# MiniMax H3 Max Text to Video - Core.Today AI API

> MiniMax H3 Max text-to-video via Fal.AI. fal's post-trained variant of MiniMax Hailuo-03 (H3), tuned for stronger prompt adherence and better aesthetics — 5-15 second clips with native audio, six aspect ratios (21:9 through 9:16), and 480P/768P native or 1080P refined output.

- **Provider**: MiniMax
- **Model ID**: minimax/h3-max/text-to-video
- **Category**: Video Generation
- **Credits**: 930 per 5s 768P video — billed per second (480P 116/s, 768P 186/s, 1080P 372/s)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Post-trained H3 variant with stronger prompt adherence and aesthetics
- Native audio generated alongside the video
- 5-15 second duration, billed per second
- 480P/768P native generation or 1080P refinement

## Use Cases
- Marketing and hero videos where prompt fidelity matters
- Wide (21:9) cinematic shots for landing pages
- Vertical (9:16) social clips with native audio
- Storyboard previews at 480P before a 1080P final

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for video generation (up to 50,000 characters).

### Optional
- **duration**: integer (default: 5) - The duration of the video in seconds (5-15), billed per second.
- **resolution**: string (default: 768P) - 480P and 768P are native generation modes; 1080P is latent refinement from a native 768P source.
  Options: 480P, 768P, 1080P
- **aspect_ratio**: string (default: 16:9) - The aspect ratio of the generated video.
  Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
- **prompt_expansion_mode**: string (default: balanced) - How much effort to spend rewriting the prompt before generation. 'disabled' skips expansion, 'balanced' returns in about a second, 'quality' spends up to ~30s on a richer prompt.
  Options: disabled, balanced, quality
- **enable_safety_checker**: boolean (default: true) - If set to true, the safety checker will be enabled.
- **seed**: integer - Random seed. A random seed is selected when omitted.

## Examples

### Garden scene with natural motion
A gentle nature scene with smooth camera tracking at the default 768P.
```json
{
  "model": "minimax/h3-max/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": "768P",
    "aspect_ratio": "16:9"
  }
}
```

### Wide cinematic hero shot
An ultra-wide 21:9 shot refined to 1080P.
```json
{
  "model": "minimax/h3-max/text-to-video",
  "input": {
    "prompt": "A sleek electric car drives along a coastal highway at sunset, wide cinematic framing, dramatic lighting.",
    "duration": 10,
    "resolution": "1080P",
    "aspect_ratio": "21:9"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Iterate at 480P (116/s) and render the final at 768P or 1080P.
- Set prompt_expansion_mode to 'disabled' when you want the prompt used verbatim.
- Billing is per second of duration — 15s at 1080P costs three times a 5s clip.
- Audio is generated natively; describe sounds and dialogue in the prompt.

## Documentation
https://fal.ai/models/minimax/h3-max/text-to-video