> ## Documentation Index
> Fetch the complete documentation index at: https://platform.minimax.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Model List

> View the models currently available on the MiniMax API platform and those that have been retired.

For model pricing, see the [Pricing Overview](/docs/pricing/overview).

## Available Models

### LLM

| Model | Description |
| :- | :- |
| [MiniMax-M3.1-Flash-Preview](/docs/guides/text-generation) | Frontier multimodal coding model with a 1M context window and tunable thinking depth. |
| [MiniMax-M3](/docs/guides/text-generation) | Frontier multimodal coding model with a 1M context window. |
| [MiniMax-M2.7](/docs/guides/text-generation) | Beginning the journey of recursive self-improvement. |
| [MiniMax-M2.7-highspeed](/docs/guides/text-generation) | Same performance as M2.7, with significantly faster inference. |
| [MiniMax-M2.5](/docs/guides/text-generation) | Optimized for code generation and refactoring. |
| [MiniMax-M2.5-highspeed](/docs/guides/text-generation) | Same performance as M2.5, with significantly faster inference. |

### Video Models

| Model | Description |
| :- | :- |
| [MiniMax-H3](/docs/guides/video-generation) | Next-generation open, general-purpose multimodal video model supporting text-to-video, image-to-video, first-and-last-frame generation, and multimodal references. Supports 768P / 2K output and videos from 4 to 15 seconds. |
| [MiniMax-H3-Max](/docs/guides/video-generation) | High-speed video model post-trained on MiniMax H3, optimized for high-speed generation. Supports text-to-video and image-to-video (first / last frame), with 480P / 768P output and videos from 5 to 15 seconds. |
| [MiniMax-Hailuo-2.3](/docs/guides/video-generation) | Text-to-video and image-to-video generation with state-of-the-art instruction following and extreme physics mastery. |
| [MiniMax-Hailuo-2.3-Fast](/docs/guides/video-generation) | Image-to-video generation with extreme physics mastery and a focus on value and efficiency. |
| [MiniMax-Hailuo-02](/docs/guides/video-generation) | Text-to-video and image-to-video generation with state-of-the-art instruction following and extreme physics mastery. |

### Speech Models

| Model | Description |
| :- | :- |
| [speech-2.8-hd](/docs/guides/speech-t2a-websocket) | Ultra-realistic quality featuring sound tags. |
| [speech-2.8-turbo](/docs/guides/speech-t2a-websocket) | Seamless speed meets natural flow. |
| [speech-2.6-hd](/docs/guides/speech-t2a-websocket) | Ultimate similarity and ultra-high quality. |
| [speech-2.6-turbo](/docs/guides/speech-t2a-websocket) | Ultimate value and low latency. |
| [speech-02-hd](/docs/guides/speech-t2a-websocket) | Stronger replication similarity and high-quality voice generation. |
| [speech-02-turbo](/docs/guides/speech-t2a-websocket) | Superior rhythm and stability with low latency. |

### Image Models

| Model | Description |
| :- | :- |
| [image-01](/docs/guides/image-generation) | Supports text-to-image and image-to-image generation. |
| [image-01-live](/docs/guides/image-generation) | Generates images from a text prompt and a reference image. |

## Retired Models

The following models have been retired and are no longer available.

| Model | Type | Status |
| :- | :- | :- |
| MiniMax-M2.1 | LLM | Retired |
| MiniMax-M2.1-highspeed | LLM | Retired |
| MiniMax-M2 | LLM | Retired |
| M2-her | LLM | Retired |
| music-3.0 | Music | Retired |
| music-2.6 | Music | Retired |
| music-cover | Music | Retired |
| music-3.0-free | Music | Retired |
| music-2.6-free | Music | Retired |
| music-cover-free | Music | Retired |
| Music-2.5+ | Music | Retired |
| Music-2.5 | Music | Retired |
| Music-2.0 | Music | Retired |