# MiniMax AI 模型系列

MiniMax's video generation models are a family of multimodal video systems that turn text, images, and audio into high-quality, cinematic clips with native synchronized sound, strong motion, and up to 2K resolution.

8 个模型更新于 2026年10月

[立即开始](<https://www.modellix.ai/console>)

[充值](<https://www.modellix.ai/console/billing/top-up>)

## 全部 MiniMax 模型

[查看所有模型](<https://www.modellix.ai/zh_CN/explore.md>)

![minimax/minimax-h3-max-v2v](<https://img.modellix.ai/modelix-models-image/20261015/glowing-pen-stroke.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-max-v2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-max-v2v.md>)

视频生视频

MiniMax's fast video-to-video model for drafts guided by reference motion, with optional stills and audio, and picture and sound together. It uses 1 to 3 reference videos in a 5 to 15 second clip at 480p or 768p.

$0.0500\~$0.0800/sec

![minimax/minimax-h3-max-i2v](<https://img.modellix.ai/modelix-models-image/20261015/origami-butterfly-emerging.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-max-i2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-max-i2v.md>)

图生视频

MiniMax's fast reference-to-video model for drafts that keep a subject or style consistent, with picture and sound together. It uses 1 to 9 reference images and up to three audio clips, in a 5 to 15 second clip at 480p or 768p.

$0.0500\~$0.0800/sec

![minimax/minimax-h3-max-fl2v](<https://img.modellix.ai/modelix-models-image/20261015/polaroid-lifting-off.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-max-fl2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-max-fl2v.md>)

图生视频

MiniMax's fast first-and-last-frame model for drafts that open on a still, land on an end frame, or bridge both, with picture and sound together. It makes a 5 to 15 second clip at 480p or 768p.

$0.0500\~$0.0800/sec

![minimax/minimax-h3-max-t2v](<https://img.modellix.ai/modelix-models-image/20261015/paper-cut-cheetah.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-max-t2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-max-t2v.md>)

文生视频

MiniMax's fast text-to-video model for prompt-only drafts and short scenes, with picture and sound together. It makes a 5 to 15 second clip at 480p or 768p, including vertical 9:16 and ultrawide 21:9 frames.

$0.0500\~$0.0800/sec

![minimax/minimax-h3-v2v](<https://img.modellix.ai/modelix-models-image/20260814/porcelain-turning-conch.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-v2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-v2v.md>)

视频生视频

MiniMax's video-to-video model for a new clip guided by reference motion, with optional stills and audio, and picture and sound together. It uses 1 to 3 reference videos in a 4 to 15 second clip at 768p or 2K.

$0.0800\~$0.1300/sec

![minimax/minimax-h3-i2v](<https://img.modellix.ai/modelix-models-image/20260814/origami-diving-conch.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-i2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-i2v.md>)

图生视频

MiniMax's reference-to-video model for a new scene that keeps characters, products, or a style consistent, with picture and sound together. It uses 1 to 9 reference images and up to three audio clips, in a 4 to 15 second clip at 768p or 2K.

$0.0800\~$0.1300/sec

![minimax/minimax-h3-fl2v](<https://img.modellix.ai/modelix-models-image/20260814/chrome-tumbling-conch.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-fl2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-fl2v.md>)

图生视频

MiniMax's first-and-last-frame model for opening on a still, landing on an end frame, or bridging both, with picture and sound together. It makes a 4 to 15 second clip at 768p or 2K.

$0.0800\~$0.1300/sec

![minimax/minimax-h3-t2v](<https://img.modellix.ai/modelix-models-image/20260814/glass-rising-conch.jpg?v=1&w=1376&h=768>)

### [minimax/minimax-h3-t2v](<https://www.modellix.ai/zh_CN/models/minimax/minimax-h3-t2v.md>)

文生视频

MiniMax's text-to-video model for storyboards, character shorts, and cinematic b-roll from a prompt, with picture and sound together. It makes a 4 to 15 second clip at 768p or 2K, including vertical 9:16 and ultrawide 21:9 frames.

$0.0800\~$0.1300/sec

没有找到需要的模型？ [告诉我们。](<https://www.modellix.ai/zh_CN/about.md#contact>)

## 探索更多

[图生视频](<https://www.modellix.ai/zh_CN/category/image-to-video.md>)

探索 Modellix 上的图生视频模型与 API。

62 个模型

[文生视频](<https://www.modellix.ai/zh_CN/category/text-to-video.md>)

探索 Modellix 上的文生视频模型与 API。

29 个模型

[视频生视频](<https://www.modellix.ai/zh_CN/category/video-to-video.md>)

探索 Modellix 上的视频生视频模型与 API。

28 个模型

![HappyHorse](<https://img.modellix.ai/modelix-models-image/20260916/happyhorse.png?v=1&w=640&h=640>)

[HappyHorse](<https://www.modellix.ai/zh_CN/series/happyhorse.md>)

探索 Modellix 上的HappyHorse模型与 API。

7 个模型

![PixVerse](<https://img.modellix.ai/modelix-models-image/20260916/pixverse-color.png?v=1&w=640&h=640>)

[PixVerse](<https://www.modellix.ai/zh_CN/series/pixverse.md>)

探索 Modellix 上的PixVerse模型与 API。

13 个模型

![Gemini Omni](<https://img.modellix.ai/modelix-models-image/20260916/gemini-color.png?v=1&w=640&h=640>)

[Gemini Omni](<https://www.modellix.ai/zh_CN/series/gemini-omni.md>)

探索 Modellix 上的Gemini Omni模型与 API。

9 个模型
