the first open-weights model from Reflection, a 501B-total, 23B-active mixture-of-experts built for agentic tool use, coding and general reasoning. it reads text only and its weights ship under Apache 2.0.
pick it if
you want a long-window text model priced with the flash tier
you want Apache 2.0 weights, with BF16, FP8 and NVFP4 builds to self-host
you run tool-calling agents on text and repeat long prompts, so cached input matters
skip it if
you need image, audio or video input; Beam reads text only
long autonomous coding is the job; its reported DeepSWE v1.1 score sits below GLM-5.3 Flash and DeepSeek V4.1 Flash
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
faq
which is better, Beam or MiMo V2.6 Flash?
on Terminal Bench 2.1, as each maker reports it, Beam scores 80.1% and MiMo V2.6 Flash 87.6. these are each maker's own numbers, not a controlled head-to-head; the spec table lists every benchmark both publish.
which is cheaper, Beam or MiMo V2.6 Flash?
Beam lists the lower input price, while MiMo V2.6 Flash lists the lower output price. on a coding-agent session (2M tokens in, 60,000 out) Beam costs $0.27 and MiMo V2.6 Flash $0.30.
which one accepts images?
MiMo V2.6 Flash supports vision; Beam does not.
can i switch between Beam and MiMo V2.6 Flash mid-task?
yes. in an octomind session, /model octohub:beam and /model octohub:mimo-v2.6-flash 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.