> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Hailuo Series

> MiniMax Hailuo video — Hailuo 2.3 / 2.3 Fast, with 15 bracketed camera-movement tags

MiniMax Hailuo video generation series.

**Two tiers** — `minimax-hailuo-2.3` (the 2.3 main release, adds 15 camera-movement tags) and `minimax-hailuo-2.3-fast` (the 2.3 accelerated tier, faster and cheaper, ideal for previews / batch).

Supports text-to-video (T2V) and image-to-video (I2V).

## Pricing

Billed by **resolution × duration**, in `$ / second`.

| Model                     | 768P       | 1080P      |
| ------------------------- | ---------- | ---------- |
| `minimax-hailuo-2.3`      | `$0.05185` | `$0.0765`  |
| `minimax-hailuo-2.3-fast` | `$0.02635` | `$0.04505` |

## Examples

<CodeGroup>
  ```bash Text-to-video (minimal) theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "minimax-hailuo-2.3",
      "prompt": "A Shiba Inu in a spacesuit walking on the moon, cinematic lighting",
      "duration": 6,
      "resolution": "1080p",
      "aspect_ratio": "16:9"
    }'
  ```

  ```bash Image-to-video (I2V first frame) theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "minimax-hailuo-2.3",
      "action": "image2video",
      "prompt": "The character walks slowly toward the camera",
      "image_urls": ["https://cdn.example.com/portrait.jpg"],
      "duration": 6,
      "resolution": "1080p"
    }'
  ```

  ```bash 2.3 with camera-movement tags theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "minimax-hailuo-2.3",
      "prompt": "[推进] An ancient temple shrouded in mountain mist, [变焦推近] the bronze bell under the eaves swaying gently in the wind",
      "camera_movement_tags": ["推进", "变焦推近"],
      "duration": 6,
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "prompt_optimizer": true
    }'
  ```

  ```bash Accelerated tier (2.3-fast) theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "minimax-hailuo-2.3-fast",
      "prompt": "City night scene, neon lights flickering along the street",
      "duration": 6,
      "resolution": "768p",
      "aspect_ratio": "16:9"
    }'
  ```
</CodeGroup>

<ResponseExample>
  ```json Submission accepted theme={"system"}
  {
    "task_id": "task-wave1775285160b950328499",
    "model": "minimax-hailuo-2.3",
    "action": "generate",
    "status": "queued",
    "created_at": 1775285160040,
    "progress": 0
  }
  ```
</ResponseExample>

After submission, poll status with [`GET /v1/tasks/{task_id}`](/en/api-reference/task/status); see [Task System](/en/docs/task-system) for details.

## Available Models

| Model ID                  | Resolution   | Duration (sec) | Actions                | Notes                                                             |
| ------------------------- | ------------ | -------------- | ---------------------- | ----------------------------------------------------------------- |
| `minimax-hailuo-2.3`      | 768p / 1080p | 6 / 10         | generate / image2video | 1080p only at 6 sec; 15 camera-movement tags; prompt ≤ 2000 chars |
| `minimax-hailuo-2.3-fast` | 768p / 1080p | 6 / 10         | generate / image2video | Accelerated tier, lower unit price                                |

## Common Parameters

<ParamField body="model" type="string" required>
  Model ID. Allowed values:

  * `minimax-hailuo-2.3`
  * `minimax-hailuo-2.3-fast`
</ParamField>

<ParamField body="action" type="string" default="generate">
  Operation type, usually no need to set explicitly (the backend auto-routes by media fields). Allowed values:

  * `generate` — text-to-video (T2V)
  * `image2video` — image-to-video (I2V); pair with `image_urls`
</ParamField>

<ParamField body="prompt" type="string" required>
  Video description text, up to **2000 characters**. Embed `[tag]` brackets in the text to trigger the corresponding camera movement (see [Camera-movement tags](#camera-movement-tags-2-3-2-3-fast) below)
</ParamField>

<ParamField body="aspect_ratio" type="string" default="16:9">
  Frame aspect ratio. Allowed values:

  * `16:9` — landscape widescreen
  * `9:16` — portrait
  * `1:1` — square
</ParamField>

<ParamField body="resolution" type="string" default="768p">
  Output resolution; see [Available Models](#available-models) for per-model support. Allowed values:

  * `768p`
  * `1080p`
</ParamField>

<ParamField body="duration" type="integer">
  Video duration in seconds. Allowed: `6` / `10` (1080p only at 6)
</ParamField>

<ParamField body="image_urls" type="string[]">
  Reference image URL array; triggers **I2V** mode. Public URL or Base64
</ParamField>

<ParamField body="callback_url" type="string">
  Webhook callback URL, invoked when the task reaches a terminal state. See [Callback Mechanism](/en/docs/sync-async#async-task-webhook)
</ParamField>

<ParamField body="callback_events" type="string[]">
  Subscribed callback event types; defaults to all terminal events
</ParamField>

## Model-specific Parameters

<Tabs>
  <Tab title="minimax-hailuo-2.3">
    <ParamField body="watermark" type="boolean" default="false">
      Whether to overlay a MiniMax watermark on the output video
    </ParamField>

    <ParamField body="prompt_optimizer" type="boolean" default="true">
      Auto-optimize the prompt; when disabled, generation runs against the original `prompt`
    </ParamField>

    <ParamField body="fast_pretreatment" type="boolean" default="false">
      Shortens prompt-optimization latency
    </ParamField>

    <ParamField body="camera_movement_tags" type="string[]">
      Camera-movement tag list (15 total). Recommended to also embed `[tag]` brackets directly in the `prompt`; see [Camera-movement tags](#camera-movement-tags-2-3-2-3-fast) below
    </ParamField>
  </Tab>

  <Tab title="minimax-hailuo-2.3-fast">
    <ParamField body="watermark" type="boolean" default="false">
      Whether to overlay a MiniMax watermark on the output video
    </ParamField>

    <ParamField body="prompt_optimizer" type="boolean" default="true">
      Auto-optimize the prompt
    </ParamField>

    <ParamField body="fast_pretreatment" type="boolean" default="false">
      Shortens prompt-optimization latency
    </ParamField>

    <ParamField body="camera_movement_tags" type="string[]">
      Camera-movement tag list (15 total), identical to 2.3
    </ParamField>
  </Tab>
</Tabs>

## Camera-movement Tags (2.3 / 2.3-fast)

The signature feature of the Hailuo 2.3 series — **embed `[tag]` brackets in the `prompt`** to trigger the corresponding camera movement; multiple tags can stack in a single sentence and the backend parses them in order. You can also pass them explicitly via the `camera_movement_tags` field for higher recognition reliability.

| Category        | Tag                 | Effect                                |
| --------------- | ------------------- | ------------------------------------- |
| **Translation** | `[左移]` (pan-left)   | Camera pans horizontally to the left  |
|                 | `[右移]` (pan-right)  | Camera pans horizontally to the right |
|                 | `[上升]` (boom-up)    | Camera moves vertically upward        |
|                 | `[下降]` (boom-down)  | Camera moves vertically downward      |
| **Dolly**       | `[推进]` (dolly-in)   | Camera physically moves forward       |
|                 | `[拉远]` (dolly-out)  | Camera physically moves backward      |
| **Pan/Tilt**    | `[左摇]` (pan left)   | Body fixed, head pans left            |
|                 | `[右摇]` (pan right)  | Body fixed, head pans right           |
|                 | `[上摇]` (tilt up)    | Body fixed, head tilts up             |
|                 | `[下摇]` (tilt down)  | Body fixed, head tilts down           |
| **Zoom**        | `[变焦推近]` (zoom-in)  | Focal-length zoom-in (body still)     |
|                 | `[变焦拉远]` (zoom-out) | Focal-length zoom-out (body still)    |
| **Special**     | `[晃动]` (shake)      | Handheld shake                        |
|                 | `[跟随]` (follow)     | Follow the subject's motion           |
|                 | `[固定]` (static)     | Completely static camera              |

<Tip>
  **Example** — `"[推进] cobblestone street of an old town, [变焦推近] raindrops falling from the eaves"` — camera pushes forward first, then focuses on the eaves detail.
</Tip>

## Resource Limits

| Item                           | Limit                           |
| ------------------------------ | ------------------------------- |
| Reference image (`image_urls`) | URL or Base64, JPG/PNG/WEBP     |
| Prompt length                  | ≤ 2000 characters               |
| Duration                       | 6 / 10 sec; 1080p only at 6 sec |
| Output                         | MP4, link valid for 24 hours    |

## Related Docs

* [Task System Reference](/en/docs/task-system) — task state machine / polling cadence / async push
* [Request & Response Format](/en/docs/request-response) — common error codes / headers / rate limits
* [Authentication](/en/docs/authentication) — API key signup and usage