# Segment Anything Model 3 API

> Larawan segmentation mula sa teksto, point o box prompt na nagbabalik ng mga mask na larawan, na may opsyonal na score at box

Nagsasagawa ng segmentation sa isang larawan gamit ang SAM 3 at teksto na `prompt`, `point_prompts` o `box_prompts`. Kapag naka-enable ang `return_multiple_masks`, nagbabalik ito ng hanggang `max_masks` na mask (1 hanggang 32). Maaaring isama ang opsyonal na confidence score at bounding box. Ang output format ay jpeg, png o webp.

- Model id: `sam-3/image`
- Made by: Meta
- Category: Image Editing
- Output: image
- Estimated price per run: $0.005 / run (cheapest run $0.005 (5 API credits))
- Run: `POST https://api.doitong.com/v1/run/sam-3/image`
- Quote: `POST https://api.doitong.com/v1/quote/sam-3/image`
- Docs page: https://doitong.com/fil/developers/models/sam-3/image

## Pricing

Price: **$0.005 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.005 = 5 API credits (1 request × 5 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/sam-3/image` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `image_url` | `image` | string (image URL) | yes |  |  | URL ng larawang ise-segment. |
| `prompt` |  | string | no | `wheel` |  | Text instruction na gumagabay sa segmentation. |
| `text_prompt` |  | string \| null | no |  |  | [DEPRECATED] Legacy input na pinanatili para sa backward compatibility; gamitin ang 'prompt' sa halip nito. |
| `point_prompts` |  | array of object {x, y, label, object_id, frame_index} | no | `[]` |  | Collection ng mga point-based prompt. |
| `point_prompts[].x` |  | integer \| null | no |  |  | Posisyon ng prompt sa X axis. |
| `point_prompts[].y` |  | integer \| null | no |  |  | Posisyon ng prompt sa Y axis. |
| `point_prompts[].label` |  | enum (integer) \| null | no |  | `0`, `1` | Label ng foreground/background: foreground ang tinutukoy ng 1; background ang 0. |
| `point_prompts[].object_id` |  | integer \| null | no |  |  | Opsyonal na identifier na nagpapangkat sa mga prompt na nagre-refine ng iisang object. Kung may text ding ibinigay bilang prompt, tinutukoy ng identifier na ito kung aling nadetect na object ang nire-refine ng mga point na iyon. |
| `point_prompts[].frame_index` |  | integer \| null | no |  |  | Index na tumutukoy sa frame para sa interaction. |
| `box_prompts` |  | array of object {x_min, y_min, x_max, y_max, object_id, frame_index} | no | `[]` |  | Mga box prompt na ang object_id ang tumutukoy sa pagpapangkat: iniuugnay ng magkaparehong ID ang mga box sa isang object, habang ang mga walang laman na ID ay kumakatawan sa magkakahiwalay na object. Maaaring magbigay ng maraming box, bawat isa gamit ang coordinates (x_min, y_min, x_max, y_max). |
| `box_prompts[].x_min` |  | integer \| null | no |  |  | Pinakamababang x-coordinate para sa box. |
| `box_prompts[].y_min` |  | integer \| null | no |  |  | Pinakamababang y-coordinate para sa box. |
| `box_prompts[].x_max` |  | integer \| null | no |  |  | Pinakamataas na X coordinate para sa box. |
| `box_prompts[].y_max` |  | integer \| null | no |  |  | Pinakamataas na Y coordinate para sa box. |
| `box_prompts[].object_id` |  | integer \| null | no |  |  | Opsyonal na identifier na nagpapangkat sa mga box na nagre-refine ng iisang object. |
| `box_prompts[].frame_index` |  | integer \| null | no |  |  | Index na tumutukoy sa frame para sa interaction. |
| `apply_mask` |  | boolean | no | `true` |  | Kinokontrol kung ilalapat ang mask sa larawan. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png`, `webp` | File format ng resultang larawan. |
| `return_multiple_masks` |  | boolean | no | `false` |  | Opsyon para sa pagbabalik ng maraming mask: kapag naka-enable, ginagamit nito ang `max_masks` upang tukuyin kung ilang nabuong mask ang ia-upload at isasama sa response. |
| `max_masks` |  | integer | no | `3` | 1 – 32 | Pinakamataas na bilang ng ibabalik na mask kapag naka-enable ang `return_multiple_masks`. |
| `include_scores` |  | boolean | no | `false` |  | Kinokontrol kung isasama ang confidence score para sa mga mask. |
| `include_boxes` |  | boolean | no | `false` |  | Kinokontrol kung isasama ang bounding box para sa bawat mask, kung available. |

File parameters (`image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/sam-3/image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/sam-3/image?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sam-3/image", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "sam-3/image",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "sam-3/image",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 5,
    "usd": "0.005",
    "charged": 5,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "image": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768
    },
    "masks": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ],
    "metadata": [
      {
        "index": 1,
        "score": 1.0,
        "box": [
          1.0
        ]
      }
    ],
    "scores": [
      1.0
    ],
    "boxes": [
      [
        1.0
      ]
    ]
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `image` | object {url, content_type, file_name, file_size, width, height} \| null | Preview na nagpapakita ng pangunahing segmentation mask. |
| `masks` | array of object {url, content_type, file_name, file_size, width, height} | Mga larawang naglalaman ng segmentation mask. |
| `metadata` | array of object {index, score, box} \| null | Metadata para sa bawat mask, kasama ang score at box nito. |
| `scores` | array of number \| null | Confidence score para sa bawat mask, ibinibigay kapag hiniling. |
| `boxes` | array of array of number \| null | Mga normalized box para sa bawat mask, ipinapahayag bilang [cx, cy, w, h], kung hiniling. |

## Related models

- [Sam 3 · Image RLE](https://doitong.com/developers/models/sam-3/image-rle.md) (`sam-3/image-rle`): $0.005 / run
- [Sam 3 · Video](https://doitong.com/developers/models/sam-3/video.md) (`sam-3/video`): $0.005 / 16 frames of input video
- [Sam 3 · Video RLE](https://doitong.com/developers/models/sam-3/video-rle.md) (`sam-3/video-rle`): $0.005 / 16 frames of input video
- [Sam 3 · 3D Body](https://doitong.com/developers/models/sam-3/3d-body.md) (`sam-3/3d-body`): $0.02 / run
- [Sam 3 · 3D Objects](https://doitong.com/developers/models/sam-3/3d-objects.md) (`sam-3/3d-objects`): $0.02 / run
- [Sam 3 · 3D Align](https://doitong.com/developers/models/sam-3/3d-align.md) (`sam-3/3d-align`): $0.02 / run
- [Sam 3 · Image · Embed](https://doitong.com/developers/models/sam-3/image/embed.md) (`sam-3/image/embed`): $0.005 / run
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image

## Links

- HTML page: https://doitong.com/developers/models/sam-3/image
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=sam-3/image
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/sam-3/image