MiniMax M3.1 Flash, the model behind Space Bunny, is free on Ollama Cloud through Oct 22

Ollama has teamed up with MiniMax to make MiniMax M3.1 Flash free on Ollama Cloud. Input, cached input, and output all cost $0 until October 22, 11:59 PM UTC. The model is hosted in the US, and Ollama keeps zero retention of your prompts and responses.

What you can use

• MiniMax M3.1 Flash is built for coding and agent work, and the stealth model Space Bunny was an earlier version of it. It has a 976K-token context window and 428B total parameters, takes image input, and supports tool calling and thinking.
• After the free window, it bills pay-as-you-go at $0.15 per million input tokens, $0.015 per million cached input tokens, and $0.60 per million output tokens.
• Free Ollama accounts run one request at a time, and their starter usage covers a smaller set of starter models. Buying usage credits unlocks every cloud model.

How to use it

1. Install Ollama, open the app or run ollama in a terminal, and sign in to your Ollama account.
2. To chat in the terminal, run ollama run minimax-m3.1-flash:cloud. It runs in the cloud, so there is nothing to download.
3. To use it in Claude Code, run ollama launch claude --model minimax-m3.1-flash:cloud. Swap claude for codex or opencode to launch Codex or OpenCode instead.
4. For the API, create an API key on the Ollama site, send requests to https://ollama.com/api/chat, and set the model to minimax-m3.1-flash.

The same model is also free on OpenCode, OpenRouter, and Vercel AI Gateway. If you prefer MiniMax's own subscription, see M Plan half off.

See the Ollama model page, Ollama pricing, and Ollama's announcement.