MiniMax H3 - Argil

Model id minimax-h3 · MiniMax · video · 3 modes: text-to-video, image-to-video, reference-to-video.

This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls get_model with the mode.

Text To Video

Mode text-to-video. Text to video.

Input

Field	Type	Required	Allowed	Description
`prompt`	string	Yes	up to 5,000 characters	What the video should show: subject, action, camera and style.
`duration`	integer	Yes	5 to 15	Video duration in seconds. Integer 5–15.
`aspect_ratio`	string		`adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Aspect ratio. Defaults to adaptive; frames mode follows the start frame.
`resolution`	string		`480P`, `768P`, `2K`	480P (H3 Max, fastest), 768P (default) or 2K.

Pricing

~3.87 credits/s at 768P (default; 2K ~6.29/s), output + reference-video input, first 5 reference images free then ~1.94 each. 480P (MiniMax H3 Max): ~2.42/s output, ~2.68/s reference video, first 2 images free then ~3.58 each. Audio free. Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "minimax-h3",
  "mode": "text-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "duration": 5,
    "aspect_ratio": "adaptive",
    "resolution": "480P"
  }
}

Image To Video

Mode image-to-video. Animate a start frame, optionally to an end frame.

Input

Field	Type	Required	Allowed	Description
`prompt`	string	Yes	up to 5,000 characters	What the video should show: subject, action, camera and style.
`duration`	integer	Yes	5 to 15	Video duration in seconds. Integer 5–15.
`aspect_ratio`	string		`adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Aspect ratio. Defaults to adaptive; frames mode follows the start frame.
`resolution`	string		`480P`, `768P`, `2K`	480P (H3 Max, fastest), 768P (default) or 2K.
`first_frame`	File			The image to use as the first frame of the video.
`last_frame`	File			Optional last frame: the video goes from the first to it.

Pricing

Example

The arguments of generate_media:

{
  "model": "minimax-h3",
  "mode": "image-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera",
    "duration": 5,
    "aspect_ratio": "adaptive",
    "resolution": "480P"
  }
}

Reference To Video

Mode reference-to-video. A video guided by up to 9 images, 3 videos and 3 audios.

Input

Field	Type	Required	Allowed	Description
`prompt`	string	Yes	up to 5,000 characters	What the video should show. Refer to the references as Image 1, Video 1, Audio 1, in order.
`duration`	integer	Yes	5 to 15	Video duration in seconds. Integer 5–15.
`aspect_ratio`	string		`adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Aspect ratio. Defaults to adaptive; frames mode follows the start frame.
`resolution`	string		`480P`, `768P`, `2K`	480P (H3 Max, fastest), 768P (default) or 2K.
`references`	File list		0 to 15 items	References the output must follow. The kind of each one (image, video, audio) is read from the file; per-kind limits are in the mode’s `capabilities.references`.

References: up to 15: 9 images, 3 videos of 2 to 15 s (15 s in total), 3 audio files (15 s in total). Assets, URLs and elements are accepted.

Pricing

Example

The arguments of generate_media:

{
  "model": "minimax-h3",
  "mode": "reference-to-video",
  "input": {
    "prompt": "A ginger cat walks into a sunlit kitchen, handheld camera, keeping the look of the reference",
    "duration": 5,
    "aspect_ratio": "adaptive",
    "resolution": "480P",
    "references": [
      "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
    ]
  }
}

​Text To Video

​Input

​Pricing

​Example

​Image To Video

​Input

​Pricing

​Example

​Reference To Video

​Input

​Pricing

​Example

Text To Video

Input

Pricing

Example

Image To Video

Input

Pricing

Example

Reference To Video

Input

Pricing

Example