Name: SAM 3 API: Text-Prompted Image Segmentation
Brand: magicapi
SKU: api-magicapi-prompt-based-segmentation-api-mattsays-sam3-image
Availability: InStock
Author: API Market

Shashank Agarwal

# ✂️ Text-Prompted Image Segmentation API (Meta SAM 3)

## Overview
SAM 3 is a foundation model for prompt-based segmentation. Its developer describes it as a unified model for images and videos; this API segments one image per request.

Send an `image` and a short text `prompt` naming what to segment (default `person`). Objects detected above the confidence `threshold` are masked. With `return_zip` set to `true` (the default) the output is a ZIP file of individual masks as PNGs. Set it to `false` to get one image instead: a colored overlay on the original image, or a black-and-white mask when `mask_only` is `true`.

## Features
- **Text prompts**: name the objects to segment in `prompt`, for example `clothes`, `person` or `car`.
- **Confidence threshold**: `threshold` (0 to 1, default 0.5) sets how confident a detection must be to be masked.
- **Individual masks**: `return_zip` (default `true`) returns a ZIP of one PNG mask per object; `save_overlay` adds the overlay image to the ZIP.
- **Overlay or mask image**: with `return_zip` `false`, get a colored overlay on the original image, or a black-and-white mask with `mask_only`.
- **Overlay styling**: `mask_color` (`green`, `red`, `blue`, `yellow`, `cyan` or `magenta`) and `mask_opacity` (0 to 1).

## Use Cases
1. **Product and fashion images**: cut out clothes, shoes or products named in the prompt.
2. **Photo editing pipelines**: masks for background replacement, recoloring or inpainting steps.
3. **Dataset labeling**: per-object masks for a named class across many images.
4. **Counting and locating objects**: one mask file per detected object in the ZIP.

## Visual Examples
### Example Input
![Example input image for SAM 3](https://blog.api.market/wp-content/uploads/2026/10/sam3-image-input-api-market.jpg)

Prompt: "clothes", with `threshold` `0.5` and `return_zip` `true`.

```json
{
  "image": "https://blog.api.market/wp-content/uploads/2026/10/sam3-image-input-api-market.jpg",
  "prompt": "clothes",
  "mask_only": false,
  "threshold": 0.5,
  "mask_color": "green",
  "return_zip": true,
  "mask_opacity": 0.5,
  "save_overlay": false
}
```

### Example Output
[Download the example output (ZIP file of PNG masks)](https://blog.api.market/wp-content/uploads/2026/10/sam3-image-output-0myggn07-api-market.zip)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes | none |  | Image URL (jpeg, png, gif or webp) |
| `prompt` | string | No | `person` |  | Text prompt for segmentation |
| `threshold` | number | No | `0.5` | `0` to `1` | Confidence threshold for object detection |
| `save_overlay` | boolean | No | `false` |  | If true, includes the overlay image in the ZIP file |
| `mask_only` | boolean | No | `false` |  | If true, returns a black-and-white mask image instead of an overlay on the original image |
| `return_zip` | boolean | No | `true` |  | If true, returns a ZIP file containing individual masks as PNGs |
| `mask_opacity` | number | No | `0.5` | `0` to `1` | Opacity of the mask overlay (0.0 to 1.0) |
| `mask_color` | string | No | `green` |  | Color of the mask overlay. Options: green, red, blue, yellow, cyan, magenta |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0022 per API unit.
- **1 API unit = 1 request with up to 2 seconds of processing time.** A request that takes longer is billed one unit per started 2-second block (for example, 3.5 seconds of processing is 2 units, $0.0044).
- **Example cost**: the example took 1.95 seconds of processing: 1 API unit = **$0.0022**.
- **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/prompt-based-segmentation-api-mattsays-sam3-image`

### 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/prompt-based-segmentation-api-mattsays-sam3-image/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "d73db077226443ba4fafd34e233b3626b552eac2a433f90c7c32a9ac89bd9e72",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/sam3-image-input-api-market.jpg",
      "prompt": "clothes",
      "mask_only": false,
      "threshold": 0.5,
      "mask_color": "green",
      "return_zip": true,
      "mask_opacity": 0.5,
      "save_overlay": false
    }
  }'
```

Response (201 Created):
```json
{
  "id": "0myggn07fdrmr0d1c6na4pvz6g",
  "version": "d73db077226443ba4fafd34e233b3626b552eac2a433f90c7c32a9ac89bd9e72",
  "status": "starting",
  "created_at": "2026-10-22T03:31:35.588Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/prompt-based-segmentation-api-mattsays-sam3-image/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "0myggn07fdrmr0d1c6na4pvz6g",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/sam3-image-output-0myggn07-api-market.zip",
  "error": null,
  "created_at": "2026-10-22T03:31:35.588Z",
  "started_at": "2026-10-22T03:31:35.600Z",
  "completed_at": "2026-10-22T03:31:37.549Z"
}
```

`output` is a single URL string. With `return_zip` `true` it points to a ZIP file of PNG masks; with `return_zip` `false` it points to one image.

### 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` or a `threshold` outside 0 to 1.
- **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
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.
## 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/prompt-based-segmentation-api-mattsays-sam3-image";

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: "d73db077226443ba4fafd34e233b3626b552eac2a433f90c7c32a9ac89bd9e72", 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({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/sam3-image-input-api-market.jpg",
    "prompt": "clothes",
    "mask_only": false,
    "threshold": 0.5,
    "mask_color": "green",
    "return_zip": true,
    "mask_opacity": 0.5,
    "save_overlay": false
  }).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/prompt-based-segmentation-api-mattsays-sam3-image"


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": "d73db077226443ba4fafd34e233b3626b552eac2a433f90c7c32a9ac89bd9e72", "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")


output = create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/sam3-image-input-api-market.jpg",
    "prompt": "clothes",
    "mask_only": False,
    "threshold": 0.5,
    "mask_color": "green",
    "return_zip": True,
    "mask_opacity": 0.5,
    "save_overlay": False
})
print(output)
```

## FAQ
- **What should I put in the prompt?**
  - A short name for the objects to segment, such as `clothes`, `person` or `dog`. The default is `person`.
- **How do I get one image instead of a ZIP file?**
  - Set `return_zip` to `false`. You get a colored overlay on the original image, or a black-and-white mask if `mask_only` is `true`.
- **Some objects are missing from the masks. What can I do?**
  - Lower `threshold` (default 0.5) to keep less confident detections.
- **Can I segment a video?**
  - No. This API takes one image per request.
- **How much does a request cost?**
  - $0.0022 for each started 2 seconds of processing. The example took 1.95 seconds and cost $0.0022.
- **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`.

## Contact Us
If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


SAM 3 API: segment every object in an image that matches a short text prompt and get PNG masks in a ZIP file or a colored overlay. Pay as you go.