MiniMax M3.1 Flash just went free on OpenRouter

Description and use

MiniMax M3.1 Flash is now free on OpenRouter, offering 1M‑token context, multimodal input, and adjustable reasoning effort, making it practical for everyday coding.

Problem

Developers lacked a free, 1M‑token, multimodal coding model with reasoning capabilities.

Outcome

MiniMax M3.1 Flash is now freely accessible, offering 1M‑token context, multimodal input, and adjustable reasoning effort, making it a practical option for everyday coding tasks.

Workflow

• 1. Obtain an OpenRouter API key.
• 2. Set OpenAI client base_url to https://openrouter.ai/api/v1 and api_key to your key.
• 3. Call client.chat.completions.create with model "minimax/minimax-m3.1-flash:free" and desired messages.
• 4. Adjust reasoning effort via the "thinking" parameter (low, medium, high, xhigh, max).

Evidence

MiniMax shipped M3.1 Flash as a preview on September 27, 2026, with almost no fanfare.

Source

A free listing on OpenRouter means anyone with an API key can now try it in a couple of lines.

Source

MiniMax hasn't published speed numbers. Early users report decode in the 90–110 tokens/sec range.

Source