MiniMax

MiniMax M2.5

by MiniMaxtext->text8 endpoints
Neura Intelligence Index
63.8/ 100
Rank
#118
Confidence
low
Benchmarks
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
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
204.8K tokens
Max Output
128K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
230000000000B
License
mitOpen Weights
Country
🇨🇳CN
Release Date
February 12, 20267mo

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
80.2
verified
SWE-Bench Pro
55.4
verified

agent

BenchmarkScoreSource
BrowseComp
76.3
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.27
Output$1.08
Cache read$0.03
Added
February 12, 2026
Last synced 9/21/2026