# Wan 2.1 VACE Long Reframe API

> Recadre les vidéos longues scène par scène avec VACE 2.1, détection des scènes et réintégration

Conçu pour les clips longs : il détecte les scènes, recadre chacune d’elles et peut réintégrer le résultat dans la vidéo d’origine avec `paste_back`. `scene_threshold` (0 à 100) définit la sensibilité de détection ; les valeurs basses trouvent davantage de scènes. Le sous-échantillonnage automatique est activé par défaut. Propose également `zoom_factor`, `trim_borders`, le format d’image et une `resolution` de 240p à 720p.

- Model id: `wan-vace-apps/long-reframe`
- Made by: Alibaba
- Category: Video to Video
- Output: video
- Price per 2 seconds of your input video: from $0.04 / 2 seconds of input video (cheapest run $0.04 (40 API credits))
- Run: `POST https://api.doitong.com/v1/run/wan-vace-apps/long-reframe`
- Quote: `POST https://api.doitong.com/v1/quote/wan-vace-apps/long-reframe`
- Docs page: https://doitong.com/fr/developers/models/wan-vace-apps/long-reframe

## Pricing

Price: **from $0.04 / 2 seconds of input video** (the lowest tier; the quote prices your exact input). Price per 2 seconds 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.

Price by tier:

- 240p: $0.04 / 2 seconds of input video
- 360p: $0.04 / 2 seconds of input video
- 480p: $0.04 / 2 seconds of input video
- 580p: $0.06 / 2 seconds of input video
- auto: $0.08 / 2 seconds of input video
- 720p: $0.08 / 2 seconds of input video

The full example input below costs $0.40 = 400 API credits (5 × 2 s input video × $0.08 (auto)).

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/wan-vace-apps/long-reframe` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | no | `` |  | Instructions textuelles guidant la génération vidéo ; facultatives lors d'un recadrage. |
| `negative_prompt` |  | string | no | `letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards` |  | Prompt négatif appliqué lors de la génération d'une vidéo. |
| `seed` |  | integer \| null | no |  |  | Seed rendant la génération reproductible. La valeur None sélectionne un seed aléatoire. |
| `resolution` |  | enum (string) | no | `auto` | `auto`, `240p`, `360p`, `480p`, `580p`, `720p` | Résolution de la vidéo de sortie. |
| `aspect_ratio` |  | enum (string) | no | `auto` | `auto`, `16:9`, `1:1`, `9:16` | Format d'image de la vidéo obtenue. |
| `num_inference_steps` |  | integer | no | `30` | 2 – 50 | Nombre d'étapes d'échantillonnage, avec un temps de traitement plus long pour une meilleure qualité lorsque le nombre augmente. |
| `guidance_scale` |  | number | no | `5` | 1 – 10 | Intensité d'alignement du prompt contrôlée par le guidage sans classifieur ; l'augmenter incite les images générées à suivre plus fidèlement le texte. |
| `sampler` |  | enum (string) | no | `unipc` | `unipc`, `dpm++`, `euler` | Sampler utilisé lors de la génération vidéo. |
| `shift` |  | number | no | `5` | 1 – 15 | Paramètre de décalage appliqué lors de la génération vidéo. |
| `video_url` | `video` | string (video URL) | yes |  |  | Référence de recadrage fournie sous forme d'URL pointant vers le fichier vidéo source. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Commutateur de contrôle de sécurité dont la désactivation nécessite l’autorisation du compte. Sans cette autorisation, chaque requête est contrôlée quel que soit le réglage ; true active le contrôle. |
| `acceleration` |  | enum (string) \| null | no | `regular` | `none`, `low`, `regular` | Paramètre d'accélération de l'inférence, avec le choix entre 'none' et 'regular' : le traitement accéléré améliore considérablement la vitesse au prix d'une très légère modification de la sortie. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Niveau de qualité de la vidéo résultante. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Mode d’écriture de la vidéo résultante. |
| `enable_auto_downsample` |  | boolean | no | `true` |  | Commutateur de sous-échantillonnage automatique. |
| `auto_downsample_min_fps` |  | number | no | `6` | 1 – 60 | Fréquence d'images minimale en FPS pour le sous-échantillonnage automatique. |
| `interpolator_model` |  | enum (string) | no | `film` | `rife`, `film` | Sélection du modèle d'interpolation d'images : 'rife' ou 'film'. |
| `transparency_mode` |  | enum (string) | no | `content_aware` | `content_aware`, `white`, `black` | Gestion de la transparence des images de début et de fin, déterminant la manière dont leurs régions transparentes sont remplies. |
| `return_frames_zip` |  | boolean | no | `false` |  | Contrôle si une archive ZIP contenant chaque image générée est également renvoyée ; activée lorsque la valeur est true. |
| `zoom_factor` |  | number | no | `0` | 0 – 0.9 | Définissez le zoom vidéo sur 0 pour la laisser inchangée. Un facteur positif agrandit la vidéo par rapport au canevas de cette valeur, en recadrant les bords extérieurs. |
| `trim_borders` |  | boolean | no | `true` |  | Contrôle le rognage des bordures de la vidéo. |
| `scene_threshold` |  | number | no | `30` | 0 – 100 | Seuil de détection des scènes : le diminuer augmente le nombre de scènes détectées. Accepte les valeurs de 0 à 100. |
| `paste_back` |  | boolean | no | `true` |  | Contrôle si la scène recadrée est recollée dans la vidéo d'origine. |

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/wan-vace-apps/long-reframe?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/wan-vace-apps/long-reframe?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/wan-vace-apps/long-reframe", 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": "wan-vace-apps/long-reframe",
      "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": "wan-vace-apps/long-reframe",
  "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": 400,
    "usd": "0.40",
    "charged": 400,
    "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    }
  },
  "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, width, height, fps, duration, num_frames} | Fichier vidéo résultant. |

## Related models

- [Wan VACE Video Edit](https://doitong.com/developers/models/wan-vace-apps/video-edit.md) (`wan-vace-apps/video-edit`): from $0.05 / second of input video
- [Happy Horse Video Edit](https://doitong.com/developers/models/alibaba/happy-horse/video-edit.md) (`alibaba/happy-horse/video-edit`): from $0.28 / second of input video
- [Wan 2.2 VACE Fun A14B · Depth](https://doitong.com/developers/models/wan-22-vace-fun-a14b/depth.md) (`wan-22-vace-fun-a14b/depth`): from $0.05 / second of output video
- [Wan 2.2 VACE Fun A14B · Inpainting](https://doitong.com/developers/models/wan-22-vace-fun-a14b/inpainting.md) (`wan-22-vace-fun-a14b/inpainting`): from $0.05 / second of output video
- [Wan 2.2 VACE Fun A14B · Outpainting](https://doitong.com/developers/models/wan-22-vace-fun-a14b/outpainting.md) (`wan-22-vace-fun-a14b/outpainting`): from $0.05 / second of output video
- [Wan 2.2 VACE Fun A14B · Reframe](https://doitong.com/developers/models/wan-22-vace-fun-a14b/reframe.md) (`wan-22-vace-fun-a14b/reframe`): from $0.05 / second of output video
- [Wan Motion](https://doitong.com/developers/models/wan-motion.md) (`wan-motion`): $0.06 / second of input video
- [Wan VACE 14B](https://doitong.com/developers/models/wan-vace-14b.md) (`wan-vace-14b`): from $0.04 / second of output video

## Links

- HTML page: https://doitong.com/developers/models/wan-vace-apps/long-reframe
- 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=wan-vace-apps/long-reframe
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/wan-vace-apps/long-reframe