#MiniMax
18 related articles
AI Buzz Weekly: GPT-6.5 Leak, New Claude Model, and MiniMax's Cost-Effectiveness
This week's AI buzz roundup: suspected GPT-6.5 leak, Microsoft configs showing GPT-6.1 Tera, Anthropic's new model that can identify entire classes of bugs, disappointing early Gemini 4 Carbon results, and MiniMax M3.1 Flash beating Claude Opus 5 and GPT-5.6 Sol in benchmarks at extremely low cost.
vLLM Delivers Day-0 Support for MiniMax M3.1 Flash: Engineering Optimizations for Automation and Visual Reasoning
vLLM announces Day-0 support for MiniMax M3.1 Flash, a model built for multi-step automation, real-codebase engineering, and visual reasoning, with native NVFP4 KV cache, NVFP4 MoE weights, and DSpark speculative decoding.
MiniMax Open-Sources MCode Stack: The Agent Skill Library Its Engineering Team Uses Daily
MiniMax open-sources MCode Stack under MIT: 17 SKILL.md skill files and 5 checklists covering code review, sub-agent decomposition, context budgets, and long-running commands.
MiniMax M3.1 Flash Released: 3x Faster, 30% Cheaper, Purpose-Built for Agents
MiniMax releases M3.1 Flash for agentic tasks, coding, and computer use—claimed 3x faster online, 70% lower agentic task cost, 200+ tokens/s output, priced at $0.15/$0.60 per million tokens, now available via API and MiniMax Code.
MiniMax M3.1 Flash Now Free on OpenRouter: A 1M-Context Coding Powerhouse
MiniMax M3.1 Flash is now free on OpenRouter, supporting 1M token context and multimodal input for everyday coding tasks. Here's its positioning, reasoning effort controls, speed, and how to call it.
MiniMax M3.1 Flash Launches Free on AI Gateway: A Multimodal Model with 1M Context
MiniMax M3.1 Flash is free on Vercel AI Gateway through October 20. The open-weight multimodal model supports a 1M-token context and strengthens coding, agentic, and computer use capabilities.
MiniMax M3.1 Flash Hands-On: How Reasoning Effort Determines Bug-Fixing Cost
MiniMax M3.1 Flash on AIHubMix at $0.165/$0.66 per 1M tokens: all 215 hidden tests pass at both max and low reasoning effort, but each bug fix costs $0.0045 at max versus $0.0006 at low—plus full specs, pricing, and a migration checklist.
MiniMax M3.1 Flash Migration in Practice: Fixing Error 2013 and Tuning Thinking Mode
A practical guide to migrating from MiniMax M2.7 to M3.1 Flash: fixing error 2013 (requires adaptive thinking), the ~10x cost gap between default max and low effort, and silent failures in Claude Code, Codex CLI, and OpenCode integrations.
MiniMax M2.5/M2.7 Retirement: M3 API Migration Guide and Cost Analysis
MiniMax announces M2.5 and M2.7 will retire on November 18, 2026, with new user registrations closing October 19. This article covers the M3 model ID changes, API adjustment steps, and cost considerations to help developers transition smoothly.
Product ReviewsMiniMax M2.5 Hands-On Review: How 10B Parameters Deliver Flagship-Level Coding Performance
Hands-on review of MiniMax M2.5's coding performance in Claude Code, including 3D game dev and AI translation platforms, compared to Claude Opus and GPT-5.2.
TutorialsDIY AI Storyboard Tool: Precisely Control Video Generation with Grid-Based Panels
Open-source AI storyboard assistant built with MiniMax M2.5 in 3 days. Supports 9-panel and 25-panel grid generation with per-cell editing for precise Seedance 2.0 video control.
TutorialsComplete Guide for Beginners: Setting Up an AI Programming Environment from Scratch (2025 Latest)
Step-by-step guide for beginners to set up an AI programming environment with Claude Code, VS Code, and MiniMax API, plus an IBE encryption hands-on project.
Product ReviewsChinese AI Coding Plans Compared: How to Choose the Best Value Among 7 Models
2025 comparison of 7 Chinese AI coding subscription plans—Zhipu AI, MiniMax, Kimi, ByteDance Ark & more. Find the best value from ¥29 to ¥200/month.
TutorialsMiniMax M2.7 Free Access Guide: Zero-Cost AI Coding via NVIDIA Endpoint + Kilo CLI
MiniMax M2.7 is now available on NVIDIA's free endpoint. 230B parameter MoE architecture with 204.8K context. Learn how to connect via Kilo CLI for zero-cost AI coding.
TutorialsClaude Code Web Search Broken After Connecting MiniMax? 1-Minute Fix
Fix Claude Code Web Search failure after switching to MiniMax M2.7. Configure the official MiniMax Coding Plan MCP tool with one command to restore search and prevent hallucinations.
Product ReviewsMiniMax Agent Desktop Hands-On: A Chinese AI Assistant That Can Control Your Computer
Hands-on review of MiniMax Agent desktop's computer control capabilities, covering web data collection, file organization, and report generation scenarios.
Product ReviewsMiniMax M2.7 Hands-On Review: Coding Ability Rivals Claude Opus at 50x Lower Cost
In-depth hands-on review of MiniMax M2.7 agentic model: coding ability rivals Claude Opus 4.6 at 50x lower input cost. Real-world tests include MacOS system generation, game dev, and dynamic landing pages.
Product ReviewsMiniMax AI Agent Review: Testing 3 Real-World Scenarios with This Free AI Agent
In-depth MiniMax AI Agent review: tested across business plans, research reports, and PPT creation. Powered by MiniMax M1 with 1M token context. Free to start.