MiMo V2.5

mimo-v2.5 · Xiaomi

This model will be retired on 2026-10-21. Plan to migrate to mimo-v2.6-flash.
Calls still work until then. All model retirements

MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can see, hear, and read, and translate understanding into action. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M context length. Built on a powerful model base, we continuously scale compute across broader agent scenarios, further expanding the agent’s action space and achieving an important generalization from coding to claw.

API Pricing

Input$0.155 / 1M tokens
Output$0.31 / 1M tokens
Cache read$0.0031 / 1M tokens

Specifications

Context1.05M tokens
Modalitiestext, image, video, audio
CapabilitiesThinking, Streaming, Tool calling, Web search, Structured outputs, Prompt caching

Frequently asked questions

What is MiMo V2.5?

MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can see, hear, and read, and translate understanding into action. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M context length. Built on a powerful model base, we continuously scale compute across broader agent scenarios, further expanding the agent’s action space and achieving an important generalization from coding to claw.

What is the context length of MiMo V2.5?

MiMo V2.5 has a 1,048,576 token context window.

How much does MiMo V2.5 cost?

On AIHubMix, MiMo V2.5 costs $0.155 per million input tokens and $0.31 per million output tokens. Cached input reads are billed at $0.0031 per million tokens.

What modalities does MiMo V2.5 support?

MiMo V2.5 accepts text, image, video and audio input.

What capabilities does MiMo V2.5 support?

MiMo V2.5 supports web search. Per-protocol parameter support is listed in the capability table on this page.

How do I call MiMo V2.5 via API?

MiMo V2.5 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-v2.5 — no other code changes needed.

Who created MiMo V2.5?

MiMo V2.5 is developed by Xiaomi. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was MiMo V2.5 released?

MiMo V2.5 was released on April 22, 2026 by Xiaomi.

More models from Xiaomi

See all Xiaomi models →

MiMo V2.6 Flash

by Xiaomi

mimo-v2.6-flash is Xiaomi's latest model series. A fully multimodal, highly intelligent…

$0.155/1M in · $0.31/1M out
1,048,576 tokens context

MiMo V2.6 Pro

by Xiaomi

MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning…

$0.48/1M in · $0.96/1M out
1,048,576 tokens context

MiMo V2.6 Pro Ultraspeed

by Xiaomi

MiMo-V2.6-Pro-UltraSpeed combines the flagship performance of MiMo-V2.6-Pro and offers up…

$4.8/1M in · $9.6/1M out
1,048,576 tokens context

Xiaomi Mimo V2.6 Pro (free)

by Xiaomi

xiaomi-mimo-v2.6-pro-free is the open free version of xiaomi-mimo-v2.6-pro. To maintain…

1,048,576 tokens context

Xiaomi Mimo V2.6 Flash (free)

by Xiaomi

xiaomi-mimo-v2.6-flash-free is the open free version of xiaomi-mimo-v2.6-flash. To…

1,048,576 tokens context

Coding Xiaomi Mimo V2.6 Flash

by Xiaomi

Only supports OpenAI-compatible formats.

$0.08/1M in · $0.16/1M out
1,048,576 tokens context

Use MiMo V2.5 via the AIHubMix unified API — one interface for every major LLM.