# MiniMax H3 Reference to Video LoRA API

> Reference-to-video H3 com LoRAs, aceitando até 9 imagens, 3 vídeos e 3 clipes de áudio

Gera vídeo a partir de referências nomeadas no prompt como Image 1, Video 1, Audio 1 e assim sucessivamente. Aceita até 9 imagens, 3 vídeos e 3 clipes de áudio, com um máximo de 12 ficheiros no total. Requer 1 a 3 `loras`. A duração é de 5 a 15 segundos, com proporções entre adaptive e 21:9 e 9:16, e resoluções até 4K.

- Model id: `minimax/h3/reference-to-video/lora`
- Made by: MiniMax
- Category: Reference to Video
- Output: video
- Price: from $0.0625 / second (5 s ≈ $0.313) (cheapest run $0.313 (313 API credits))
- Run: `POST https://api.doitong.ru/v1/run/minimax/h3/reference-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/minimax/h3/reference-to-video/lora`
- Docs page: https://doitong.com/pt-PT/developers/models/minimax/h3/reference-to-video/lora

## Pricing

Price: **from $0.0625 / second (5 s ≈ $0.313)** (the lowest tier; the quote prices your exact input). Billed per second of output (`duration`, default 15).

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

- When `resolution` = 768P: $0.075 (75 API credits) / second
- When `resolution` = 2K: $0.1625 (162.5 API credits) / second
- When `resolution` = 4K: $0.20 (200 API credits) / second

The full example input below costs $0.813 = 813 API credits (5 s × 162.5 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.ru/v1/quote/minimax/h3/reference-to-video/lora` 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 |  | 1 – 50000 characters | Instruções de geração de vídeo com referências identificadas pelo tipo de recurso e pela posição em cada lista de referências, usando etiquetas como Audio 1, Video 1, Image 1, Image 2 e assim por diante. |
| `duration` |  | integer | no | `5` | 5 – 15 | Duração do vídeo, medida em segundos. |
| `resolution` |  | enum (string) | no | `2K` | `480P`, `768P`, `2K`, `4K` | Escolha a resolução do vídeo gerado, com 2K e 4K obtidos através de upscaling de uma base 768P. A escolha de 480P ou 768P usa geração nativa. |
| `seed` |  | integer \| null | no |  |  | Seed para geração aleatória; se omitida, é escolhida aleatoriamente. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Ativação do verificador de segurança; true ativa a verificação. |
| `prompt_expansion_mode` |  | string \| null | no | `balanced` |  | Esforço de reescrita do prompt antes da geração: escolha 'quality' para um prompt mais rico que demora até aproximadamente 30 segundos, ou 'fast' para um resultado em cerca de um segundo. Com 'balanced', a escolha é feita por pedido; 'disabled' desativa a expansão. |
| `aspect_ratio` |  | enum (string) | no | `adaptive` | `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Proporção do vídeo de saída. |
| `reference_image_urls` | `images` | array of image URL | no |  | ≤ 9 items | URLs de imagens de referência do sujeito ou estilo, partilhando um máximo de 12 ficheiros com todas as referências de vídeo e áudio. Identifique estas imagens no prompt pela posição na lista, usando Image 1, Image 2 e as etiquetas seguintes. |
| `reference_video_urls` |  | array of video URL | no |  | ≤ 3 items | URLs de vídeos de referência de movimento ou outros, identificados pela posição na lista no prompt através de Video 1, Video 2 e etiquetas seguintes. O limite partilhado entre referências de imagem, vídeo e áudio é de 12 ficheiros; cada clip de vídeo deve durar 2–15 segundos e o total não pode exceder 15 segundos. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | Forneça o áudio de referência como URLs e identifique os clips no prompt usando Audio 1, Audio 2 e etiquetas seguintes. Cada clip deve durar 2–15 segundos, com um máximo total de 15 segundos de áudio. Qualquer tipo de referência de imagem, vídeo ou áudio pode ser fornecido isoladamente ou combinado, sujeito ao máximo partilhado de 12 ficheiros. |
| `loras` |  | array of object {path, weight_name, scale} | yes |  | 1 – 3 items | Lista de adaptadores LoRA a aplicar ao transformer. |
| `loras[].path` |  | string | yes |  |  | Localização dos pesos LoRA, fornecida como URL ou ID de repositório HuggingFace no formato owner/repo. |
| `loras[].weight_name` |  | string \| null | no |  |  | Especifique o nome do ficheiro de pesos LoRA apenas para selecionar entre vários LoRAs num repositório HuggingFace identificado por `path`. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Intensidade da influência LoRA, entre 0.0 e 4.0. |

File parameters (`images`, `reference_video_urls`, `reference_audio_urls`) 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",
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ]
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ]
}
```

## 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.ru/v1/run/minimax/h3/reference-to-video/lora?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",
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ]
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/minimax/h3/reference-to-video/lora?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",
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ]
  }),
});
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.ru/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",
    "loras": [
        {
            "path": "https://example.com/your-file.safetensors",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3/reference-to-video/lora", 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.ru/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": "minimax/h3/reference-to-video/lora",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "loras": [
          {
            "path": "https://example.com/your-file.safetensors"
          }
        ]
      },
      "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": "minimax/h3/reference-to-video/lora",
  "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": 813,
    "usd": "0.813",
    "charged": 813,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ]
  },
  "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
    },
    "expanded_prompt": "string"
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Vídeo produzido pelo modelo. |
| `expanded_prompt` | string \| null | Prompt expandido pronto para o modelo, ou null se não estiver disponível texto expandido. Os casos null são expansão desativada, expansão sem alterações e expansão processada internamente pela API alojada do modelo. |

## Related models

- [MiniMax H3 Text to Video LoRA](https://doitong.com/developers/models/minimax/h3/text-to-video/lora.md) (`minimax/h3/text-to-video/lora`): from $0.0625 / second
- [MiniMax H3 Image to Video LoRA](https://doitong.com/developers/models/minimax/h3/image-to-video/lora.md) (`minimax/h3/image-to-video/lora`): from $0.0625 / second
- [Seedance 2.0 Fast Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/reference-to-video.md) (`bytedance/seedance-2.0/fast/reference-to-video`): from $0.113 / second
- [Seedance 2.0 Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/reference-to-video.md) (`bytedance/seedance-2.0/reference-to-video`): from $0.141 / second
- [Wan 3.0 Reference to Video](https://doitong.com/developers/models/alibaba/wan-3.0/reference-to-video.md) (`alibaba/wan-3.0/reference-to-video`): from $0.05 / second
- [H3 Max Reference to Video](https://doitong.com/developers/models/minimax/h3-max/reference-to-video.md) (`minimax/h3-max/reference-to-video`): from $0.05 / second of output video
- [MiniMax H3 Reference to Video](https://doitong.com/developers/models/minimax/h3/reference-to-video.md) (`minimax/h3/reference-to-video`): from $0.05 / second of output video
- [Alibaba V2.6 · Reference to Video · Flash](https://doitong.com/developers/models/wan/v2.6/reference-to-video/flash.md) (`wan/v2.6/reference-to-video/flash`): from $0.05 / second of output video

## Links

- HTML page: https://doitong.com/developers/models/minimax/h3/reference-to-video/lora
- 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=minimax/h3/reference-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/minimax/h3/reference-to-video/lora