minimax/h3-max/extend-video

H3 Max Extend Video adds a text-guided continuation to an existing video. It supports prompt expansion, adjustable duration and aspect ratio, and output resolutions from 480p to 2K, returning either the full extended video or only the new footage.

Learn more about H3

Inference

Commercial use

Schema

LLMs

Playground API Examples

Input

Video Url*

Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif

Prompt*

Type # to reference inputs.

Duration

Resolution

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0aaad109/HrdPiGacT39YHwjgEoy8z_minimax-h3.mp4",
    "content_type": "video/mp4",
    "file_name": "HrdPiGacT39YHwjgEoy8z_minimax-h3.mp4",
    "file_size": 12141724
  },
  "checkpoint": {
    "url": "https://v3b.fal.media/files/b/0aaad109/Q1lBK4Pj0cxPw8idvGlvQ_minimax-h3-av-checkpoint.safetensors",
    "sha256": "944672b0dd053669c2fcf63270eb022befe6c1390f481c4e1ebb7d10b31b73c4",
    "size_bytes": 2331672,
    "version": 1,
    "model": "minimax-h3",
    "transformer_family": "ref2va-tdm-k10",
    "loras": [],
    "resolution": "768p",
    "checkpoint_id": "54fdc191cd1e183b79e055def9467ab2",
    "owner_id": "8ec360ba025089beb2e6012b3fc40ed49872a612c38dbec764b0c8fc430c343b",
    "source_request_id": "01a0b085-634a-7ee2-a7a6-e5c410ea005f",
    "issued_at": 1789667983,
    "expires_at": 1789754383,
    "audience": "minimax-h3/continue-video",
    "signature": "a83ac7fcca503054532daa1602d3b878961be8f9071b6c4b43354a6f98928e81"
  },
  "seed": 1536522176,
  "frame_count": 616,
  "duration": 25.667,
  "source": {
    "width": 3792,
    "height": 2184,
    "fps": 24,
    "duration": 15.041667,
    "frame_count": 361,
    "has_audio": false
  },
  "expanded_prompt": null,
  "timings": {
    "fetch": 2.735,
    "video_moderation": 3.294,
    "generation": 50.965,
    "source_encode": 8.892,
    "denoising": 12.573,
    "stitch": 17.203,
    "safety_wait": 0,
    "total": 56.995
  }
}

Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token count.