LFM2.5-1.2B-Thinking (free)
LFM2.5-1.2B-Thinking (free) (LiquidAI, 2026) is an chat model. LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
by LiquidAI · 33K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use LFM2.5-1.2B-Thinking (free) in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your LiquidAI API key. osFoundry discovers LFM2.5-1.2B-Thinking (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 LFM2.5-1.2B-Thinking (free) yourself
LFM2.5-1.2B-Thinking (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.
LFM2.5-1.2B-Thinking (free) vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| LFM2.5-1.2B-Thinking (free) | LiquidAI | — | 33K | Free | API only |
| Palmyra X5 | Writer | — | 1040K | $ 0.600 /1M | API only |
| MiniMax M2-her | MiniMax | — | 66K | $ 0.300 /1M | API only |
| GLM 4.7 Flash | Z.ai | — | 203K | $ 0.060 /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 LFM2.5-1.2B-Thinking (free)
How much does LFM2.5-1.2B-Thinking (free) cost?
LFM2.5-1.2B-Thinking (free) is metered at Free for input, and Free for output. Bring your own LiquidAI API key — osFoundry passes through provider pricing without markup.
Can I use LFM2.5-1.2B-Thinking (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 LFM2.5-1.2B-Thinking (free)?
LFM2.5-1.2B-Thinking (free) supports a 33K token context window.
Can I run LFM2.5-1.2B-Thinking (free) locally?
No — LFM2.5-1.2B-Thinking (free) is hosted only and accessed via the LiquidAI API. An open-weights equivalent is available to self-host — see the cross-link above.
What is LFM2.5-1.2B-Thinking (free) best at?
LFM2.5-1.2B-Thinking (free) is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use LFM2.5-1.2B-Thinking (free) in osFoundry?
Paste your LiquidAI API key in the key dialog (or deploy the open weights for self-hostable models), assign LFM2.5-1.2B-Thinking (free) to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by LiquidAI on January 20, 2026. Source: https://openrouter.ai/liquid/lfm-2.5-1.2b-thinking:free