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
@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
Oct 23, 2026 · 3:18 AM UTC
9
9
112
16,116
@FireworksAI_HQ @MiniMax_AI Strong benchmarks at that price.
0
0
0
29
@FireworksAI_HQ @MiniMax_AI 62.8 on automationbench from a flash model is solid
0
0
0
45
@FireworksAI_HQ @MiniMax_AI We actually broke down how MSA and DSpark work together to hit those agentic benchmarks and the cost efficiency you mentioned. x.com/AGTPinsights/s…
MiniMax just released the open weights for M3.1 Flash today. Here's what you need to know.
The model teased earlier as Space Bunny is now downloadable. MiniMax says it has 428B parameters in total, with 23B activated per token. Weights are on Hugging Face and ModelScope. It d video input, with a 1M-token context window. Space Bunny topped global leaderboards with 200T+ tokens, and MiniMax says it was an earlier version of M3.1 Flash.
MiniMax says it is a generational leap in agentic tasks, coding and cybersecurity. It also says efficiency comes from MiniMax Sparse Attention and DSpark speculative decoding. Earlier it claimed nearly 3x faster online inference and 70% lower agentic cost than M3. The earlier free launch period on OpenRouter ended Oct 22.
Day-0 support landed across the stack. Together AI, Fireworks, vLLM, SGLang, Tenstorrent and Inferact all went live at release. SGLang reports over 1K tokens per second at batch size 1 decode. NVIDIA says Vera Rubin ran it at up to 200K TPS per GPU. Inco AI open-sourced a DFlash 2 drafter under Apache 2.0, which it says makes generation up to 3.5x faster, and lossless. MiniMax also announced a partnership with Inferact to improve production inference, with engineering work going back to vLLM.
Community reaction centers on two points. One observer says M3.1 Flash is essentially M3 with attention sparsified in 3 more layers, quantized, and DSpark added on top. Others say MiniMax got permission to open source it under new Chinese rules after the Oct 16 AI export restrictions, with DeepSeek getting approval for V4.1F-1017 too.
Key numbers:
- 428B total parameters, 23B active per token
- 76.2 on BankerToolBench
- 73.7% on DeepSWE v1.1
- 61.7 on OSWorld V2
- 29.6 on Agents' Last Exam
- 82.2 on CyberGym
- 62.8 on AutomationBench-AA, per Fireworks
- OpenRouter price of $0.10 input and $0.50 output per 1M tokens, with $0.005 cached input
The official post had about 97K views a few hours after it went up.
0
0
0
88
@FireworksAI_HQ @MiniMax_AI Day-0 on three platforms at once is honestly absurd turnaround. I remember when open releases took weeks to show up on inference providers. My judgment: launch-day serving is becoming table stakes.
0
0
0
92
@FireworksAI_HQ @MiniMax_AI Keep it and delete all the other opensource Models like kimi k3
0
0
0
38
@FireworksAI_HQ @MiniMax_AI and why couldn't you send an otp on an indonesian number?
0
0
0
9