MiniMax: MiniMax M2.7

Text input Text output Unavailable
Author's Description

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 collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

Key Specifications
Cost
$$$$
Context
204K
Released
Mar 18, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Temperature Response Format Include Reasoning Tool Choice Reasoning Max Tokens Top P Tools
Features

This model supports the following features:

Tools Response Format Reasoning
Performance Summary

MiniMax M2.7, created by minimax, is a next-generation large language model designed for autonomous, real-world productivity. While it tends to have longer response times, ranking in the 17th percentile for speed, its pricing is moderate, placing it in the 29th percentile. A standout feature is its exceptional reliability, demonstrating a 99% success rate across benchmarks. M2.7 exhibits strong performance in several key areas, achieving perfect accuracy in General Knowledge, where it is also noted as the most accurate model at its price point and among models of similar speed. It also shows high accuracy in Reasoning (94.0%) and Coding (92.0%), indicating robust problem-solving and programming capabilities. Its agentic capabilities are further supported by strong results on SWE-Pro (56.2%) and Terminal Bench 2 (57.0%), alongside a 1495 ELO on GDPval-AA. A notable weakness is its relatively high cost for Mathematics benchmarks, where it ranks in the 14th percentile for price. Despite this, its overall accuracy across diverse tasks, particularly in knowledge and reasoning, combined with its high reliability, positions M2.7 as a capable model for complex, real-world applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $1.2
Input Cache Read $0.06

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Minimax
Minimax | minimax/minimax-m2.7-20260318 204K $0.3 / 1M tokens $1.2 / 1M tokens
Minimax
Minimax | minimax/minimax-m2.7-20260318 204K $0.6 / 1M tokens $2.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by minimax