# Sam 3 1 · Video API

> Segmentation vidéo SAM 3.1 qui suit jusqu'à 128 objets et produit une sortie mp4 ou webm

Segmente et suit les objets d'une vidéo avec SAM 3.1 à partir d'un `prompt` textuel séparé par des virgules, de points ou de cadres. `max_num_objects` définit le nombre d'objets à suivre, de 1 à 128 (16 par défaut). `detection_threshold` va de 0.1 à 1. La sortie est en X264 (.mp4) ou VP9 (.webm).

- Model id: `sam-3-1/video`
- Made by: Meta
- Category: Video to Video
- Output: video
- Price per 16 frames of your input video: $0.01 / 16 frames of input video (cheapest run $0.01 (10 API credits))
- Run: `POST https://api.doitong.com/v1/run/sam-3-1/video`
- Quote: `POST https://api.doitong.com/v1/quote/sam-3-1/video`
- Docs page: https://doitong.com/fr-FR/developers/models/sam-3-1/video

## Pricing

Price: **$0.01 / 16 frames of input video**. Price per 16 frames of your input video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.19 = 190 API credits (19 × 16 frames input video × $0.01).

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-3-1/video` 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 |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  |  | URL de la vidéo pour la segmentation. |
| `prompt` |  | string | no | `` |  | Invite de segmentation prenant en charge plusieurs objets suivis au moyen de descriptions séparées par des virgules, telles que 'person, cloth'. |
| `point_prompts` |  | array of object {x, y, label, object_id} | no | `[]` |  | Collection d’invites basées sur des points. |
| `point_prompts[].x` |  | integer \| null | no |  |  | Position de l’invite sur l’axe X. |
| `point_prompts[].y` |  | integer \| null | no |  |  | Position de l’invite sur l’axe Y. |
| `point_prompts[].label` |  | enum (integer) \| null | no |  | `0`, `1` | Libellé premier plan/arrière-plan : 1 indique le premier plan ; 0 indique l’arrière-plan. |
| `point_prompts[].object_id` |  | integer \| null | no |  |  | Identifiant facultatif regroupant les invites qui affinent un même objet. Si du texte est également fourni comme invite, cet identifiant détermine l’objet détecté que ces points affinent. |
| `box_prompts` |  | array of object {x_min, y_min, x_max, y_max, object_id} | no | `[]` |  | Invites de boîte répertoriées sous forme de tuples de coordonnées (x_min, y_min, x_max, y_max). |
| `box_prompts[].x_min` |  | integer \| null | no |  |  | Coordonnée x minimale de la boîte. |
| `box_prompts[].y_min` |  | integer \| null | no |  |  | Coordonnée y minimale de la boîte. |
| `box_prompts[].x_max` |  | integer \| null | no |  |  | Coordonnée X maximale de la boîte. |
| `box_prompts[].y_max` |  | integer \| null | no |  |  | Coordonnée Y maximale de la boîte. |
| `box_prompts[].object_id` |  | integer \| null | no |  |  | Identifiant facultatif regroupant les boîtes qui affinent un même objet. |
| `apply_mask` |  | boolean | no | `true` |  | Indique s’il faut appliquer le masquage à la vidéo. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)` | Type de sortie de la vidéo résultante. |
| `detection_threshold` |  | number | no | `0.5` | 0.1 – 1 | Seuil de confiance de la détection : une réduction de la valeur augmente le nombre de détections au détriment de la précision ; la plage est comprise entre 0.0 et 1.0. |
| `max_num_objects` |  | integer | no | `16` | 1 – 128 | Limite supérieure du nombre d’objets suivis dans la vidéo. |

File parameters (`video`) 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
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## 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-3-1/video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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-3-1/video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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 = {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sam-3-1/video", 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-3-1/video",
      "input": {
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "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-3-1/video",
  "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": 190,
    "usd": "0.19",
    "charged": 190,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "boundingbox_frames_zip": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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 |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Vidéo produite par la segmentation. |
| `boundingbox_frames_zip` | object {url, content_type, file_name, file_size} \| null | Archive ZIP des superpositions de boîtes englobantes pour chaque image. |

## Related models

- [Sam 3 1 · Image](https://doitong.com/developers/models/sam-3-1/image.md) (`sam-3-1/image`): $0.01 / run
- [Sam 3 1 · Image RLE](https://doitong.com/developers/models/sam-3-1/image-rle.md) (`sam-3-1/image-rle`): $0.01 / run
- [Sam 3 1 · Video RLE](https://doitong.com/developers/models/sam-3-1/video-rle.md) (`sam-3-1/video-rle`): $0.01 / 16 frames of input video
- [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
- [Segment Anything Model 2 · Video](https://doitong.com/developers/models/sam2/video.md) (`sam2/video`): $0.001111 / second of processing time
- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time
- [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md) (`fast-animatediff/turbo/video-to-video`): $0.00125 / second of processing time

## Links

- HTML page: https://doitong.com/developers/models/sam-3-1/video
- 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-3-1/video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/sam-3-1/video