MiniMax: MiniMax M1
9.1 / 10
1M context
Proprietary
About this model
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
Benchmark Scores
MATH-500
96.8
AIME-2024
86.0
Technical Specs
- Architecture: text->text
- Context Window: 1,000,000 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.55 / 1M tokens | 2.2 / 1M tokens | USD |