# SAM 3

> SAM 3 is a unified foundation model for promptable segmentation in images and videos.

## Overview

- **Endpoint**: `https://api.runflow.io/v1/run/meta/sam-3/image`
- **Model ID**: `meta/sam-3/image`
- **Provider**: Meta
- **License**: commercial
- **Last Updated**: 2026-04-05

## Pricing

- **Base price**: $0.005/image
- **Note**: Usage-based, per image
## Input Schema

### `prompt` (string, optional)

Text prompt for segmentation
- **Default**: `wheel`

### `include_boxes` (boolean, optional)

Whether to include bounding boxes for each mask (when available).
- **Default**: `false`

### `include_scores` (boolean, optional)

Whether to include mask confidence scores.
- **Default**: `false`

### `return_multiple_masks` (boolean, optional)

If True, upload and return multiple generated masks as defined by `max_masks`.
- **Default**: `false`

### `image_url` (image, required)

URL of the image to be segmented

### `sync_mode` (boolean, optional)

If True, the media will be returned as a data URI.
- **Default**: `false`

### `point_prompts` (string, optional)

List of point prompts

### `output_format` (string, optional)

The format of the generated image.
- **Default**: `png`
- **Options**: `jpeg`, `png`, `webp`

### `max_masks` (integer, optional)

Maximum number of masks to return when `return_multiple_masks` is enabled.
- **Default**: `3`
- **Min**: 1
- **Max**: 32

### `box_prompts` (string, optional)

Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.

### `apply_mask` (boolean, optional)

Apply the mask on the image.
- **Default**: `true`

### `text_prompt` (string, optional)

[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.

## Usage Examples

### cURL

```bash
curl -X POST https://api.runflow.io/v1/run/meta/sam-3/image \
  -H "Authorization: Bearer $RUNFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A professional headshot, soft studio lighting",
    "image_url": "https://example.com/input.jpg",
    "output_format": "png"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://api.runflow.io/v1/run/meta/sam-3/image",
    headers={"Authorization": "Bearer RUNFLOW_API_KEY"},
    json={
        "prompt": "A professional headshot, soft studio lighting",
        "image_url": "https://example.com/input.jpg",
        "output_format": "png",
    },
)

data = response.json()
print(data["image"]["url"])
```

### JavaScript

```javascript
const response = await fetch(
  "https://api.runflow.io/v1/run/meta/sam-3/image",
  {
    method: "POST",
    headers: {
      "Authorization": "Bearer RUNFLOW_API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      prompt: "A professional headshot, soft studio lighting",
      image_url: "https://example.com/input.jpg",
      output_format: "png",
    }),
  }
);

const data = await response.json();
console.log(data.image.url);
```

## Additional Resources

- [Playground](https://www.runflow.io/models/meta/sam-3/image)
- [API Reference](https://www.runflow.io/models/meta/sam-3/image/api)
- [Documentation](https://www.runflow.io/docs)