> ## 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.
# Models
> Overview of MiniMax AI models and their capabilities
### Language
MiniMax-M3.1-Flash-Preview is available only through M Plan and MiniMax Code for now.
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| MiniMax-M3.1-Flash-Preview | Frontier multimodal coding model with 1M context window and tunable thinking depth | • Multimodal
• 1M context window
• Frontier coding
• Tunable thinking depth |
| [MiniMax-M3](/docs/api-reference/text-anthropic-api) | Frontier multimodal coding model with 1M context window | • Multimodal
• 1M context window
• Frontier coding |
| [MiniMax-M2.7](/docs/api-reference/text-anthropic-api) | Beginning the journey of recursive self-improvement | • Top real-world engineering
• Professional office delivery
• Character-rich interaction |
| [MiniMax-M2.7-highspeed](/docs/api-reference/text-anthropic-api) | Same performance as M2.7
• Significantly faster inference | • Polyglot code mastery
• Precision code refactoring
• Low latency |
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| [MiniMax-M2.5](/docs/api-reference/text-anthropic-api) | • Optimized for code generation and refactoring | • Peak Performance. Ultimate Value. Master the Complex. |
| [MiniMax-M2.5-highspeed](/docs/api-reference/text-anthropic-api) | • Same performance as M2.5
• Significantly faster inference | • Polyglot code mastery
• Precision code refactoring
• Low latency |
| [MiniMax-M2.1](/docs/api-reference/text-anthropic-api) | • 230B total parameters with 10B activated per inference
• Optimized for code generation and refactoring | • Polyglot code mastery
• Precision code refactoring
• Enhanced reasoning |
| [MiniMax-M2.1-highspeed](/docs/api-reference/text-anthropic-api) | • Same performance as M2.1
• Significantly faster inference | • Polyglot code mastery
• Precision code refactoring
• Low latency |
| [MiniMax-M2](/docs/api-reference/text-anthropic-api) | • Context Length: 200k tokens
• Maximum Output: 128k tokens (including CoT) | • Agentic capabilities
• Function calling
• Advanced reasoning
• Real-time streaming |
### Video
| **Models** | **Description** | **Res.& Dur.** | **FPS** |
| :- | :- | :- | :- |
| [MiniMax H3](/docs/api-reference/video-generation-v2-create) | Next-gen open general-purpose multimodal video model
• Text-to-Video / Image-to-Video / First–Last Frame / Multimodal reference | • 768P / 2K
• 4–15s | 24 fps |
| [MiniMax H3 Max](/docs/api-reference/video-generation-v2-create) | High-speed video model post-trained by [fal.ai](https://fal.ai/) on MiniMax H3, optimized for high-speed generation
• Text-to-Video / Image-to-Video (first / last frame) | • 480P / 768P
• 5–15s | 24 fps |
| **Models** | **Description** | **Res.& Dur.** | **FPS** |
| :- | :- | :- | :- |
| [MiniMax Hailuo 2.3](/docs/api-reference/video-generation-t2v) | • Text to Video & Image to Video
• SOTA instruction following
• Extreme physics mastery | • 1080p 6s
• 768p 6s, 10s
| 24 fps |
| [MiniMax Hailuo 2.3Fast](/docs/api-reference/video-generation-i2v) | • Image to Video
• Extreme physics mastery
• Value and Efficiency | • 1080p 6s
• 768p 6s, 10s
| 24 fps |
| [MiniMax Hailuo 02](/docs/api-reference/video-generation-t2v) | • Text to Video & Image to Video
• SOTA instruction following
• Extreme physics mastery | • 1080p 6s
• 768p 6s, 10s
• 512p 6s, 10s | 24 fps |
### Audio
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| [speech-2.8-hd](/docs/api-reference/speech-t2a-http) | • Ultra-realistic quality featuring sound tags | • 40 languages supported
• 7 emotions supported
• specified languages and dialects supported |
| [speech-2.8-turbo](/docs/api-reference/speech-t2a-http) | • Seamless speed meets natural flow | • 40 languages supported
• 7 emotions supported
• specified languages and dialects supported |
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| [speech-2.6-hd](/docs/api-reference/speech-t2a-http) | • Ultimate Similarity
• Ultra-High Quality | • 40 languages supported
• 7 emotions supported
• specified languages and dialects supported |
| [speech-2.6-turbo](/docs/api-reference/speech-t2a-http) | • Ultimate Value
• Low latency | • 40 languages supported
• 7 emotions supported
• specified languages and dialects supported |
| [speech-02-hd](/docs/api-reference/speech-t2a-http) | • Stronger replication similarity
• High quality voice generation | • 24 languages supported
• 7 emotions supported
• specified languages and dialects supported |
| [speech-02-turbo](/docs/api-reference/speech-t2a-http) | • Superior rhythm and stability
• Low latency | • 24 languages supported
• 7 emotions supported
• specified languages and dialects supported |
### Music
Starting August 20, 2026, the paid APIs (Music Generation and Lyrics Generation) will no longer be available to new users; existing paying users can continue to use the current API services. The free music generation APIs (Music-3.0-free, Music-2.6-free, music-cover-free) will be discontinued.
To experience or use music generation capabilities, please visit [MiniMax Audio](https://www.minimax.io/audio), or use the open-source [MiniMax Music 3 model on Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-Music3).
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| [music-3.0](/docs/api-reference/music-generation) | • New Music Generation Capabilities | • Intent Understood
• Sound Elevated
• Vocals Humanized |
| [music-2.6](/docs/api-reference/music-generation) | • Cover Reborn. Bass Redefined. | • Cover Reborn. Bass Redefined. |
| [music-cover](/docs/api-reference/music-generation) | • Generate cover versions from reference audio | • One-step cover generation
• Two-step cover with lyrics modification
• Style transfer
• Auto lyrics extraction |
| **Models** | **Description** | **Features** |
| :- | :- | :- |
| [music-2.0](/docs/api-reference/music-generation) | • Text to Music
• Enhanced musicality
• Natural vocals and smooth melodies | • Human-like performance
• Riche emotional expression
• Enhanced tone control
|