MiMo V2 Flash

xiaomi

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Top open-source coding agent

Swe-bench-level software engineering

Budget reasoning and coding with tools

Technical Specifications

Context Window

262,144 tokens

Max Output

32,768 tokens

Cache Miss Cost

$0.09 per 1M tokens

Non-Reasoning Cost

$0.29 per 1M tokens

Cache Read Cost

$0.045 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus