# Wan-2.1 First-Last-Frame-to-Video API

> Gerador de vídeo Wan 2.1 que anima entre uma imagem inicial e uma imagem final fornecidas

Cria um clipe que passa de `start_image_url` para `end_image_url`, orientado por um `prompt`. A resolução é 480p ou 720p e a proporção pode ser auto, 16:9, 9:16 ou 1:1. `num_frames` é 81-100 e `frames_per_second` 5-24. Suporta `negative_prompt`, `seed`, controlos de orientação e passos e pesos LoRA através de `loras`.

- Model id: `wan-flf2v`
- Made by: Alibaba
- Category: Image to Video
- Output: video
- Price: from $0.20 / video (cheapest run $0.20 (200 API credits))
- Run: `POST https://api.doitong.com/v1/run/wan-flf2v`
- Quote: `POST https://api.doitong.com/v1/quote/wan-flf2v`
- Docs page: https://doitong.com/pt-PT/developers/models/wan-flf2v

## Pricing

Price: **from $0.20 / video** (the lowest tier; the quote prices your exact input). Billed once per generated video.

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `num_frames` > 81 and `resolution` = 720p: $0.50 (500 API credits) / video
- When `resolution` = 720p: $0.40 (400 API credits) / video
- When `num_frames` > 81: $0.25 (250 API credits) / video

The full example input below costs $0.40 = 400 API credits (1 video × 400 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/wan-flf2v` 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 | yes |  |  | Instruções de texto que orientam a geração de vídeo. |
| `negative_prompt` |  | string | no | `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 negativo aplicado ao gerar um vídeo. |
| `start_image_url` | `image` | string (image URL) | yes |  |  | Forneça a imagem inicial por URL; para corresponder à proporção selecionada, é necessário redimensionar e recortar em torno do centro sempre que a proporção da imagem for diferente. |
| `end_image_url` | `end_image` | string (image URL) | yes |  |  | Forneça a imagem final por URL; para corresponder à proporção selecionada, é necessário redimensionar e recortar em torno do centro sempre que a proporção da imagem for diferente. |
| `num_frames` |  | integer \| null | no | `81` | 81 – 100 | Número de frames da geração, entre 81 e 100 inclusive. |
| `frames_per_second` |  | integer \| null | no | `16` | 5 – 24 | Taxa de frames do vídeo gerado, em frames por segundo, entre 5 e 24. |
| `seed` |  | integer \| null | no |  |  | Seed que torna a geração reproduzível. Defini-la como None seleciona uma seed aleatoriamente. |
| `resolution` |  | enum (string) | no | `720p` | `480p`, `720p` | Resolução do vídeo de saída, 480p ou 720p. |
| `num_inference_steps` |  | integer | no | `30` | 2 – 40 | Número de passos de amostragem, trocando um tempo de processamento mais longo por melhor qualidade à medida que o número aumenta. |
| `guide_scale` |  | number | no | `5` | 1 – 10 | Intensidade da orientação sem classificador, trocando uma possível perda de qualidade por uma correspondência mais próxima do prompt à medida que a escala aumenta. |
| `shift` |  | number | no | `5` | 1 – 10 | Definição de deslocamento aplicada ao gerar o vídeo. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Interruptor de verificação de segurança cuja desativação exige autorização da conta. Sem essa autorização, todos os pedidos são verificados independentemente da definição; true ativa o verificador. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Controla se a expansão do prompt está ativada. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular` | Definição de aceleração, com 'regular' como opção recomendada. Aumentar a aceleração sacrifica qualidade para reduzir o tempo de geração. |
| `aspect_ratio` |  | enum (string) | no | `auto` | `auto`, `16:9`, `9:16`, `1:1` | Proporções do vídeo gerado, selecionadas automaticamente a partir da imagem de entrada quando definidas como 'auto'. |
| `loras` |  | array of object {path, weight_name, scale} | no | `[]` |  | Pesos LoRA aplicados durante a inferência. |
| `loras[].path` |  | string | yes |  |  | Localização dos pesos LoRA, especificada como URL ou caminho. |
| `loras[].weight_name` |  | string \| null | no |  |  | Nome do peso LoRA, obrigatório apenas quando um repositório Hugging Face contém mais de 1 ficheiro safetensors. Este nome só é utilizado quando `path` identifica esse repositório. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Multiplicador aplicado ao peso LoRA antes de este ser fundido no modelo base. |

File parameters (`image`, `end_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
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "end_image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "end_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/wan-flf2v?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "end_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/wan-flf2v?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "end_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 = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "end_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/wan-flf2v", 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-flf2v",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "end_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": "wan-flf2v",
  "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": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "start_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "end_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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
    },
    "seed": 42
  },
  "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} | Ficheiro de vídeo produzido pela geração. |
| `seed` | integer | Valor da seed aplicado durante a geração. |

## Related models

- [Wan-2.1 Pro Text-to-Video](https://doitong.com/developers/models/wan-pro/text-to-video.md) (`wan-pro/text-to-video`): $0.80 / run
- [Wan-2.1 Text-to-Video](https://doitong.com/developers/models/wan-t2v.md) (`wan-t2v`): from $0.20 / video
- [Wan Effects](https://doitong.com/developers/models/wan-effects.md) (`wan-effects`): $0.35 / video
- [Wan-2.1 Image-to-Video](https://doitong.com/developers/models/wan-i2v.md) (`wan-i2v`): from $0.20 / video
- [Wan-2.1 Pro Image-to-Video](https://doitong.com/developers/models/wan-pro/image-to-video.md) (`wan-pro/image-to-video`): $0.80 / video
- [Wan 3.0 Image to Video](https://doitong.com/developers/models/alibaba/wan-3.0/image-to-video.md) (`alibaba/wan-3.0/image-to-video`): from $0.05 / second
- [FLUX 3 Max Image to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/image-to-video.md) (`blackforestlabs/flux-3-max/image-to-video`): from $0.0425 / second of output video
- [Grok Imagine Video 1.5 Image to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/image-to-video.md) (`xai/grok-imagine-video/v1.5/image-to-video`): from $0.082 / second

## Links

- HTML page: https://doitong.com/developers/models/wan-flf2v
- 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-flf2v
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/wan-flf2v