MiniMax: MiniMax M2
minimax/minimax-m2
92nd smartest of 182ReasoningToolsJSON
Intelligence
28.3
92nd of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.255
122nd cheapest
Context
205K
131K max out
How it compares
Smarter than49%
of all ranked models
Cheaper than63%
of all ranked models
Overview
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis73th percentile
Intelligence Index
28.3
GPQA Diamond
78%
Humanity's Last Exam
13%
SciCode
36%
Tau²-Bench (agentic)
87%
Providers & pricing (3)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Minimaxfp8 | $0.255 | $1.02 | 205K | — |
| $0.300 | $1.20 | 197K | — | |
| Novitafp8 | $0.300 | $1.20 | 205K | — |
Specifications
Context window205K
Max output131K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsMiniMaxAI/MiniMax-M2 ↗
MiniMax M2 FAQ
How much does MiniMax M2 cost?
MiniMax M2 costs $0.255 per million input tokens and $1.02 per million output tokens via OpenRouter, making it 122nd cheapest of 332 paid models.
How smart is MiniMax M2?
MiniMax M2 scores 28.3 on the Artificial Analysis Intelligence Index, ranking 92nd of 182 benchmarked models, with a GPQA Diamond score of 78%.
What is MiniMax M2's context window?
MiniMax M2 supports a 205K-token context window and can output up to 131K tokens. It accepts text input.
Similar models
All MiniMax M2 alternatives →Compare head-to-head
MiniMax: MiniMax M2 vs Anthropic: Claude Opus 4.1MiniMax: MiniMax M2 vs Anthropic: Claude Opus 4.1 (batch)MiniMax: MiniMax M2 vs Qwen: Qwen3.5-35B-A3BMiniMax: MiniMax M2 vs Anthropic: Claude Sonnet 4.5MiniMax: MiniMax M2 vs Anthropic: Claude Sonnet 4.5 (batch)MiniMax: MiniMax M2 vs Mistral: Mistral Medium 3.5