MiniMax M3.1 Flash, the model behind Space Bunny, is free on Command Code from the $1 Go plan up
#Command Code#MiniMax#M3.1 Flash#Limited time
MiniMax's new M3.1 Flash, released on October 19, is free on Command Code for a limited time. Input, output, and cache reads cost $0 and don't use your plan credits. Every subscriber can use it, from the $1/month Go plan up to Max, with a 1M-token context window.
The briefing
Command Code is a coding agent you can run from the terminal or in its web Studio, on a monthly subscription. MiniMax released its new M3.1 Flash model on October 19, and Command Code has made it free for a limited time, so every subscriber can code with it without touching their plan credits.
What you can use
- The free model ID is
minimax/minimax-m3.1-flash:free. While the deal runs, input, output, and cache reads are billed at $0 and requests don't use your plan credits. - It's available to every subscriber, from the $1/month Go plan through GOAT ($10), Pro ($20), and the Max plans.
- M3.1 Flash normally costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. It has a 1M-token context window, handles image and other multimodal input, and lets you tune thinking depth.
How to use
- Sign in at Command Code. If you don't have a plan yet, subscribe to any tier from Studio > Billing. If you're already subscribed, there's nothing to turn on.
- If you don't have the CLI yet, install it with
npm i -g command-code, then type/modelin a session and pick the free MiniMax M3.1 Flash, or runcmd --model minimax/minimax-m3.1-flash:free. Switching models mid-session keeps your context.
See the announcement in Command Code's post on X, model details on the Command Code model page, and plans on the Command Code pricing page.
Is this still live?
Community signal100% say it still works
