Loading...
Loading...
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
Input
$0.29
per 1M tokens
Output
$0.95
per 1M tokens
Blended
$0.45
per 1M tokens
Cheaper than 53% of models. Median price is $0.56/1M tokens.
Daily
$0.45
Monthly
$13.65
78
tokens/sec
Faster than 45% of models
1.35
seconds
Faster than 36% of models
26.97
seconds
Faster than 18% of models
Market Median
86 tok/s
9% slower
Median TTFT
1.07s
26% slower
Throughput/Dollar
172
tok/s per $/1M
Speed Comparison
Context Window
197K
tokens
Larger than 54% of models
Max Output
197K
tokens
100% of context
Quality Index
39.4
76th of 507
Top 15%
Coding Index
32.8
101st of 417
Top 24%
Math Index
82.7
56th of 269
Top 21%
Price/1M
$0.45
297th cheapest
19% below median
Top 47%
Speed
78 tok/s
Top 55%
TTFT
1.35s
Context Window
197K
186th largest
Top 46%