Hailuo Video Models | OpenModels Documentation

Use POST /videos to create a Hailuo video generation task. The examples include optional route and route_mode fields; remove them to use the default available route.

Text-to-video example:

curl -s https://api.getopenmodels.com/v1/videos \
  -H "Authorization: Bearer $OM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax/MiniMax-Hailuo-2.3",
    "route": { "provider": "<provider-for-this-model>" },
    "route_mode": "balanced",
    "prompt": "Generate a video of a carp leaping over the Dragon Gate.",
    "prompt_optimizer": true,
    "fast_pretreatment": false,
    "duration": 6,
    "resolution": "1080P",
    "aigc_watermark": false
  }'

Image-to-video example:

curl -s https://api.getopenmodels.com/v1/videos \
  -H "Authorization: Bearer $OM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax/MiniMax-Hailuo-2.3",
    "route": { "provider": "<provider-for-this-model>" },
    "route_mode": "balanced",
    "first_frame_image": "https://cdn.hailuoai.com/prod/2024-09-18-16/user/multi_chat_file/9c0b5c14-ee88-4a5b-b503-4f626f018639.jpeg",
    "prompt": "Generate a video of a carp leaping over the Dragon Gate.",
    "prompt_optimizer": true,
    "fast_pretreatment": false,
    "duration": 6,
    "resolution": "1080P",
    "aigc_watermark": false
  }'

Use the returned ID to retrieve the task status and generated video result.

curl "https://api.getopenmodels.com/v1/videos/{id}" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OM_API_KEY"

For the MiniMax Hailuo model, set generation options in the request body.

Field	Type	Notes
`model`	string	Model name. Use `MiniMax/MiniMax-Hailuo-2.3`.
`first_frame_image`	string	Required for image-to-video. Use a public image URL or a base64 Data URL such as `data:image/jpeg;base64,...`. Supported formats: JPG, JPEG, PNG, WebP. File size must be under 20 MB, the short side must be over 300 px, and the aspect ratio must be between 2:5 and 5:2.
`prompt`	string	Text description of the video. Required for text-to-video. Maximum length: 2000 characters. Supports camera-control instructions in square brackets.
`prompt_optimizer`	boolean	Whether to optimize the prompt automatically. Default: `true`. Set `false` for more direct prompt control.
`fast_pretreatment`	boolean	Whether to reduce prompt optimizer preprocessing time. Default: `false`.
`duration`	integer	Video duration in seconds. Default: 6. `768P` supports `6` or `10`; `1080P` supports `6`.
`resolution`	string	Video resolution. A 6-second video supports `768P` or `1080P`; a 10-second video supports `768P`. Default: `768P`.
`callback_url`	string	Optional URL for task status callbacks. If omitted, poll `GET https://api.getopenmodels.com/v1/videos/{id}`.
`aigc_watermark`	boolean	Whether to add an AI-generated-content watermark. Default: `false`.