MiMo-V2-Flash (Reasoning)

by Xiaomi

MiMo-V2-Flash (Reasoning) is a reasoning model from Xiaomi, released on December 16, 2025. It has a 256K-token context window and can generate up to 16K output tokens. API pricing is $0.1 per 1M input tokens and $0.3 per 1M output tokens.

MiMo-V2-Flash is a powerful, efficient, and ultra-fast foundation language model that excels in reasoning, coding, and agentic scenarios. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, featuring a hybrid attention architecture with sliding-window and full attention (5:1 ratio, 128-token window). Delivers 150 tokens/sec inference with 256k context window.

Key specs

ProviderXiaomi
Release date2025-12-16
Licenseopen source
Context window256K tokens
Max output16K tokens
Input price$0.1 / 1M tokens
Output price$0.3 / 1M tokens
Intelligence Score30.6
Coding index17.3

Quick answers

What is the context window of MiMo-V2-Flash (Reasoning)?

MiMo-V2-Flash (Reasoning) has a context window of 256K tokens, with a maximum output of 16K tokens per response.

How much does MiMo-V2-Flash (Reasoning) cost?

MiMo-V2-Flash (Reasoning) costs $0.1 per 1M input tokens and $0.3 per 1M output tokens through the API.

Is MiMo-V2-Flash (Reasoning) open source?

Yes. MiMo-V2-Flash (Reasoning) is an open model released under the open source license.

When was MiMo-V2-Flash (Reasoning) released?

Xiaomi released MiMo-V2-Flash (Reasoning) on December 16, 2025.

Compare on the AI leaderboard · All AI models

More models from Xiaomi