Sample Request

curl --request POST \
     --url https://cloud.leonardo.ai/api/rest/v2/generations \
     --header 'accept: application/json' \
     --header 'authorization: Bearer <YOUR_API_KEY>' \
     --header 'content-type: application/json' \
     --data '
{
  "model": "hailuo-03",
  "public": false,
  "parameters": {
    "prompt": "A koala and a cat playing together in a sunlit meadow",
    "quantity": 1,
    "width": 2560,
    "height": 1440,
    "duration": 5,
    "motion_has_audio": true
  }
}
'

API Request Endpoint, Headers, Parameters

Endpoint

https://cloud.leonardo.ai/api/rest/v2/generations

Headers

--header "accept: application/json" \
--header "authorization: Bearer <YOUR_API_KEY>" \
--header "content-type: application/json"

Body Parameters

Parameter	Type	Definition
duration	`integer`	Optional. Duration of the video in seconds. Accepts `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`. Defaults to `5`.
guidances	`object`	Optional. Object defining guidance inputs (e.g. reference images, start/end frames, audio) that influence the result.
guidances.audio_reference	`array`	Optional. Specifies a list of audio references for guidance. Maximum 3 items. Each item includes audio.id and audio.type (`UPLOADED`, `GENERATED`).
guidances.end_frame	`array`	Optional. Creative reinterpretation of vibe or structure from a reference image. Maximum 1 item. Each item includes image.id and image.type (`INIT`, `GENERATION`, `UPLOADED`, `GENERATED`, `VARIATION`).
guidances.image_reference	`array`	Optional. References images to guide your video generation. Maximum 5 items. Each item includes image.id and image.type (`INIT`, `GENERATION`, `UPLOADED`, `GENERATED`, `VARIATION`), strength (`LOW`, `MID`, `HIGH`).
guidances.start_frame	`array`	Optional. Creative reinterpretation of vibe or structure from a reference image. Maximum 1 item. Each item includes image.id and image.type (`INIT`, `GENERATION`, `UPLOADED`, `GENERATED`, `VARIATION`).
height	`integer`	Optional. Height of the output in pixels. Accepts `1440`, `1920`, `2560`, `0`. Defaults to `1440`.
model	`string`	Required. Specifies the model used for generation. Set to `hailuo-03`.
motion_has_audio	`boolean`	Optional. MiniMax Hailuo 03 always generates native audio; this cannot be disabled. Defaults to `True`.
prompt	`string`	Required. The prompt to use for the generation. Maximum 2000 characters.
public	`boolean`	Optional. Controls whether the generation is public (`true`) or private (`false`).
quantity	`integer`	Required. The number of outputs to generate. Defaults to `1`. Range 1-1.
width	`integer`	Optional. Width of the output in pixels. Accepts `1440`, `1920`, `2560`, `3360`, `0`. Defaults to `2560`.

Dimensions

The API accepts width and height parameters in the following combinations:

Aspect Ratio	Pixel Values (Width x Height)
21:9 (Landscape)	3360 x 1440
16:9 (Landscape)	2560 x 1440
4:3 (Landscape)	1920 x 1440
1:1 (Square)	1440 x 1440
3:4 (Portrait)	1440 x 1920
9:16 (Portrait)	1440 x 2560
Auto	0 x 0

Defaults to 2560 x 1440. Setting both width and height to 0 selects Auto, which matches the dimensions of a supplied reference image.