Loading...
Loading...
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Input
$0.15
per 1M tokens
Output
$1.15
per 1M tokens
Blended
$0.40
per 1M tokens
Cheaper than 55% of models. Median price is $0.56/1M tokens.
Daily
$0.40
Monthly
$12.00
73
tokens/sec
Faster than 42% of models
1.57
seconds
Faster than 28% of models
29.13
seconds
Faster than 16% of models
Market Median
86 tok/s
15% slower
Median TTFT
1.07s
47% slower
Throughput/Dollar
181
tok/s per $/1M
Speed Comparison
Context Window
197K
tokens
Larger than 54% of models
Max Output
197K
tokens
100% of context
Quality Index
41.9
62nd of 507
Top 12%
Coding Index
37.4
62nd of 417
Top 15%
Price/1M
$0.40
282nd cheapest
29% below median
Top 45%
Speed
73 tok/s
Top 58%
TTFT
1.57s
Context Window
197K
186th largest
Top 46%