Tag: minimax
7 items with this tag.
MiniMax Admin Portal — Mantine + Next.js + M2.7
MiniMax Admin Portal — Mantine + Next.js + M2.7 Admin portal project using Mantine v9 + Next.js as frontend, MiniMax M2.7 as the AI backend via OpenAI-compatible SDK.
MiniMax M2.7 API — OpenAI-Compatible Access
MiniMax M2.7 API — OpenAI-Compatible Access How to call MiniMax M2.7 via the OpenAI-compatible SDK — no new SDK required.
LiteLLM — Configuring Local LLM and MiniMax
LiteLLM — Configuring Local LLM and MiniMax How to add both a local Ollama model and the MiniMax cloud API to a single LiteLLM config.yaml.
MiniMax Is Cost-Optimal for Solo AI Workflow Testing — Claude Code Team Only Makes Sense at 5+ Seats
MiniMax Is Cost-Optimal for Solo AI Workflow Testing — Claude Code Team Only Makes Sense at 5+ Seats Core Idea For solo developers or small teams (1–4 people) testing and building AI workflows, MiniMax Ultra-Highspeed is significantly cheaper and more flexible than Claude Code Team Premium.
MiniMax Ultra-Highspeed Token Plan Procurement
MiniMax Ultra-Highspeed Token Plan Procurement Purchase approval for MiniMax Ultra-Highspeed token plan to support AI Workflow development and testing via Claude Code at BOL.
MiniMax AI Security and Privacy Features
MiniMax AI Security and Privacy Features Enterprise-grade security and privacy posture of the MiniMax AI platform (Hailuo AI).
Minimax + LiteLLM Cost Estimation (Team)
Minimax + LiteLLM Cost Estimation (Team) Cost estimates for running Minimax models via a LiteLLM proxy for a development team of 20–30 people at medium daily usage.