MiniMax M3.1 Flash

MiniMax-M3.1-Flash is the successor to M3, built for multi-step co-work automation, real codebases and visual work. It has a 1M token context window, accepts text, image and video input, and always reasons, with reasoning_effort from low to max. It is free on the platform route. Bring a MiniMax key under Dashboard → BYOK to use MiniMax directly at its own rate ($0.15 input, $0.60 output per 1M tokens).

import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({ model: anyrouter("minimax/minimax-m3.1-flash"), prompt: "Find the bug in this function." })

anyr claude --model "minimax/minimax-m3.1-flash"

Playbooks: AI SDK, coding agents, OpenAI SDK.