# H3 Max Reference to Video API

> H3 Max video-generaciǎ kaj astarel sajekh subjektura le referencikane imàginença, videonça thaj audio-kliponça

Generinela video dirigime referencake asseturenca: dži ko 9 kipesa, 3 video thaj 3 audio klipura, buteder 12 fajlura savorenca. O prompto vakerel palal lende sar Image 1, Video 1, Audio 1 thaj aver. Opcionalne anglune, maškarutne (`middle_image_url` andro `middle_frame_time`) thaj palutne kadra pininena start, maškar thaj agor. `duration` si 0.92 dži ko 15 sekunda, thaj `aspect_ratio` šaj te avel adaptive

- 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/rom/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 | Video-generation instrukcije referencenca sikavde asset type taj position ande sako reference list, labelenca sar Audio 1, Video 1, Image 1, Image 2, taj avre. |
| `reference_image_urls` | `images` | array of image URL | no |  | ≤ 9 items | Subject vaj style reference kipesko URL, sajekh 12-fajlo maximumesa savore video taj audio referencesa. Sikav e kipi ando prompto e listako positionesa: Image 1, Image 2, taj avre labels. |
| `reference_video_urls` |  | array of video URL | no |  | ≤ 3 items | URL adresi le miškipeske vaj aver referentne videonge, prinžarde palal i pozicija ande lista ando prompto pe etiketenca Video 1, Video 2 thaj aver pala lende. O khetano limito le kipenge, videonge thaj audio referencenge si 12 fajlura; sako video klipo trubul te avel 2–15 sekunde, thaj sa khetane na maj but sar 15 sekunde. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | De referentno audio sar URL adresi thaj prinžar le klipura ando prompto pe etiketenca Audio 1, Audio 2 thaj aver pala lende. Sako klipo trubul te avel 2–15 sekunde, thaj sasto audio na maj but sar 15 sekunde. Le kipenge, videonge thaj audio referencenge tipura šaj te den pes korkore vaj khetane, dži ko khetano limito 12 fajlura. |
| `image_url` | `image` | string (image URL) \| null | no |  | ≥ 1 characters | Opcionalno kipesko URL savo sikavel o exacto anglutno kadro taj kerel o rezultatosko canvas. Reference assets arakhen e subjectosko consistency. |
| `middle_image_url` |  | string (image URL) \| null | no |  | ≥ 1 characters | Opcionalno guidance kipo vaš middle_frame_time, dostupno numa native 480P vaj 768P keripasa taj kana si delime angluno taj agorutno kipo. |
| `middle_frame_time` |  | number \| null | no |  | > 0, < 15 | Middle-image placement time, šaj te lelpe numa khetane middle_image_urlesa taj numa ande pozicije striktno maškar e mangline videoske anglune taj agorutne kadro. Del sekunda save nakhle katar o agor; o value si rounded ko maj pašesko 24 fps kadro. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  | ≥ 1 characters | Opcionalno agorutno-kiposko URL savo fixinel o videosko exacto agorutno kadro pe delime kipos. |
| `duration` |  | number | no | `5` | 0.92 – 15 | Manglo durata ande sekunda, savo mukel realno video dži 0.7 s maj dur sar manglo. |
| `resolution` |  | enum (string) | no | `768P` | `480P`, `768P`, `1080P` | Keripasko rezolucija: 1080P mangela latentno dorikheripe e materialosko kerde native 768P-te, na native keripe ande avrirodli rezolucija. |
| `seed` |  | integer \| null | no |  |  | Bijočaripasko semeno vaš random keripe; te na delpes, jekh randomno avralas. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Safety-checker aktivacia; true aktivarel checking. |
| `prompt_expansion_mode` |  | string | yes | `balanced` |  | Promptosko dorikheripasko zor angle keripe: 'quality' kerel jekh barvaleder prompto maj but sar 30s, taj 'balanced' delpes ande jekh sekunda. Avrirod 'disabled' te na kerel promptosko pherdipe. |
| `aspect_ratio` |  | enum (string) | no | `adaptive` | `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Aspect ratio vaš o rezultatosko video. |
| `reference_conditions` |  | array of object {type, url} | no |  | ≤ 12 items | Reference list delime sar alternativa vaš reference_*_urls, na khetane lenca. E ordering maškar modalities si významno, vaš kodo e sequence arakhelpe savore processingosko. |
| `reference_conditions[].type` |  | enum (string) | yes |  | `image`, `video`, `audio` | Reference-ki modality; e ordering maškar modalities ande list si významno. |
| `reference_conditions[].url` |  | string | yes |  | ≥ 1 characters | Reference mediaso URL. |

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} | Video kerdo modelostar. |
| `expanded_prompt` | string \| null | Modeloske pherdo prompto, vaj null te naj pherdo teksto. E null situacije si disabled expansion, expansion savo na paruvdas, taj expansion savo o modelo hostoski API kerel andre. |
| `seed` | integer | Base seed savo reprodukcir-el o kerdo rezultato. |
| `timings` | object \| null | Vaktiro meripe sikavdo ande sekunda, dostupno numa ande routes save sikaven backend timing; averčhane null. O 'inference' entry merel keci vakti lel e DiT denoising pe GPU backend. |

## 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