Xiaomi's open-weights omnimodal model, a 309B-total, 15B-active mixture-of-experts. It is the small sibling of MiMo V2.6 Pro and replaces MiMo V2.5, adding audio and video input on a 1M window.
Pick it if
you want the cheapest 1M-window model with image, video and audio input
you run high-volume agent or coding loops where cached prefixes dominate the bill
you want MIT-licensed weights you can self-host
Skip it if
you need the strongest MiMo results on security and exploit benchmarks; Pro scores higher there
Xiaomi's flagship open-weights omnimodal model, a 1.02T-total, 42B-active mixture-of-experts with a 1M window. It replaces the text-only MiMo V2.5 Pro and adds image, video and audio input.
Pick it if
you want Xiaomi's strongest model for agent, coding and computer-use work
you need image, video or audio input on a 1M window
you want MIT-licensed weights you can self-host
Skip it if
you only need Flash-level quality; Flash scores close to Pro on most maker-reported rows at a third of the price
FAQ
Which is better, MiMo V2.6 Flash or MiMo V2.6 Pro?
On DeepSWE v1.1, as each maker reports it, MiMo V2.6 Flash scores 67.9 and MiMo V2.6 Pro 71.9. These are each maker's own numbers, not a controlled head-to-head; the spec table lists every benchmark both publish.
Which is cheaper, MiMo V2.6 Flash or MiMo V2.6 Pro?
MiMo V2.6 Flash lists lower input and output prices. On a coding-agent session (2M tokens in, 60,000 out) MiMo V2.6 Flash costs $0.30 and MiMo V2.6 Pro $0.92.
Can I switch between MiMo V2.6 Flash and MiMo V2.6 Pro mid-task?
Yes. In an Octomind session, /model octohub:mimo-v2.6-flash and /model octohub:mimo-v2.6-pro switch models without losing the conversation, so you can draft on one and review on the other.
Try either model
Switch between models inside the same Octomind session.