MiniMax M3.1 Flash targets faster, lower-cost agentic workloads
MiniMax released M3.1 Flash—the model behind the early Space Bunny version—through its API, M Plan, and MiniMax Code, claiming nearly three-times faster online inference and 70% lower usage cost.
AT A GLANCE
Key points
- Space Bunny was revealed as an early version of M3.1 Flash
- MiniMax claims nearly three-times faster online inference
- The company reports a 70% usage-cost reduction
- Available through the API, M Plan, and MiniMax Code
What is changing?
MiniMax officially released its new agentic AI model, M3.1 Flash, on October 19. The company said Space Bunny, which it says processed more than 200 trillion tokens while operating anonymously, was an early version of the model. M3.1 Flash is positioned for complex agentic tasks, software development, computer use, and cybersecurity.
According to provider-reported measurements, online inference is nearly three times faster than the predecessor while total usage cost is 70% lower. MiniMax says everyday output can exceed 200 tokens per second, with median speed consistently above 170 tokens per second. API pricing is listed at $0.15 per million input tokens, $0.60 per million output tokens, and $0.015 per million cached-input tokens.
The model is available through the MiniMax API, M Plan, and MiniMax Code; model weights are planned for later release. Reuters independently reported the launch and the company’s speed and cost claims. The benchmark results remain MiniMax’s own measurements and should be validated on real production tasks.
Explore the original sources
Source date: 19 October 2026.
Published by AI Radar: 19 Oct 2026, 19:08 (Istanbul, UTC+3). Updated: 19 Oct 2026, 19:12.
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…