Roar AI
DiscordGet started
All models
Xiaomi · Open weights

MiMo-V2.5-Pro

Xiaomi’s open coding model, built to keep going through a thousand tool calls.

MiMo-V2.5-Pro is not on our public price list right now. Ask us if your team needs it.

Specs

Made byXiaomi
ReleasedApril 2026
TypeChat
Context window1M tokens
ReadsText
Thinks before answeringNot stated by the maker
WeightsOpen (MIT)
Size1.02T total, 42B active
Processed inGlobal
Model idmimo-v2.5-pro

About MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship, a trillion-parameter model made for long, autonomous software work. Xiaomi’s showcase had it build a compiler in Rust over 4.3 hours and 672 tool calls, passing all 233 tests. It is also sparing with words: Xiaomi says it uses 40–60% fewer tokens than comparable frontier models to reach similar results.

It reads text only (the image and audio model is MiMo-V2.5), and its weights are open under MIT. Xiaomi reports 57.2% on SWE-bench Pro.

What is MiMo-V2.5-Pro good for?

  • Long-running autonomous coding sessions.
  • Agent work on a tight token budget.
  • Complex, multi-step software engineering.

MiMo-V2.5-Pro limitations

  • Text only.
  • Xiaomi’s leads are self-reported, and reviewers caution that such leads have not always held up in everyday use.
  • Xiaomi has not said how its reasoning can be controlled.

How to use the MiMo-V2.5-Pro API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="mimo-v2.5-pro",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

MiMo-V2.5-Pro FAQ

Can I use MiMo-V2.5-Pro alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from MiMo-V2.5-Pro to another model only means changing the model name in your code.

Is MiMo-V2.5-Pro open source?

Its weights are open under the MIT licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

What is the context window of MiMo-V2.5-Pro?

MiMo-V2.5-Pro can read up to 1M tokens in one request.

Can MiMo-V2.5-Pro read images and PDFs?

It reads text only. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge. Scanned pages need a model that can see images.

Start using MiMo-V2.5-Pro

Create a free account, get an API key and call MiMo-V2.5-Pro with the OpenAI SDK.