About
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
Related Models
Pricing
Input
$0.18
per 1M tokens
Output
$0.72
per 1M tokens
Blended
$0.32
per 1M tokens
Cheaper than 61% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.32
Monthly
$9.45
vs. Similar Models
MoonshotAI: Kimi K2.5Q:0.0
$0.79+150%
Z.ai: GLM 5 TurboQ:0.0
$1.90+503%
OpenAI: GPT-5.4 NanoQ:+0.1
$0.46+47%
GPT-5.2 (medium)Q:-0.1
$4.81+1428%
Performance
50
tokens/sec
Faster than 16% of models
1.49
seconds
Faster than 33% of models
50.74
seconds
Faster than 7% of models
Market Median
94 tok/s
47% slower
Median TTFT
1.11s
34% slower
Throughput/Dollar
159
tok/s per $/1M
Speed Comparison
Qwen: Qwen3 VL 235B A22B Instruct
50 tok/s-0%
Z.ai: GLM 4.6
50 tok/s+0%
Mistral: Mistral Medium 3
50 tok/s-1%
Context Window
205K
tokens
Larger than 57% of models
Max Output
197K
tokens
96% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
87.4%
HLE
28.1%
LiveCodeBenchNot evaluated
SciCode
47.0%
TerminalBench Hard
39.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
75.7%
Long Context Recall
68.7%
Tau2
84.8%
Market AverageTop Score