# H3 Max Turbo Extend Video API

> Продлевает исходное видео длительностью от 1.625 до 60 секунд на 0.71–15 секунд новых кадров по промпту

Продолжает видео из `video_url` (до 50 MB), добавляя новые кадры, описанные в `prompt`. `duration` задаёт длительность добавления от 0.71 до 15 секунд, а разрешение варьируется от 480P до 2K. `output` возвращает полное расширенное видео или только клип-продолжение. До 3 `reference_audio_urls` могут задавать аудио.

- Model id: `minimax/h3-max-turbo/extend-video`
- Made by: MiniMax
- Category: Video to Video
- Output: video
- Price: from $0.025 / second (5 s ≈ $0.125) (cheapest run $0.125 (125 API credits))
- Run: `POST https://api.doitong.ru/v1/run/minimax/h3-max-turbo/extend-video`
- Quote: `POST https://api.doitong.ru/v1/quote/minimax/h3-max-turbo/extend-video`
- Docs page: https://doitong.com/developers/models/minimax/h3-max-turbo/extend-video

## Pricing

Price: **from $0.025 / second (5 s ≈ $0.125)** (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: $0.04 (40 API credits) / second
- When `resolution` = 1080P: $0.08 (80 API credits) / second
- When `resolution` = 2K: $0.16 (160 API credits) / second

The full example input below costs $0.20 = 200 API credits (5 s × 40 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-max-turbo/extend-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 |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  | ≥ 1 characters | Source video URL for extension; the file must not exceed 50 MB. Accepted videos have an aspect ratio of 0.4–2.5 and a duration of 1.625 s–60 s. |
| `prompt` |  | string | yes |  | 1 – 50000 characters | Description of the events that should follow, rather than a description of the source footage. |
| `reference_audio_urls` |  | array of audio URL | no |  | ≤ 3 items | Optional clips that guide the continuation's new audio in place of the source soundtrack; specify their roles in the prompt, for example 'Audio 1 for the voice' and 'Audio 2 for background music'. Each must last 2–15 seconds, with no more than 15 seconds across all clips. The complete extended video keeps the original source soundtrack, whose ending still guides the transition. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Source-guided prompt enhancement for a more consistent continuation. Enabling it lets the system revise the prompt automatically but can make processing take longer. |
| `duration` |  | number | no | `5` | 0.71 – 15 | Requested amount of new footage, measured in seconds rather than the continuation clip's full length. That clip also carries over the source's last 1.625 seconds, with frame rounding potentially adding further time. |
| `resolution` |  | enum (string) | no | `768P` | `480P`, `768P`, `1080P`, `2K` | Resolution of the resulting video. |
| `aspect_ratio` |  | enum (string) | no | `auto` | `auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Output proportions: selecting a ratio applies cropping to match it, whereas 'auto' uses the source video's aspect ratio. |
| `seed` |  | integer \| null | no |  |  | Continuation generation seed; leaving it unspecified uses a random value. |
| `output` |  | enum (string) | no | `extended` | `extended`, `continuation` | Output mode: 'continuation' provides the new footage preceded by a 1.625-second replay of the source ending. To receive the source joined to the new footage in a single video, choose 'extended'. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Moderation of both the input video and prompt. |

File parameters (`video`, `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
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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-turbo/extend-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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-turbo/extend-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max-turbo/extend-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-turbo/extend-video",
      "input": {
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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-turbo/extend-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": 200,
    "usd": "0.20",
    "charged": 200,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    },
    "seed": 42,
    "duration": 5,
    "source": {},
    "expanded_prompt": "string",
    "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} | Resulting video, with an opening 1.625-second repeat when using 'continuation' mode. |
| `seed` | integer | Seed applied when generating the continuation. |
| `duration` | number | Returned video's duration in seconds. |
| `source` | object | Source footage metadata covering dimensions (width and height), frame rate, length, and audio. |
| `expanded_prompt` | string \| null | Expanded prompt text, or null if no changes were made. |
| `timings` | object |  |

## Related models

- [H3 Max Turbo Text to Video](https://doitong.com/developers/models/minimax/h3-max-turbo/text-to-video.md) (`minimax/h3-max-turbo/text-to-video`): from $0.0163 / second of output video
- [H3 Max Turbo Image to Video](https://doitong.com/developers/models/minimax/h3-max-turbo/image-to-video.md) (`minimax/h3-max-turbo/image-to-video`): from $0.0163 / 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
- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time

## Links

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