MiniMax M2-her

Minimax · minimax/minimax-m2-her

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...

MiniMax M2-her ranks #179 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.75 blended per million tokens, it is cheaper than 58% of models with published API pricing. Its 65,536-token context window is 4.0× smaller than the catalog median (262,144 tokens).

texttext->text

vs Claude Opus 5 vs Claude Fable 5 vs Qwen3.8 27B Test in arena Open on OpenRouter

Context

Max context: 65536
Max output: 2048

Pricing

Input / 1M: 0.30
Output / 1M: 1.20
Blend / 1M: 0.75

Quality

Quality index: —

Provider

Provider: Minimax
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.75per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / month	Est. cost (USD)
1,000,000	$0.75
10,000,000	$7.50
100,000,000	$75.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

Closest API price

LongCat 2.0
$0.75 / 1M
MiniMax M3
$0.75 / 1M
KAT-Coder-Pro V2
$0.75 / 1M
MiniMax M2.7
$0.75 / 1M
MiniMax M2.1
$0.75 / 1M