The AI Native Workspace is here. Download: https://xitter.cf/t.co/TpTjUJbtR0
Joined February 2026
- Tweets214
- Following16
- Followers19K
- Likes429
MiniMax Code retweeted
Each step lays the groundwork for the next.
If your tool catalog is a mess, tool search won't find things
if tool search isn't solid, PTC will struggle too. Don't try to do it all at once. Go bottleneck by bottleneck, and measure at every step.
MiniMax Code retweeted
Models are still getting better fast, and an architecture that makes sense today may not in a few months. More worth remembering than any particular structure is the principle: measure first, change one thing at a time, keep what survives testing.
MiniMax Code retweeted
Mini Apps are now an open standard in MiniMax Code: a port, an Agent, a data directory. You describe the tool, the Agent builds it.
agent.minimax.io/docs/miniap…
Built something useful? Contribute it 👇
github.com/MiniMax-AI/MiniMa… View article
MiniMax Code retweeted
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
MiniMax Code retweeted
Two limited-time perks, only on MiniMax Code
- 2x credits for daily check-ins Sep 28 – Oct 7 (UTC+8), check in on MiniMax Code every day to earn double free credits. Open to new and existing users.
Use them on any model: code with M3.1-Flash-Preview, or make videos with H3 and H3 Max.
- Token Plan quotas reset for everyone All Token Plan quotas reset as soon as M3.1-Flash-Preview goes live.
More resets are coming, so stay tuned.
MiniMax Code retweeted
MiniMax Code CLI is now open sourced 🎉 and SOTA on FrontierHarness Eval
After rapid iterations from day one, we’re thrilled to share this with the developer community. Grateful for every contributor and supporter
MiniMax Code retweeted
I believe experimental throughput and evaluation methodology are becoming the most important parts of a harness. They are also a critical step toward moving from handcrafted harnesses to auto harnesses.
MiniMax Code retweeted
@MiniMaxAgent just shipped H3-based plugins for dynamic images and white-model rendering! Been playing around with them a bit. We're still tuning the white model quality, but this is already pretty fun to mess with~
MiniMax Code retweeted
I tried MiniMax Code CLI (MCode) as soon as it launched.
It fits into your daily dev workflow: use it inside a repo, run it in scripts and CI, or connect it to Zed through ACP.
The part I like is the full engineering loop. MCode reads the project rules first, finds the issue, makes the change, runs tests, and verifies the result.
I ran it on a real task from one of my projects. It moved fast and finished without issues.
Quick test video below 👇
MiniMax Code retweeted
We're delighted to announce that MiniMax M2.7 is now officially open source.
With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 (57.0%).
You can find it on Hugging Face now. Enjoy!🤗
huggingface：huggingface.co/MiniMaxAI/Min…
Blog: minimax.io/news/minimax-m27-…
MiniMax API: platform.minimax.io/
Readers added context they thought people might want to know
The MiniMax M2.7 model weights are publicly available, but under a license prohibiting commercial use without authorization. This does not meet the Open Source Initiative's definition of open source, which requires allowing commercial use.
License: huggingface.co/MiniMaxAI/Mini…
OSI: opensource.org/osd
MiniMax Code retweeted
AI agents are moving fast from research into real products.
Great discussion today at AI+ Renaissance with an incredible group of builders exploring the future of multimodal AI systems.
Our GM of Global Business Linda Sheng joined speakers from @windsurf_ai @arizeai @composio @WorkOS and @Google.
Thanks AI Plus team for hosting.
MiniMax Code retweeted
Now you can start OpenClaw within seconds with MaxClaw.
MaxClaw with telegram and Whatsapp integration can build stuff that a simple agent or llm can't build.
It is fast and its your employee that works 24x7, it builds stuff while you sleep.
I have assigned it to build me a SaaS lets see what it builds, MaxClaw is literally OpenClaw on steroids
Try it out 👇
MiniMax Code retweeted
Introducing M2.5, an open-source frontier model designed for real-world productivity.
- SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work.
- Optimized for efficient execution, 37% faster at complex tasks.
- At $1 per hour with 100 tps, infinite scaling of long-horizon agents now economically possible
MiniMax Agent: agent.minimax.io
API: platform.minimax.io
CodingPlan: platform.minimax.io/subscrib…
