MiniMax

About MiniMax

Overview of MiniMax AI models and their capabilities

Website ↗GitHub ↗Documentation ↗

Source ↗ · 2026-10-24T08:34:50.638378719Z

Service status

unknown

LLM, text-to-speech and video generation

Official status page ↗

33 indexed models

33 matching models

MiniMax: MiniMax M3.1 Flash

minimax/minimax-m3.1-flash-20261019

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real c

Context window
1,048,576
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput

Benchmarks

  • Artificial Analysis: 29.1
  • OpenRouter Benchmarks: 86.785%

Inference prices

  • Cache read / 1M tokens : $0.02 / cache_read_tokens_per_million · miniMax ↗
  • Input / 1M tokens : $0.15 / input_tokens_per_million · miniMax ↗
  • Output / 1M tokens : $0.60 / output_tokens_per_million · miniMax ↗

MiniMax: MiniMax M3

minimax/minimax-m3-20260531

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full a

Context window
1,048,576
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput

Benchmarks

  • Artificial Analysis: 18.9
  • OpenCompass LLM: 90.8%
  • OpenRouter Benchmarks: 91.659%

asr-1.0

miniMax/asr-1.0

Input modalities
audio
Output modalities
transcription
Capabilities
audioInput, transcription

Inference prices

I2V-01

miniMax/I2V-01

Input modalities
image, text
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

I2V-01-Director

miniMax/I2V-01-Director

Input modalities
image, text
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

I2V-01-live

miniMax/I2V-01-live

Input modalities
image, text
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

image-01

miniMax/image-01

Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

image-01-live

miniMax/image-01-live

Input modalities
image, text
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

MiniMax H3

miniMax/MiniMax-H3

Next-gen open general-purpose multimodal video model; • Text-to-Video / Image-to-Video / First–Last Frame / Multimodal reference

Input modalities
text, image, video, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoInput, videoOutput, visionInput

MiniMax-H3-Highspeed

miniMax/MiniMax-H3-Highspeed

Input modalities
text, image, video, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoInput, videoOutput, visionInput

MiniMax-H3-Image-Highspeed

miniMax/MiniMax-H3-Image-Highspeed

• High-speed version of MiniMax-H3-Image • Text-to-Image & Image Edit

Output modalities
image
Capabilities
imageOutput

MiniMax-H3-Lite

miniMax/MiniMax-H3-Lite

Input modalities
text, image, video, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoInput, videoOutput, visionInput

MiniMax H3 Max

miniMax/MiniMax-H3-Max

High-speed video model post-trained by fal.ai on MiniMax H3, optimized for high-speed generation; • Text-to-Video / Image-to-Video (first / last frame)

Input modalities
text, image, video, audio
Output modalities
video
Capabilities
audioInput, multimodal, videoInput, videoOutput, visionInput

MiniMax Hailuo 02

miniMax/MiniMax-Hailuo-02

• Text to Video & Image to Video; • SOTA instruction following; • Extreme physics mastery

Input modalities
text, image
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

MiniMax Hailuo 2.3

miniMax/MiniMax-Hailuo-2.3

• Text to Video & Image to Video; • SOTA instruction following; • Extreme physics mastery

Input modalities
text, image
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

MiniMax Hailuo 2.3Fast

miniMax/MiniMax-Hailuo-2.3-Fast

• Image to Video; • Extreme physics mastery; • Value and Efficiency

Input modalities
image, text
Output modalities
video
Capabilities
multimodal, videoOutput, visionInput

MiniMax: MiniMax H3 Image

minimax/minimax-h3-image-20261110

MiniMax H3 Image is MiniMax's image generation and editing model. It creates images from text prompts and edits or composes images from 1 to 16 reference images, with output up to 20 megapixels and aspect ratios from 1:3 to 3:1.

Context window
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

minimax: MiniMax Music 2.6

cloudflareWorkersAI/minimax/music-2.6

MiniMax's music generation model that creates full-length songs with vocals from text prompts and lyrics, or instrumental tracks. Supports BPM/key control and auto-generated lyrics.

Input modalities
text
Output modalities
audio
Capabilities
audioOutput, musicGeneration

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace