MiniMax M2.5 (free)
MiniMax's MiniMax M2.5 (free) is a 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 (free) in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your MiniMax API key. osFoundry discovers MiniMax M2.5 (free) 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 (free) yourself
MiniMax M2.5 (free) 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 (free) vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| MiniMax M2.5 (free) | MiniMax | — | 197K | Free | API only |
| Aion-2.0 | AionLabs | — | 131K | $ 0.800 /1M | API only |
| LFM2-24B-A2B | LiquidAI | — | 33K | $ 0.030 /1M | API only |
| GLM 5 | Z.ai | — | 203K | $ 0.600 /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 (free)
How much does MiniMax M2.5 (free) cost?
MiniMax M2.5 (free) is metered at Free for input, and Free for output. Bring your own MiniMax API key — osFoundry passes through provider pricing without markup.
Can I use MiniMax M2.5 (free) 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 (free)?
MiniMax M2.5 (free) supports a 197K token context window.
Can I run MiniMax M2.5 (free) locally?
No — MiniMax M2.5 (free) 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 (free) best at?
MiniMax M2.5 (free) is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use MiniMax M2.5 (free) in osFoundry?
Paste your MiniMax API key in the key dialog (or deploy the open weights for self-hostable models), assign MiniMax M2.5 (free) 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:free