2 Xiaomi models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.
MiMo-V2.6-Flash is Xiaomi's efficiency-balanced sparse MoE model (309B total, 15B active), natively omnimodal across text, image, video and audio with a 1M-token context window, built for long-horizon coding, tool use and computer use.
xiaomi/mimo-v2.6-flashSep 21, 2026+1MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse MoE model (1.02T total, 42B active), natively omnimodal with a 1M-token context window, built for long-horizon coding and multi-tool agents.
xiaomi/mimo-v2.6-proSep 21, 2026+1Model scores sourced from ArtificialAnalysis