LLM Comparison

MiniMax M2-her vs MiniMax M2.7

Side-by-side specs, pricing & capabilities · Updated September 2026

Add to comparison

2/6 models

Same tier:

	MiniMax M2-her	MiniMax M2.7
Organization	MiniMax	MiniMax
OpenTools Score		42 56.5
Family	MiniMax	MiniMax
Status	Current	Current
Release Date	Jan 2026	Mar 2026
Context Window	66K tokens	197K tokens
Input Price	$0.30/M tokens	$0.30/M tokens
Output Price	$1.20/M tokens	$1.20/M tokens
Pricing Notes	Cache read: $0.0300/M tokens	Cache read: $0.0590/M tokens
Capabilities	textcode	textcode
Max Output	2K tokens	—
API Identifier	`minimax/minimax-m2-her`	`minimax/minimax-m2.7`
Benchmarks
SWE-bench Pro	—	56.22https://huggingface.co/MiniMaxAI/MiniMax-M2.7
Terminal-Bench 2	—	57https://huggingface.co/MiniMaxAI/MiniMax-M2.7
Artificial Analysis Intelligence Index v4.3	—	23.2171artificial-analysis
GPQA Diamond	—	87.3737artificial-analysis
SciCode	—	50.1157artificial-analysis
Terminal-Bench 2.1	—	55.4307artificial-analysis
	View MiniMax M2-her	View MiniMax M2.7

Cost Calculator

Enter your expected monthly token usage to compare costs.

Input tokens / month

Output tokens / month

Model	Input	Output	Total / mo	vs Best
MiniMax M2-herCheapest	$0.30	$0.60	$0.90	—
MiniMax M2.7Cheapest	$0.30	$0.60	$0.90	—

MiniMax

MiniMax M2-her

MiniMax M2-her is a language-model variant designed for character role-play and interactive storytelling. MiniMax describes work on world consistency, story progression and adaptation to user preferences. It is distinct from the general-purpose MiniMax M2 family.

MiniMax

MiniMax M2.7

MiniMax M2.7 is a large language model from MiniMax. Supports up to 196,608 token context window. Available from $0.30/M input tokens.