Pinned Tweet
Fastest MiMo-V2.6-Pro endpoint on Artificial Analysis.
407 tok/s at 10K input. 9x Xiaomi's own API.
5.6s to first token vs 47.2s.
$0.87 per 1M output tokens.
Try it today.
407 tok/s at 10K input. 9x Xiaomi's own API.
5.6s to first token vs 47.2s.
$0.87 per 1M output tokens.
Try it today.
3
1
118
887,552
Big smiles, one balloon, great week at @WeAreDevs 🎈
The PrimaLabs team came to meet developers building with open models, and we had a reason to celebrate: #1 on @ArtificialAnlys for MiMo.
Thanks to everyone who stopped by!
The PrimaLabs team came to meet developers building with open models, and we had a reason to celebrate: #1 on @ArtificialAnlys for MiMo.
Thanks to everyone who stopped by!
0
0
1
39
Congrats to the @XiaomiMiMo team on MiMo-V2.6-Pro. We serve it at 407 tok/s, the fastest endpoint on Artificial Analysis.
artificialanalysis.ai/models/mimo-v2…
primalabs.ai/blog/mimo-v2-6…
artificialanalysis.ai/models/mimo-v2…
primalabs.ai/blog/mimo-v2-6…
Introducing Xiaomi MiMo-V2.6 — Pro & Flash.
Frontier intelligence, all the modalities, built in public.
🔹 Two omnimodal models, advancing through scaled reinforcement learning
🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks
🔹 Pro scores 46 ois Intelligence Index — the highest among open-source models
🔹 Stronger coding, computer use, 3D reasoning and creative capabilities
🔹 Open model weights, technical report, RL environments and training code
Blog：mimo.xiaomi.com/mimo-v2-6
0
0
0
89
PrimaLabs retweeted
Hey @OpenRouter team - is there any plan to bring #PrimaLabs to OR ? They are claiming to be best in speed for MiMo model at regular price point.
3
1
5
265