Xiaomi's MiMo-V2.6 Model Family Goes Live on OpenRouter
- Source
- x.com
- Date
Xiaomi MiMo-V2.6 from @XiaomiMiMo is live on OpenRouter. Three new models. A 1T+ parameter flagship, an open-source MoE, and a ~10x faster variant of the flagship. All three take text, image, video, and audio with 1M context. More in the thread 🧵
Context
The same day Xiaomi's MiMo-V2.6 launched, OpenRouter added the family to its unified model API: a 1T+ parameter flagship, an open-source variant, and a roughly 10x faster version of the flagship. OpenRouter says all three accept text, image, video and audio input with a 1M- .
That gives a developer already calling other models through OpenRouter's API a way to add MiMo-V2.6 without a separate Xiaomi integration, and the faster flagship variant targets latency-sensitive use, such as interactive agents, where the standard flagship's response time would be a bottleneck. The tweet points to a longer thread for more detail not captured here, so specifics like per-variant pricing are not established by this post alone.
- mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…