kite-3.1-20m
Released by qikp in 2026, kite-3.1-20m is an chat model. kite-3.1-20m is an open-weights chat model.
by qikp
Best for
Ways to use kite-3.1-20m in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your qikp API key. osFoundry discovers kite-3.1-20m 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.
Deploy a dedicated endpoint
kite-3.1-20m is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
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.
kite-3.1-20m vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about kite-3.1-20m
Is kite-3.1-20m free to use?
kite-3.1-20m is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use kite-3.1-20m commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run kite-3.1-20m locally?
Yes. kite-3.1-20m is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is kite-3.1-20m best at?
kite-3.1-20m is well-suited to text generation.
How do I use kite-3.1-20m in osFoundry?
Paste your qikp API key in the key dialog (or deploy the open weights for self-hostable models), assign kite-3.1-20m to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by qikp on April 19, 2026. Source: https://huggingface.co/qikp/kite-3.1-20m