmr0d1mvpbqc6ckm",
  "version": "6d9285b49483724cfa20294f80f711ca32fc1c488bb98ca01f0499651d966773",
  "status": "starting",
  "created_at": "2026-11-04T14:18:32.186Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/floorplan-image-segmentation-ton731-floorplan-recognition/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK, `wall` and `door` shortened to their first polygon):
```json
{
  "id": "2n52887zf9rmr0d1mvpbqc6ckm",
  "status": "succeeded",
  "output": "{\"wall\": [[[280, 335], [280, 343], [458, 343], [458, 336], [457, 335]]], \"door\": [[[662, 394], [661, 395], [642, 395], [642, 403], [681, 403], [682, 402], [682, 397], [681, 396], [681, 395], [678, 395], [677, 394]]], \"entry_door\": [[[461, 343], [461, 345], [460, 346], [454, 346], [454, 366], [453, 367], [453, 377], [464, 377], [464, 363], [463, 362], [463, 347], [462, 346], [462, 344]]], \"window\": [[[453, 301], [453, 307], [454, 308], [454, 332], [459, 332], [461, 334], [462, 334], [462, 333], [463, 332], [463, 315], [464, 314], [464, 302], [454, 302]]], \"kitchen\": [], \"door_center_line\": [[[642, 398], [718, 398]], [[201, 339], [280, 339]]], \"entry_door_center_line\": [[[458, 377], [458, 343]]], \"window_center_line\": [[[458, 301], [458, 334]]]}",
  "error": null,
  "created_at": "2026-11-04T14:18:32.186Z",
  "started_at": "2026-11-04T14:18:52.190Z",
  "completed_at": "2026-11-04T14:19:02.548Z"
}
```

`output` is a string that holds a JSON object. Parse it (`JSON.parse` in JavaScript, `json.loads` in Python) to get one key per element class. Each class is a list of polygons, each polygon a list of `[x, y]` points; each center line is a list of two points.

### 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 `image`.
- **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, for example an image URL that cannot be downloaded. 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/floorplan-image-segmentation-ton731-floorplan-recognition";

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: "6d9285b49483724cfa20294f80f711ca32fc1c488bb98ca01f0499651d966773", 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 JSON.parse(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({
  "image": "https://blog.api.market/wp-content/uploads/2026/11/floorplan-recognition-plan-w15-input-api-market.png"
}).then((plan) => {
  console.log(`Walls: ${plan.wall.length}, doors: ${plan.door.length}, windows: ${plan.window.length}`);
});
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/floorplan-image-segmentation-ton731-floorplan-recognition"


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": "6d9285b49483724cfa20294f80f711ca32fc1c488bb98ca01f0499651d966773", "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 json.loads(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")


plan = create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/11/floorplan-recognition-plan-w15-input-api-market.png"
})
print(f"Walls: {len(plan['wall'])}, doors: {len(plan['door'])}, windows: {len(plan['window'])}")
```

## FAQ
- **What image formats are accepted?**
  - JPEG or PNG, sent as a URL in `image`.
- **What do the numbers in the output mean?**
  - Each polygon is a list of `[x, y]` points tracing the outline of one wall, door, window or kitchen zone. Each center line is a pair of points through the middle of a door, entry door or window.
- **Why is `output` a string and not an object?**
  - The model returns its result as a JSON-encoded string. Parse it with `JSON.parse` or `json.loads` before reading the keys.
- **Why is `kitchen` empty?**
  - The model found no kitchen zone in that plan. Any class can be an empty list.
- **What does one request cost?**
  - $0.0023 for each started 19 seconds of processing. The example processed for 10.4 seconds and cost one unit, $0.0023.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the image URL is reachable and is a JPEG or PNG, and try again.

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


Segment a floor plan image into walls, doors, the entry door, windows and kitchen zones, with contours and door and window center lines as JSON. $0.0023 per request, pay as you go.