MiniMax: MiniMax M2-her

MINIMAX Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1434Chatbot Arena Verified

Max Context Limit65,536Max Out: 2,048 tokens

Prompt Caching90% OFF$0.03 / 1M cached

Standard API / 1M$1.50Blended Standard Rate

Model Capabilities & Contract SLAs

Roleplay
Drafting
Classification
Coding & Logic
Fictional

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.30 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.03 / 1M

Output Tokens (Completion)$1.20 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupMiniMax: MiniMax M2-her vs Qwen: Qwen3.5-35B-A3B VS Engine MatchupMiniMax: MiniMax M2-her vs MiniMax: MiniMax M2.5 VS Engine MatchupMiniMax: MiniMax M2-her vs DeepSeek: DeepSeek V3.1 VS Engine MatchupMiniMax: MiniMax M2-her vs Mistral: Mistral Small 3.1 24B VS Engine MatchupMiniMax: MiniMax M2-her vs OpenAI: GPT-6 Luna VS Engine MatchupMiniMax: MiniMax M2-her vs OpenAI: GPT-6 Sol Pro