MiniMax M2.7
by MiniMaxtext->text6 endpoints
Neura Intelligence Index
41.2/ 100
Rank
#237—
Confidence
lowBenchmarks
2(5% coverage)
Overview
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...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
204.8K tokens
Max Output
176.9K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
License
mitOpen Weights
Country
🇨🇳CN
Release Date
March 18, 20267mo
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Benchmark Performance
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Pro | 56.2 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| Toolathlon | 46.3 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.21
Output$0.84
Cache read$0.04
Added
March 18, 2026
Last synced 11/6/2026