Parameters
428B
Context Length
1M
Modality
Multimodal
Architecture
Dense
KV Cache Rate
120 KB/tok
License
Proprietary
Release Date
1 Jun 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.30 · Output: $1.20
Precision
Context
Workload Memory: 843.49 GB
FP16 · 8K context
Base Weights: 840.05 GB
KV Cache: 0.94 GB
Runtime & Graphs: 2.50 GB
8x NVIDIA H200 141GB
843.5 / 1015.2 GB usable · TP 8
Determine requirements for datacenter hardware:
Upgrade to Pro
Rank
#136
| Benchmark | Score | Rank |
|---|---|---|
StackUnseen | 0.825 | 13 |
Data Analysis | 0.76 | 32 |
Agentic Coding | 0.41 | 54 |
General | 0.67 | 56 |
Mathematics | 0.77 | 56 |
LiveBench Average | 0.67 | 56 |
Reasoning | 0.74 | 58 |
Agent Arena | -10.16 | 58 |
Agentic Index | 0.29 | 59 |
Coding | 0.68 | 60 |
Web Development | 1483 | 61 |
Coding Index | 0.59 | 69 |
General Text | 1439 | 82 |
Intelligence Index | 0.19 | 166 |
Overall Rank
#136
Coding Rank
#86
MiniMax's flagship multimodal model released June 1, 2026. Powered by MiniMax Sparse Attention (MSA) architecture, which replaces traditional full attention with a KV-block selection pattern, drastically reducing compute costs to 1/20th of the previous generation. It is highly optimized for long-horizon agentic workflows, complex software engineering, and video understanding. Features a 1M token context window, supports text, image, and video inputs, and is priced at $0.30 per million input tokens and $1.20 per million output tokens.
Attention
Attention Structure
Multi-Head Attention
Attention Heads
64
Key-Value Heads
4
Attention Head Dimension
128
Position Embedding
Absolute Position Embedding
RoPE Theta
5,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
6,144
Number of Layers
60
FFN Intermediate Size (Dense)
12,288
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
200,064
MiniMax's flagship M3 model family, released June 1, 2026, is powered by MiniMax Sparse Attention (MSA) architecture, offering 1M context capabilities at exceptionally low compute cost and optimized for long-horizon agentic workflows.