Pinned Tweet
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 s 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
🚀🐰 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 s 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
465
673
7,481
1,671,174
MiniMax M3.1 Flash is now on @tenstorrent Cloud -bringing frontier AI to Tensix silicon, Ethernet scale-out, and an open-source stack from the team led by Jim Keller.
Open weights. Diverse architectures. An open, heterogeneous AI future.🫡
Open weights. Diverse architectures. An open, heterogeneous AI future.🫡
Today @MiniMax_AI released the open weights for MiniMax M3.1 Flash – available now on Tenstorrent Cloud.
Explore in the playground or connect to your agent harness. Start building → bit.ly/47vU2zc
15
22
176
11,099
Thanks @FireworksAI_HQ for bringing M3.1 Flash to serverless on day 0! Looking sharp with the rebrand! 🎆
Try M3.1 Flash in serverless preview for your next multi-step agent workflow 🐰
Try M3.1 Flash in serverless preview for your next multi-step agent workflow 🐰
We have another release you don’t want to miss.
@MiniMax_AI M3.1 Flash is now live on Fireworks, day 0 with the open-weights release.
Built for agents that run long, multi-step work:
→ Cowork automation: 62.8 on AutomationBench-AA
→ Coding: 73.7% on DeepSWE v1.1
→ Visual sion
→ $0.15 input / $0.60 output / $0.015 cached per 1M tokens, half the price of M3
We've heard your feedback that you want more models on serverless. So we're launching more models in preview mode, starting today with M3.1 Flash, available for two weeks.
We'll be watching demand, and if the community likes it, we'll keep it around.
Try it now → bit.ly/4dShASp
8
5
146
9,266
MiniMax (official) retweeted
Build with MiniMax M3.1 Flash for FREE. ⚡
You build. We cover the credits.
🌆 Remix any city, any way you imagine.
🏆 Compete for the $3,000 grand prize.
Powered by @MiniMax_AI × SandBase Lab.
Pick a city. Build your version. Make it yours.
You build. We cover the credits.
🌆 Remix any city, any way you imagine.
🏆 Compete for the $3,000 grand prize.
Powered by @MiniMax_AI × SandBase Lab.
Pick a city. Build your version. Make it yours.
18
115
567
64,938
MiniMax (official) retweeted
MiniMax M3.1 Flash (aka Space Bunny) from @MiniMax_AI is live on Modular Cloud, day zero.
M3.1 Flash is best in cowork automation among open models, with SOTA-level coding and engineering performance. It can ship a fix in a real codebase, then update Jira and Slack afterwards.
iMax team ahead of launch, so M3.1 Flash is already serving production traffic on Modular Cloud. Evaluating it for your stack? Try it now: console.modular.com/signup?utm_sou…
M3.1 Flash is best in cowork automation among open models, with SOTA-level coding and engineering performance. It can ship a fix in a real codebase, then update Jira and Slack afterwards.
iMax team ahead of launch, so M3.1 Flash is already serving production traffic on Modular Cloud. Evaluating it for your stack? Try it now: console.modular.com/signup?utm_sou…
3
5
36
5,150
Thanks to @lightseekorg for Day-0 support with TokenSpeed!
Day-0 support for @MiniMax_AI M3.1 Flash is live in TokenSpeed.
DSpark speculative decoding and MXFP8 + NVFP4 mixed precision on Blackwell.
TokenSpeed is featured in the official deployment guide.
📖 huggingface.co/MiniMaxAI/Mini…
👉 github.com/lightseekorg/t…
10
2
188
19,941
M3.1 Flash weights are now open 🔓
Thanks to @togethercompute for being a day-0 launch partner and bringing M3.1 Flash to production on the AI Native Cloud. Open weights, no GPUs to manage. Great building together! 🐰
Thanks to @togethercompute for being a day-0 launch partner and bringing M3.1 Flash to production on the AI Native Cloud. Open weights, no GPUs to manage. Great building together! 🐰
minimax m3.1 flash is now live on together ai
we’re excited to be a day-0 launch partner for the model, aka space bunny
m3.1 flash is built for agentic tasks, coding, computer use + cybersecurity, with a 1m context window and vision support
try it now together.ai/models/minimax…
25
13
514
64,233
From inference to RL, ready from day one. 🐰
Thanks to the teams behind SGLang, and Miles @sgl_project alongside @NVIDIAAI and @AMD, for supporting MiniMax M3.1 Flash. Great building together!
Thanks to the teams behind SGLang, and Miles @sgl_project alongside @NVIDIAAI and @AMD, for supporting MiniMax M3.1 Flash. Great building together!
Space Bunny is here! 🐰 MiniMax M3.1 Flash hits >1K tok/s, bs1 decode with SGLang, production-ready from Day 0. This integration is a joint effort by @MiniMax_AI, @NVIDIAAI, @AMD, and @radixark, and you can also run RL with Miles!
-Broad hardware support: NVIDIA Blackwell and Hop00), plus AMD Instinct MI350X and MI355X.
-Agentic serving at scale: ~100K total tok/s per GPU on the AgentX coding-agent trace with 96 concurrent sessions.
-Speculative decoding: Supports MiniMax's DSpark draft and a DFlash2 draft trained by @radixark; supports HiCache and multimodal input.
-Ultra-low-latency inference: MegaKernels deliver 2.15× faster single-request decode.
5
5
341
58,397
MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token.
Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency.
Hugging Face:
huggingface.co/MiniMaxAI/Mini…
ModelScope:
modelscope.cn/models/MiniMax…
API: platform.minimax.io
M Plan: minimax.io/m-planMiniMax
MCode for desktop: agent.minimax.io/download
Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency.
Hugging Face:
huggingface.co/MiniMaxAI/Mini…
ModelScope:
modelscope.cn/models/MiniMax…
API: platform.minimax.io
M Plan: minimax.io/m-planMiniMax
MCode for desktop: agent.minimax.io/download
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 s 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
161
264
3,865
398,583
Thanks SGLang day 0 support.
x.com/sgl_project/st…
x.com/sgl_project/st…
Space Bunny is here! 🐰 MiniMax M3.1 Flash hits >1K tok/s, bs1 decode with SGLang, production-ready from Day 0. This integration is a joint effort by @MiniMax_AI, @NVIDIAAI, @AMD, and @radixark, and you can also run RL with Miles!
-Broad hardware support: NVIDIA Blackwell and Hop00), plus AMD Instinct MI350X and MI355X.
-Agentic serving at scale: ~100K total tok/s per GPU on the AgentX coding-agent trace with 96 concurrent sessions.
-Speculative decoding: Supports MiniMax's DSpark draft and a DFlash2 draft trained by @radixark; supports HiCache and multimodal input.
-Ultra-low-latency inference: MegaKernels deliver 2.15× faster single-request decode.
2
0
37
8,258
Thanks to the NVIDIA NeMo team for day-0 fine-tuning support for MiniMax-M3.1-Flash! 🐰
What magic will this 🐰 bring in the post train scenario?
What magic will this 🐰 bring in the post train scenario?
You’ve probably already used it: Space Bunny pushed 200T+ tokens before anyone knew it was MiniMax-M3.1-Flash. Now it’s open weights 🔥 Thank you @MiniMax_AI for open sourcing it!
Day-0 fine-tuning in NVIDIA NeMo-AutoModel
✅ FSDP2, expert, pipeline, and context parallelism, ✅scaling up to 128 GPUs, and the NVFP4 checkpoint loads directly.
github.com/NVIDIA-NeMo/Au…
4
7
381
61,867
Thanks Inferact Day 0 support!
x.com/inferact/statu…
x.com/inferact/statu…
Today, we are announcing a strategic partnership with @MiniMax_AI to advance frontier production inference for open-source models.
The Inferact Platform has served MiniMax M3.1 Flash in production since the day it launched. Requests through the MiniMax platform are routed to our stack alongside MiniMax’s own capacity, after we met MiniMax’s vendor verification requirements for accuracy and reliability.
The Inferact Platform serves this agentic workload with guaranteed SLAs and auto-tunes the endpoint against live traffic, while MiniMax keeps control of how its model is served.
Inferact also leads day-0 @vllm_project support for each MiniMax release, so the model serves at production quality the day the weights ship. The engineering from both efforts is upstreamed to vLLM.
Thanks to the MiniMax team for the partnership. Read the full announcement:
inferact.ai/news/minimax-p…
1
3
50
10,644
MiniMax (official) retweeted
The meter's off.
MiniMax M3.1 Flash is free on 0G Private Computer until Oct 24, 13:00 UTC.
No balance needed, just an API key.
Let your agent run with @MiniMax_AI
pc.0g.ai/models/minimax…
MiniMax M3.1 Flash is free on 0G Private Computer until Oct 24, 13:00 UTC.
No balance needed, just an API key.
Let your agent run with @MiniMax_AI
pc.0g.ai/models/minimax…
Save your longest agent run for Wednesday.
MiniMax M3.1 Flash goes free on 0G Private Computer for 3 days, from Oct 21, 13:00 UTC.
No balance needed, just an API key. Point your Hermes Agent at it.
pc.0g.ai/models/minimax…
3
14
58
15,793
MiniMax (official) retweeted
Congratulations to @MiniMax_AI on launching M3.1 Flash! 🎉 We're proud to be a launch partner from day one.
Faster, lighter, and built for volume. Whether you’re building, learning something new or just getting through the day, your Mind is a digital companion that grows with you and helps you unlock what you never thought was possible.
Try it out at hellominds.ai.
Faster, lighter, and built for volume. Whether you’re building, learning something new or just getting through the day, your Mind is a digital companion that grows with you and helps you unlock what you never thought was possible.
Try it out at hellominds.ai.
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 s 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
1
5
37
5,284
Great to have Inferact as an API launch partner for M3.1 Flash!
Thanks for bringing your vLLM expertise to the collaboration. Excited to keep building the serving infrastructure for complex agent workloads together.
Thanks for bringing your vLLM expertise to the collaboration. Excited to keep building the serving infrastructure for complex agent workloads together.
Inferact is an API launch partner for MiniMax M3.1 Flash! 🎉
We're working with @MiniMax_AI on production inference for its latest model, built for multi-step automation, real-codebase engineering and visual reasoning.
M3.1 Flash scored 29.6 on Agents’ Last Exam (ALE), alongside 72.5% on AutomationBench-AA and 73.67% on DeepSWE—capabilities that matter when agents need to plan work, use tools and carry tasks through.
Our contribution is the serving stack: bringing our vLLM engineering and the Inferact Platform to the collaboration.
Thanks to the MiniMax team for the partnership.
Explore the model and API integration:
platform.minimax.io/docs/guides/te…
11
4
468
67,311
Thank you for bringing H3 to TPUs! Excited to see more open-source work on efficient video inference and what it could enable: faster creative iteration, new interactive experiences, and more ways for developers to build with H3.
Today we launch SGLang-TorchTPU, built with @Google TPU team and Meta @PyTorch team.
We’re excited to see it powering production inference at Meta!
SGLang-TorchTPU is a TPU plugin for SGLang that brings:
- Top open models on TPU: Muse Spark Open, GLM-5.3 Flash, Kimi K3, Ling SGLang’s production features for large agentic workloads
- Custom MegaKernel: Muse Spark Open hits 770 tok/s decode at bs=1 on InferenceX 8K/1K
SGLang-TorchTPU is available now: github.com/sgl-project/sg…
9
4
425
62,825
MiniMax M3.1 Flash + SGLang Omni: building toward a more interactive generation of voice agents. The shift ahead is from “ask, wait, listen” to conversations people can interrupt, correct, and redirect as a task unfolds.
MiniMax M3.1 Flash brings intelligence and fast, concise adds streaming, conversation state, and interruption handling so users can redirect conversations in real time.
Together, they give developers a foundation to explore proactive tutors, support agents, and hands-free copilots - pairing Flash’s capabilities with infrastructure for continuous interaction.
Thanks to the SGLang Omni team for exploring this direction with M3.1 Flash! ✨
MiniMax M3.1 Flash brings intelligence and fast, concise adds streaming, conversation state, and interruption handling so users can redirect conversations in real time.
Together, they give developers a foundation to explore proactive tutors, support agents, and hands-free copilots - pairing Flash’s capabilities with infrastructure for continuous interaction.
Thanks to the SGLang Omni team for exploring this direction with M3.1 Flash! ✨
We just tried @MiniMax_AI's M3.1 Flash in our SGLang Omni cascaded voice interaction system, and the experience was genuinely impressive! 🐰🚀
Our original pipeline was Qwen3-ASR → Qwen3 LLM → Qwen3-TTS. We replaced the locally hosted LLM with the MiniMax M3.1 Flash API while pipeline unchanged, and recorded a demo to see how it performs in real conversations.
The results were excellent. M3.1 Flash responded incredibly fast, understood our questions well, and consistently delivered sharp, concise, and direct answers. The conversation felt remarkably smooth and natural.
One thing I increasingly appreciate about voice agents is that intelligence alone isn't enough. Unlike text, users can't easily skim an audio response. A model that understands what you need and gets straight to the point can make a huge difference to the overall interaction experience.
This is also what makes the modular architecture of SGLang Omni so exciting to me. We can swap individual components, connect local speech models with frontier LLM APIs, and immediately explore how different models change the end-to-end interaction experience.
Huge congrats to the MiniMax team! Really impressive work, and we're excited to explore more together. 🔥
22
18
559
69,768