# H3 Max Reference to Video API

> Ġenerazzjoni tal-vidjo H3 Max li żżomm is-suġġetti konsistenti billi tuża immaġnijiet, vidjows u klipps awdjo ta' referenza

Jiġġenera vidjo ggwidat minn assi ta' referenza: sa 9 immaġnijiet, 3 vidjows u 3 klipps awdjo, b'massimu ta' 12-il fajl b'kollox. Il-prompt jirreferi għalihom bħala Image 1, Video 1, Audio 1 u hekk ikompli. L-ewwel, tan-nofs fakultattiv (`middle_image_url` f'`middle_frame_time`) u l-aħħar frejms jiffissaw il-bidu, in-nofs u t-tmiem. `duration` huwa 0.92 sa 15-il sekonda, u `aspect_ratio` jista' jkun adattiv.

- 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/mt/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 | Istruzzjonijiet għall-ġenerazzjoni tal-vidjo b’referenzi identifikati skont it-tip ta’ assi u l-pożizzjoni fil-lista ta’ referenzi rispettiva, bl-użu ta’ tikketti bħal Audio 1, Video 1, Image 1, Image 2, u oħrajn. |
| `reference_image_urls` | `images` | array of image URL | no |  | ≤ 9 items | URLs ta’ immaġnijiet ta’ referenza għas-suġġett jew għall-istil, b’massimu kondiviż ta’ 12-il fajl mar-referenzi kollha tal-vidjo u tal-awdjo. Identifika dawn l-immaġnijiet fil-prompt skont il-pożizzjoni fil-lista billi tuża Image 1, Image 2, u tikketti sussegwenti. |
| `reference_video_urls` |  | array of video URL | no |  | ≤ 3 items | URLs ta’ vidjows ta’ referenza għall-moviment jew għal skopijiet oħra, identifikati skont il-pożizzjoni fil-lista fil-prompt billi tuża Video 1, Video 2, u tikketti sussegwenti. Il-limitu kondiviż bejn ir-referenzi tal-immaġni, tal-vidjo u tal-awdjo huwa ta’ 12-il fajl; kull klipp tal-vidjo jrid idum 2–15-il sekonda u t-total ma jaqbiżx 15-il sekonda. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | Ipprovdi awdjo ta’ referenza bħala URLs u identifika l-klipps fil-prompt billi tuża Audio 1, Audio 2, u tikketti sussegwenti. Kull klipp irid idum 2–15-il sekonda, b’massimu ta’ 15-il sekonda awdjo b’kollox. Kwalunkwe tip ta’ referenza tal-immaġni, tal-vidjo u tal-awdjo jista’ jiġi pprovdut waħdu jew flimkien, soġġett għal massimu kondiviż ta’ 12-il fajl. |
| `image_url` | `image` | string (image URL) \| null | no |  | ≥ 1 characters | URL ta’ immaġni mhux obbligatorju li jiddefinixxi l-frejm eżatt tal-bidu u jiddetermina l-kanvas tal-output. L-assi ta’ referenza jżommu l-konsistenza tas-suġġett. |
| `middle_image_url` |  | string (image URL) \| null | no |  | ≥ 1 characters | Immaġni ta’ gwida mhux obbligatorja għal middle_frame_time, disponibbli biss b’ġenerazzjoni nattiva f’480P jew 768P u meta jiġu pprovduti kemm immaġni tal-bidu kif ukoll immaġni tat-tmiem. |
| `middle_frame_time` |  | number \| null | no |  | > 0, < 15 | Ħin tat-tqegħid tal-immaġni tan-nofs, użabbli biss ma’ middle_image_url u ristrett għal pożizzjonijiet strettament ġewwa l-ewwel u l-aħħar frejm tal-vidjo mitlub. Ipprovdi s-sekondi li għaddew mill-bidu; il-valur jiġi arrotondat għall-eqreb frejm ta’ 24 fps. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  | ≥ 1 characters | URL ta’ immaġni finali mhux obbligatorju li jiffissa l-frejm eżatt tat-tmiem tal-vidjo għall-immaġni pprovduta. |
| `duration` |  | number | no | `5` | 0.92 – 15 | Tul mitlub f’sekondi, li jippermetti tul reali tal-vidjo sa madwar 0.7 s lil hinn minn dik it-talba. |
| `resolution` |  | enum (string) | no | `768P` | `480P`, `768P`, `1080P` | Għażla tar-riżoluzzjoni tal-ġenerazzjoni: 1080P teħtieġ irfinar latent ta’ materjal iġġenerat b’mod nattiv f’768P, minflok ġenerazzjoni nattiva fir-riżoluzzjoni magħżula. |
| `seed` |  | integer \| null | no |  |  | Seed għall-ġenerazzjoni każwali; jekk jitħalla barra, jintgħażel wieħed b’mod każwali. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Attivazzjoni tal-kontroll tas-sikurezza; true jippermetti l-kontroll. |
| `prompt_expansion_mode` |  | string | yes | `balanced` |  | Livell ta’ sforz għar-riformulazzjoni tal-prompt qabel il-ġenerazzjoni: 'quality' jiżviluppa prompt aktar rikk f’madwar 30s, filwaqt li 'balanced' jirritorna f’madwar sekonda. Agħżel 'disabled' biex titħalla barra l-espansjoni tal-prompt. |
| `aspect_ratio` |  | enum (string) | no | `adaptive` | `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Proporzjon tal-aspett għall-vidjo tal-output. |
| `reference_conditions` |  | array of object {type, url} | no |  | ≤ 12 items | Lista ta’ referenzi pprovduta bħala alternattiva għal reference_*_urls, qatt flimkien magħhom. L-ordni bejn il-modalitajiet għandha tifsira, għalhekk is-sekwenza tinżamm matul l-ipproċessar kollu. |
| `reference_conditions[].type` |  | enum (string) | yes |  | `image`, `video`, `audio` | Modalità tar-referenza; l-ordni bejn il-modalitajiet fil-lista għandha tifsira. |
| `reference_conditions[].url` |  | string | yes |  | ≥ 1 characters | URL tal-midja ta’ referenza. |

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} | Vidjo prodott mill-mudell. |
| `expanded_prompt` | string \| null | Prompt estiż lest għall-mudell, jew null jekk ma jkunx hemm test estiż disponibbli. Il-każijiet null huma espansjoni diżattivata, espansjoni li ma biddlet xejn, u espansjoni ttrattata internament mill-API ospitat tal-mudell. |
| `seed` | integer | Seed bażiku użat biex jiġi riprodott ir-riżultat iġġenerat. |
| `timings` | object \| null | Kejl tal-ħin espress f’sekondi, disponibbli biss fuq rotot li jirrapportaw il-ħinijiet tal-backend; inkella null. L-entrata 'inference' tkejjel kemm dam id-denoising DiT fuq il-backend tal-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