modelgrep
M

MiniMax: MiniMax M1

minimax/minimax-m1

ReasoningTools
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
18
266th fastest
Latency
840ms
first token
Input price
$0.400
149th cheapest
Context
1M
40K max out

How it compares

Faster than9%
of all ranked models
Cheaper than50%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis
Coding Index
14.1
GPQA Diamond
68%
Humanity's Last Exam
8%
SciCode
38%
Tau²-Bench (agentic)
32%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Minimax$0.400$2.20
Novitabf16$0.550$2.20

Specifications

Context window1M
Max output40K
Knowledge cutoffJun 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

MiniMax M1 FAQ

How much does MiniMax M1 cost?

MiniMax M1 costs $0.400 per million input tokens and $2.20 per million output tokens via OpenRouter, making it 149th cheapest of 298 paid models.

How fast is MiniMax M1?

MiniMax M1 generates around 18 tokens per second with 840ms time-to-first-token (p50), the 266th fastest tracked model.

What is MiniMax M1's context window?

MiniMax M1 supports a 1M-token context window and can output up to 40K tokens. It accepts text input.

Compare head-to-head