Models / MiniMax / MiniMax-M2 Her

MiniMax · minimax

MiniMax-M2 Her

MiniMax M2 variant tuned for conversational and character-driven agent interactions

$0.30 in · $1.20 out

per 1M tokens · provider rate closest to the median. No first-party MiniMax price was listed. The reference price is Kilo Gateway's rate, the provider closest to the median.

Context
65,536
Max output
2,048
Cache read
$0.03
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
No
License
—
Released
Jan 23, 2026
Updated in source
Jan 23, 2026
Knowledge
—
Providers
4

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Kilo Gatewayreference$0.30$1.20$0.03——
Ofox$0.30$1.20———
OpenRouter$0.30$1.20$0.03——
NanoGPT$0.30$1.21$0.15——