# MiniMax: MiniMax M1

Provider: minimax  
Category: llm  
Model ID: `minimax/minimax-m1`

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...

## Specs

- Context length: 1000000 tokens
- Max output: 40000 tokens
- Modalities: text
- Released: 2025-06-17

## Pricing

- Input: $0.40 per million tokens
- Output: $2.20 per million tokens

## Providers

- **minimax** — ctx 1000000, input $0.40/M, output $2.20/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/minimax-m1