Skip to main content
Core.Today
|
MiniMaxMediumUltra

MiniMax Hailuo-03 (H3) Text to Video

MiniMax Hailuo-03 (H3) text-to-video via Fal.AI. State-of-the-art 2K video generation from a text prompt, 5-15 second duration, native audio, and wide aspect-ratio support (21:9 through 9:16).

3020 credits
per second, tiered by resolution
State-of-the-art 2K resolution text-to-video generation
Native audio generation alongside video
5-15 second configurable duration
Wide aspect-ratio support from 21:9 to 9:16

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/h3/text-to-video",
  "input": {
    "prompt": "A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.",
    "duration": 5,
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes-Text prompt for video generation
durationintegerNo5The duration of the video in seconds.
resolutionstringNo2KThe resolution of the generated video.
768P2K
aspect_ratiostringNo16:9The aspect ratio of the generated video.
21:916:94:31:13:49:16

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Garden scene with natural motion

A gentle nature scene showcasing smooth camera tracking and natural motion at 2K resolution.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/h3/text-to-video",
  "input": {
    "prompt": "A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.",
    "duration": 5,
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }
}'

Wide cinematic hero shot

Generate an ultra-wide 21:9 shot suited for landing-page hero video.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/h3/text-to-video",
  "input": {
    "prompt": "A sleek electric car drives along a coastal highway at sunset, wide cinematic framing, dramatic lighting.",
    "duration": 10,
    "resolution": "2K",
    "aspect_ratio": "21:9"
  }
}'

Tips & Best Practices

1Use 21:9 for cinematic landing-page hero shots, or 9:16 for vertical social content โ€” both are supported at full 2K.
2Duration ranges from 5 to 15 seconds; longer clips cost proportionally more at the per-second rate.
3This model generates native audio automatically โ€” no separate audio upload is needed.

Use Cases

High-resolution flagship marketing or hero video content
Wide-format (21:9) cinematic shots for landing pages or ads
Vertical (9:16) social clips with native audio
Short narrative or product showcase videos from a single prompt