MiMo-V2.5
Built by Xiaomi, MiMo-V2.5 is an image-generation model with a 1049K token context window. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
by Xiaomi · 1049K token context window
Best for
- image generation from text
- creative design and ideation
Ways to use MiMo-V2.5 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Xiaomi API key. osFoundry discovers MiMo-V2.5 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run MiMo-V2.5 yourself
MiMo-V2.5 is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
MiMo-V2.5 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| MiMo-V2.5 | Xiaomi | — | 1049K | $ 0.400 /1M | API only |
| GPT-5.5 | OpenAI | — | 1050K | $ 5.00 /1M | API only |
| Claude Opus Latest | Anthropic | — | 1000K | $ 5.00 /1M | API only |
| Qwen3.6 27B | Qwen | — | 262K | $ 0.320 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about MiMo-V2.5
How much does MiMo-V2.5 cost?
MiMo-V2.5 is metered at $ 0.400 /1M for input, and $ 2.00 /1M for output. Bring your own Xiaomi API key — osFoundry passes through provider pricing without markup.
Can I use MiMo-V2.5 commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of MiMo-V2.5?
MiMo-V2.5 supports a 1049K token context window.
Can I run MiMo-V2.5 locally?
No — MiMo-V2.5 is hosted only and accessed via the Xiaomi API. An open-weights equivalent is available to self-host — see the cross-link above.
What is MiMo-V2.5 best at?
MiMo-V2.5 is well-suited to image generation from text, creative design and ideation.
How do I use MiMo-V2.5 in osFoundry?
Paste your Xiaomi API key in the key dialog (or deploy the open weights for self-hostable models), assign MiMo-V2.5 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Xiaomi on April 22, 2026. Source: https://openrouter.ai/xiaomi/mimo-v2.5