MiniMax M2.5
Released by MiniMax in 2026, MiniMax M2.5 is an chat model. MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
by MiniMax · 197K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use MiniMax M2.5 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your MiniMax API key. osFoundry discovers MiniMax M2.5 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 MiniMax M2.5 yourself
MiniMax M2.5 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.
MiniMax M2.5 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| MiniMax M2.5 | MiniMax | — | 197K | $ 0.150 /1M | API only |
| GLM 5 | Z.ai | — | 203K | $ 0.600 /1M | API only |
| Aion-2.0 | AionLabs | — | 131K | $ 0.800 /1M | API only |
| Qwen3 Max Thinking | Qwen | — | 262K | $ 0.780 /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 MiniMax M2.5
How much does MiniMax M2.5 cost?
MiniMax M2.5 is metered at $ 0.150 /1M for input, and $ 1.15 /1M for output. Bring your own MiniMax API key — osFoundry passes through provider pricing without markup.
Can I use MiniMax M2.5 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 MiniMax M2.5?
MiniMax M2.5 supports a 197K token context window.
Can I run MiniMax M2.5 locally?
No — MiniMax M2.5 is hosted only and accessed via the MiniMax API. An open-weights equivalent is available to self-host — see the cross-link above.
What is MiniMax M2.5 best at?
MiniMax M2.5 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use MiniMax M2.5 in osFoundry?
Paste your MiniMax API key in the key dialog (or deploy the open weights for self-hostable models), assign MiniMax M2.5 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by MiniMax on February 12, 2026. Source: https://openrouter.ai/minimax/minimax-m2.5