# H3 Max Reference to Video API

> H3 Max video ģenerēšana, saglabājot objektu konsekvenci ar atsauces attēliem, videoklipiem un audio klipiem

Ģenerē video, izmantojot atsauces materiālus: līdz 9 attēliem, 3 videoklipiem un 3 audio klipiem, kopā ne vairāk kā 12 failu. Uzvednē tie tiek apzīmēti kā Image 1, Video 1, Audio 1 un tā tālāk. Neobligāti pirmie, vidējie (`middle_image_url` pie `middle_frame_time`) un pēdējie kadri nosaka sākumu, vidu un beigas. `duration` ir no 0.92 līdz 15 sekundēm, bet `aspect_ratio` var būt 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/lv/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 ģenerēšanas instrukcijas ar atsaucēm, kas identificētas pēc resursa tipa un pozīcijas katrā atsauču sarakstā, izmantojot tādus apzīmējumus kā Audio 1, Video 1, Image 1, Image 2 u. c. |
| `reference_image_urls` | `images` | array of image URL | no |  | ≤ 9 items | Objekta vai stila atsauces attēlu URL, kopā ar visām video un audio atsaucēm nepārsniedzot 12 failus. Uzvednē identificējiet šos attēlus pēc saraksta pozīcijas, izmantojot Image 1, Image 2 un turpmākos apzīmējumus. |
| `reference_video_urls` |  | array of video URL | no |  | ≤ 3 items | Kustības vai citas atsauces video URL, kas uzvednē identificēti pēc saraksta pozīcijas, izmantojot Video 1, Video 2 un turpmākos apzīmējumus. Kopējais attēlu, video un audio atsauču limits ir 12 faili; katram video klipam jāilgst 2–15 sekundes, bet kopējais ilgums nedrīkst pārsniegt 15 sekundes. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | Norādiet atsauces audio kā URL un identificējiet klipus uzvednē, izmantojot Audio 1, Audio 2 un turpmākos apzīmējumus. Katram klipam jāilgst 2–15 sekundes, bet kopējais audio ilgums nedrīkst pārsniegt 15 sekundes. Jebkuru attēlu, video un audio atsauces tipu var norādīt atsevišķi vai kombinēt, ievērojot kopējo 12 failu limitu. |
| `image_url` | `image` | string (image URL) \| null | no |  | ≥ 1 characters | Neobligāts attēla URL, kas nosaka precīzu sākuma kadru un izvades kanvu. Atsauces resursi saglabā objekta konsekvenci. |
| `middle_image_url` |  | string (image URL) \| null | no |  | ≥ 1 characters | Neobligāts vadības attēls middle_frame_time, pieejams tikai ar sākotnēju ģenerēšanu 480P vai 768P un ja ir padots gan sākuma, gan beigu attēls. |
| `middle_frame_time` |  | number \| null | no |  | > 0, < 15 | Vidējā attēla novietojuma laiks, izmantojams tikai ar middle_image_url un ierobežots līdz pozīcijām, kas atrodas stingri starp pieprasītā video pirmo un pēdējo kadru. Norādiet kopš sākuma pagājušo sekunžu skaitu; vērtība tiek noapaļota līdz tuvākajam 24 fps kadram. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  | ≥ 1 characters | Neobligāts beigu attēla URL, kas nosaka precīzu video beigu kadru atbilstoši padotajam attēlam. |
| `duration` |  | number | no | `5` | 0.92 – 15 | Pieprasītais ilgums sekundēs, pieļaujot faktisko video garumu aptuveni par 0,7 s lielāku nekā pieprasītais. |
| `resolution` |  | enum (string) | no | `768P` | `480P`, `768P`, `1080P` | Ģenerēšanas izšķirtspējas izvēle: 1080P izmanto 768P režīmā sākotnēji ģenerēta materiāla latento precizēšanu, nevis sākotnēju ģenerēšanu izvēlētajā izšķirtspējā. |
| `seed` |  | integer \| null | no |  |  | Nejaušas ģenerēšanas sākumvērtība; ja tā nav norādīta, tā tiek izvēlēta nejauši. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Drošības pārbaudītāja aktivizēšana; true iespējo pārbaudi. |
| `prompt_expansion_mode` |  | string | yes | `balanced` |  | Uzvednes pārrakstīšanas intensitāte pirms ģenerēšanas: 'quality' izveido bagātīgāku uzvedni aptuveni līdz 30 s laikā, savukārt 'balanced' atbild aptuveni sekundes laikā. Izvēlieties 'disabled', lai izlaistu uzvednes paplašināšanu. |
| `aspect_ratio` |  | enum (string) | no | `adaptive` | `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Izvades video malu attiecība. |
| `reference_conditions` |  | array of object {type, url} | no |  | ≤ 12 items | Atsauču saraksts, kas tiek padots kā alternatīva reference_*_urls un nekad kopā ar tiem. Secībai starp modalitātēm ir nozīme, tāpēc secība tiek saglabāta visā apstrādes laikā. |
| `reference_conditions[].type` |  | enum (string) | yes |  | `image`, `video`, `audio` | Atsauces modalitāte; secībai starp modalitātēm sarakstā ir nozīme. |
| `reference_conditions[].url` |  | string | yes |  | ≥ 1 characters | Atsauces multivides 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} | Modeļa ģenerētais video. |
| `expanded_prompt` | string \| null | Paplašināta uzvedne, kas sagatavota modelim, vai null, ja paplašināts teksts nav pieejams. null gadījumi ir atspējota paplašināšana, paplašināšana bez izmaiņām un paplašināšana, ko iekšēji apstrādā modeļa viesotais API. |
| `seed` | integer | Pamata sākumvērtība ģenerētā rezultāta atkārtošanai. |
| `timings` | object \| null | Laika mērījumi sekundēs, pieejami tikai maršrutos, kas ziņo aizmugursistēmas laika mērījumus; pretējā gadījumā null. Ieraksts 'inference' mēra, cik ilgi DiT trokšņa noņemšana notika GPU aizmugursistēmā. |

## 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