MiMo-V2-Flash ¶

Tier 1: 7 points · 1,000 tokens (500 input + 500 output)

Pricing¶

Website Pricing¶

Type	Cost
Input Text	4 points/1k tokens
Output (Text)	$0.30/1M tokens · 10 points/1k tokens

All parsed rates (both currencies):

Service	Currency	Amount	Per
Input (text)	USD	0.10	1000000 tokens
Input (text)	POINTS	4	1000 tokens
Output (text)	USD	0.30	1000000 tokens
Output (text)	POINTS	10	1000 tokens

Last Checked: 2026-10-22 13:08:00.286538

Bot Information¶

Creator: @novitaai

Description: Try https://poe.com/MiMo-V2.6-Flash-Xiaomi for the first-party MiMo bot.

Xiaomi MiMo-V2-Flash is a proprietary MoE model developed by Xiaomi, designed for extreme inference efficiency with 309B total parameters (15B active). By incorporating an innovative Hybrid attention architecture and multi-layer MTP inference acceleration, it ranks among the top 2 global open-source models across multiple Agent benchmarks. Its coding capabilities surpass all open-source models and rival the industry-leading closed-source model, Claude 4.5 Sonnet—yet at only 2.5% of the inference cost and with 2x the generation speed, successfully pushing the limits of both model performance and efficiency.

Context window: 262k tokens

This bot supports optional parameters for additional customization.

Extra: Powered by a server managed by @novitaai. Learn more

Architecture¶

Input Modalities: Unknown

Output Modalities: Unknown

Modality: unknown

Technical Details¶

Model ID: MiMo-V2-Flash

Object Type: bot

Created: Unknown

Owned By: novitaai

Root: MiMo-V2-Flash

API Last Updated: Not listed in API