MiniMax

MiniMax M3

by MiniMaxtext+image+video->text12 endpoints
Neura Intelligence Index
70.1/ 100
Rank
#82
Confidence
medium
Benchmarks
6(15% coverage)

Overview

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Capabilities

Text generation
Image understanding
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
TextImageVideo
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
512K tokens
Tokenizer
Other
Uptime (24h)
9996.7%
Parameters
428000000000B
License
mitOpen Weights
Country
🇨🇳CN
Release Date
June 1, 20263mo

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
80.5
verified
SWE-Bench Pro
59
verified

multimodal

BenchmarkScoreSource
MMMU-Pro
78.1
verified

agent

BenchmarkScoreSource
BrowseComp
83.5
verified
MCP Atlas
74.2
verified
APEX Agents
27.7
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.30
Output$1.20
Cache read$0.06
Added
May 31, 2026
Last synced 9/18/2026