MiMo V2 Flash

mimo-v2-flash · Xiaomi

MiMo-V2-Flash is a mixture of experts (MoE) language model with a total of 309 billion parameters and 15 billion activated parameters. It is designed for high-speed inference and proxy workflows, adopting a novel hybrid attention architecture and multi-token prediction (MTP), significantly reducing inference costs while achieving state-of-the-art performance.

API Pricing

Input$0.192 / 1M tokens
Output$0.575 / 1M tokens
Cache read$0.038 / 1M tokens

Specifications

Modalitiestext
Featuresweb search

Frequently asked questions

What is MiMo V2 Flash?

MiMo-V2-Flash is a mixture of experts (MoE) language model with a total of 309 billion parameters and 15 billion activated parameters. It is designed for high-speed inference and proxy workflows, adopting a novel hybrid attention architecture and multi-token prediction (MTP), significantly reducing inference costs while achieving state-of-the-art performance.

How much does MiMo V2 Flash cost?

On AIHubMix, MiMo V2 Flash costs $0.192 per million input tokens and $0.575 per million output tokens. Cached input reads are billed at $0.038 per million tokens.

What modalities does MiMo V2 Flash support?

MiMo V2 Flash accepts text input.

What capabilities does MiMo V2 Flash support?

MiMo V2 Flash supports web search. Per-protocol parameter support is listed in the capability table on this page.

How do I call MiMo V2 Flash via API?

MiMo V2 Flash is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to mimo-v2-flash — no other code changes needed.

Who created MiMo V2 Flash?

MiMo V2 Flash is developed by Xiaomi. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

Free version: MiMo V2 Flash (free)

More models from Xiaomi

See all Xiaomi models →

Xiaomi Mimo V2.5

by Xiaomi

MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can…

$0.155/1M in · $0.31/1M out
256,000 tokens context

Xiaomi Mimo V2.5 Pro

by Xiaomi

MiMo-V2.5-Pro is Xiaomi's most powerful model to date. In areas such as general agent…

$0.48/1M in · $0.96/1M out
1,000,000 tokens context

Coding Xiaomi Mimo V2.5

by Xiaomi

Only supports OpenAI-compatible formats.

$0.08/1M in · $0.16/1M out

Coding Xiaomi Mimo V2.5 Pro

by Xiaomi

Only supports OpenAI-compatible formats.

$0.2/1M in · $0.4/1M out

Coding Xiaomi Mimo V2 Omni

by Xiaomi

Only supports OpenAI-compatible formats.

$0.08/1M in · $0.4/1M out

Coding Xiaomi Mimo V2 Pro

by Xiaomi

Only supports OpenAI-compatible formats.

$0.2/1M in · $0.6/1M out

Use MiMo V2 Flash via the AIHubMix unified API — one interface for every major LLM.