# H3 Max Reference to Video API

> Giniúint físeáin H3 Max a choinníonn na hábhair comhsheasmhach ag úsáid íomhánna, físeáin agus gearrthóga fuaime thagartha

Gineann sé físeán faoi threoir sócmhainní tagartha: suas le 9 íomhá, 3 fhíseán agus 3 ghearrthóg fuaime, le 12 chomhad san iomlán ar a mhéad. Tagraíonn an leid dóibh mar Image 1, Video 1, Audio 1 agus mar sin de. Socraíonn na frámaí roghnacha tosaigh, lárnacha (`middle_image_url` ag `middle_frame_time`) agus deiridh an tús, an lár agus an deireadh. Is é `duration` 0.92 go 15 soicind, agus is féidir `aspect_ratio` a bheith oiriúnaitheach.

- Model id: `minimax/h3-max/reference-to-video`
- Made by: MiniMax
- Category: Reference to Video
- Output: video
- Price per second of your output video: from $0.05 / second of output video (cheapest run $0.05 (50 API credits))
- Run: `POST https://api.doitong.ru/v1/run/minimax/h3-max/reference-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/minimax/h3-max/reference-to-video`
- Docs page: https://doitong.com/ga/developers/models/minimax/h3-max/reference-to-video

## Pricing

Price: **from $0.05 / second of output video** (the lowest tier; the quote prices your exact input). Price per second of your output 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:

- 480P: $0.05 / second of output video
- 768P: $0.08 / second of output video
- 1080P: $0.16 / second of output video

The full example input below costs $0.40 = 400 API credits (5 s output video × $0.08 (768P)).

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-max/reference-to-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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 50000 characters | Treoracha giniúna físeáin le tagairtí aitheanta de réir chineál na sócmhainne agus a suíomh laistigh de gach liosta tagairtí, ag úsáid lipéid amhail Audio 1, Video 1, Image 1, Image 2, agus mar sin de. |
| `reference_image_urls` | `images` | array of image URL | no |  | ≤ 9 items | URLanna íomhánna tagartha don ábhar nó don stíl, ag roinnt uasmhéid 12 chomhad leis na tagairtí físeáin agus fuaime go léir. Aithin na híomhánna seo sa leid de réir a suíomh sa liosta agus úsáid Image 1, Image 2, agus lipéid ina dhiaidh sin. |
| `reference_video_urls` |  | array of video URL | no |  | ≤ 3 items | URLanna físeáin tagartha gluaisne nó eile, aitheanta de réir a suíomh sa liosta sa leid agus Video 1, Video 2, agus lipéid ina dhiaidh sin á n-úsáid. Is é 12 chomhad an teorainn chomhroinnte do thagairtí íomhá, físeáin agus fuaime; caithfidh gach gearrthóg físe maireachtáil 2–15 soicind agus gan níos mó ná 15 shoicind san iomlán a bheith iontu. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | Soláthair fuaim thagartha mar URLanna agus sainaithin na gearrthóga sa leid ag úsáid Audio 1, Audio 2, agus lipéid ina dhiaidh sin. Caithfidh gach gearrthóg maireachtáil 2–15 soicind, agus gan níos mó ná 15 shoicind fuaime a bheith ann san iomlán. Is féidir aon cheann de na cineálacha tagartha íomhá, físeáin agus fuaime a sholáthar leo féin nó le chéile, faoi réir uasmhéid chomhroinnte 12 chomhad. |
| `image_url` | `image` | string (image URL) \| null | no |  | ≥ 1 characters | URL roghnach íomhá a shainíonn an fráma tosaigh beacht agus a chinneann canbhás an aschuir. Coinníonn na sócmhainní tagartha comhsheasmhacht an ábhair. |
| `middle_image_url` |  | string (image URL) \| null | no |  | ≥ 1 characters | Íomhá threorach roghnach do middle_frame_time, ar fáil le giniúint dhúchasach 480P nó 768P amháin agus nuair a sholáthraítear íomhá thosaigh agus íomhá dheiridh araon. |
| `middle_frame_time` |  | number \| null | no |  | > 0, < 15 | Am suite an mheán-íomhá, inúsáidte le middle_image_url amháin agus teoranta do shuímh atá go docht laistigh de chéad agus deireanach fráma an fhíseáin iarrtha. Soláthair na soicindí atá imithe thart ó thús; slánaítear an luach go dtí an fráma 24 fps is gaire. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  | ≥ 1 characters | URL roghnach na híomhá deiridh a shocraíonn fráma deiridh beacht an fhíseáin chuig an íomhá a soláthraíodh. |
| `duration` |  | number | no | `5` | 0.92 – 15 | Fad iarrtha i soicindí, rud a cheadaíonn fad físeáin iarbhír suas le thart ar 0.7 s níos faide ná an t-iarratas sin. |
| `resolution` |  | enum (string) | no | `768P` | `480P`, `768P`, `1080P` | Roghnú taifigh na giniúna: teastaíonn mionchoigeartú latent ó 1080P ar ábhar a gineadh ó dhúchas ag 768P, seachas giniúint dhúchasach ag an taifeach roghnaithe. |
| `seed` |  | integer \| null | no |  |  | Síol don ghiniúint randamach; mura soláthraítear é, roghnaítear ceann go randamach. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Gníomhachtú an tseiceálaí sábháilteachta; cumasaíonn true an tseiceáil. |
| `prompt_expansion_mode` |  | string | yes | `balanced` |  | Iarracht athscríofa an leid roimh an nginiúint: forbraíonn 'quality' leid níos saibhre thar suas le thart ar 30s, agus filleann 'balanced' i gceann thart ar soicind. Roghnaigh 'disabled' chun leathnú an leide a fhágáil ar lár. |
| `aspect_ratio` |  | enum (string) | no | `adaptive` | `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Cóimheas gné an fhíseáin aschuir. |
| `reference_conditions` |  | array of object {type, url} | no |  | ≤ 12 items | Liosta tagairtí a sholáthraítear mar rogha ar reference_*_urls, agus ní in éineacht leo riamh. Tá brí leis an ord idir na módúlachtaí, mar sin coinnítear an seicheamh ar feadh na próiseála. |
| `reference_conditions[].type` |  | enum (string) | yes |  | `image`, `video`, `audio` | Módúlacht na tagartha; tá brí leis an ord idir na módúlachtaí sa liosta. |
| `reference_conditions[].url` |  | string | yes |  | ≥ 1 characters | URL mheán na tagartha. |

File parameters (`images`, `reference_video_urls`, `reference_audio_urls`, `image`, `middle_image_url`, `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",
  "prompt_expansion_mode": "balanced"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "prompt_expansion_mode": "balanced"
}
```

## 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-max/reference-to-video?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",
    "prompt_expansion_mode": "balanced"
  }'

# 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-max/reference-to-video?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",
    "prompt_expansion_mode": "balanced"
  }),
});
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",
    "prompt_expansion_mode": "balanced",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max/reference-to-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.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-max/reference-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "prompt_expansion_mode": "balanced"
      },
      "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-max/reference-to-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": 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",
    "prompt_expansion_mode": "balanced"
  },
  "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",
    "seed": 42,
    "timings": {}
  },
  "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} | Físeán arna tháirgeadh ag an tsamhail. |
| `expanded_prompt` | string \| null | Leid leathnaithe atá réidh don tsamhail, nó null mura bhfuil téacs leathnaithe ar fáil. Is iad na cásanna null ná leathnú díchumasaithe, leathnú nach ndearna aon athrú, agus leathnú a láimhseáil API óstáilte na samhla go hinmheánach. |
| `seed` | integer | Bunsíol a úsáidtear chun an toradh a gineadh a athchruthú. |
| `timings` | object \| null | Tomhais ama arna sloinneadh i soicindí, ar fáil ar bhealaí amháin a thuairiscíonn uainiú an inneall; murach sin null. Tomhaiseann an iontráil 'inference' cá fhad a thóg dínóisiúlú DiT ar inneall GPU. |

## Related models

- [MiniMax H3 Max Text to Video](https://doitong.com/developers/models/minimax/h3-max/text-to-video.md) (`minimax/h3-max/text-to-video`): from $0.0325 / second of output video
- [H3 Max Camera Controls](https://doitong.com/developers/models/minimax/h3-max/camera-controls.md) (`minimax/h3-max/camera-controls`): from $0.0325 / second
- [H3 Max Image to Video](https://doitong.com/developers/models/minimax/h3-max/image-to-video.md) (`minimax/h3-max/image-to-video`): from $0.0325 / second of output video
- [H3 Max](https://doitong.com/developers/models/minimax/h3-max/insert-video.md) (`minimax/h3-max/insert-video`): from $0.05 / second
- [H3 Max Extend Video](https://doitong.com/developers/models/minimax/h3-max/extend-video.md) (`minimax/h3-max/extend-video`): from $0.05 / second of output video
- [H3 Max Recast](https://doitong.com/developers/models/minimax/h3-max/recast.md) (`minimax/h3-max/recast`): from $0.30 / second of input video
- [H3 Max Reframe](https://doitong.com/developers/models/minimax/h3-max/reframe-video.md) (`minimax/h3-max/reframe-video`): from $0.05 / second of input video
- [H3 Max Relight](https://doitong.com/developers/models/minimax/h3-max/relight.md) (`minimax/h3-max/relight`): from $0.05 / second of input video

## Links

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