MiniMax
MiniMax serves the MiniMax family of LLMs (for example MiniMax-M3) through an OpenAI-compatible API.
Getting started with MiniMax
- Sign in to platform.minimax.io.
- Create an API key from your account.
- Pick a model from the MiniMax model docs (for example
MiniMax-M3).
Setting up MiniMax in Unstract
- Sign in to the Unstract Platform.
- From the side navigation menu, choose
Settings🞂LLMs. - Click on the
New LLM Profilebutton. - From the list of LLMs, choose
MiniMax. - Name — a unique name for this adapter instance.
- API Key — your MiniMax API key from platform.minimax.io.
- Model — the model name from the MiniMax docs. Defaults to
MiniMax-M3. - API Base — pre-filled with
https://api.minimax.io/v1. A base whose path ends in/anthropicuses the Anthropic-compatible protocol; any other base uses the OpenAI-compatible protocol. China accounts use theapi.minimaxi.comhost. - Service Tier —
standard(default) orpriority(faster admission at a higher price). Cost tracking records standard-tier rates. - Maximum Output Tokens — defaults to
4096. Leave empty to use the provider default. - Enable Thinking — overrides the protocol default for
MiniMax-M3. MiniMax-M2.x models always keep thinking enabled. - Leave
Max RetriesandTimeoutat their defaults. - Click on
Test Connectionand ensure it succeeds, then clickSubmit.