MiniMax M2.5
by MiniMaxtext->text15 endpoints
Neura Intelligence Index
60.6/ 100
Rank
#103—
Confidence
lowBenchmarks
3(8% coverage)
Overview
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...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
204.8K tokens
Max Output
196.6K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
230000000000B
License
mitOpen Weights
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 80.2 | verified |
| SWE-Bench Pro | 55.4 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| BrowseComp | 76.3 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.15
Output$0.90
Cache read$0.05