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

# Minimax Hailuo 2.3 Text-to-Video

Minimax Hailuo 2.3 is a newly upgraded video generation model, delivering stronger performance in body movements, physical effects, and instruction understanding and execution.

<Tip>
  This is an **asynchronous** API and returns only the asynchronous task's task\_id. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the video generation result.
</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="prompt" type="string" required={true}>
  The prompt text used to guide generation.

  Range: `1 <= x <= 2000`.

  Supports 15 camera movement instructions:

  * Lateral movement: \[左移], \[右移]
  * Pan left/right: \[左摇], \[右摇]
  * Push/pull: \[推进], \[拉远]
  * Rise/fall: \[上升], \[下降]
  * Tilt up/down: \[上摇], \[下摇]
  * Zoom: \[变焦推近], \[变焦拉远]
  * Other: \[晃动], \[跟随], \[固定]

  Usage rules:

  * Combined camera movements: Multiple instructions within the same \[] group take effect simultaneously, such as \[左摇,上升]. It is recommended to combine no more than 3 instructions.
  * Sequential camera movements: Instructions that appear earlier and later in the prompt take effect in order, such as "...\[推进], then...\[拉远]".
  * Natural language: Camera movements can also be described in natural language, but using standard instructions produces more accurate responses.
</ParamField>

<ParamField body="duration" type="integer" required={false}>
  Duration of the generated video (seconds). Default value: `6`<br />
  Available values: `6`, `10`
</ParamField>

<ParamField body="resolution" type="string" required={false}>
  Resolution of the generated video. Default value: `768P`

  * 6-second videos support: `768P`, `1080P`
  * 10-second videos support only: `768P`
</ParamField>

<ParamField body="enable_prompt_expansion" type="boolean" required={false}>
  Whether to enable prompt optimization.

  Default value: `true`.
</ParamField>

<ParamField body="fast_pretreatment" type="boolean" required={false} default={false}>
  Whether to reduce the time required for prompt optimization.

  Default value: `false`.
</ParamField>

## Response Information

<ResponseField name="task_id" type="string" required={true}>
  The task\_id of the asynchronous task. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to obtain the generation result.
</ResponseField>