Xiaomi: MiMo-V2.6-Flash

XIAOMI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1430Chatbot Arena Verified

Max Context Limit1,050,000Max Out: 131,072 tokens

Prompt Caching98% OFF$0.0028 / 1M cached

Standard API / 1M$0.42Blended Standard Rate

Model Capabilities & Contract SLAs

Drafting
Classification
Coding & Logic
Fictional

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.14 / 1M

⚡ Cached Input (Prompt Cache Read)98% OFF$0.0028 / 1M

Output Tokens (Completion)$0.28 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs StepFun: Step 3.7 Flash VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs MiniMax: MiniMax M2.1 VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs Qwen: Qwen3 30B A3B Thinking 2507 VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs MoonshotAI: Kimi K2 0711 VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs TheDrummer: UnslopNemo 12B VS Engine MatchupXiaomi: MiMo-V2.6-Flash vs inclusionAI: Ling 3.0 Flash VL