MiniMax

MiniMax M2.1

by MiniMaxtext->text3 endpoints
Neura Intelligence Index
52.9/ 100
Rank
#171
Confidence
high
Benchmarks
8(21% coverage)

Overview

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...

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
131.1K tokens
Tokenizer
Other
Uptime (24h)
9920.6%
Parameters
230000000000B
License
mitOpen Weights
Country
🇨🇳CN
Release Date
December 23, 20259mo

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
67
verified
TerminalBench
47.9
verified
SciCode
39
verified

math

BenchmarkScoreSource
AIME 2025
81
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
81
verified
Humanity's Last Exam
22
verified

agent

BenchmarkScoreSource
BrowseComp
62
verified
Toolathlon
43.5
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.30
Output$1.20
Cache read$0.03
Added
December 23, 2025
Last synced 9/19/2026