flextok_d18_d28_dfn
EPFL-VILAB's flextok_d18_d28_dfn is a chat model. flextok_d18_d28_dfn is an open-weights chat model.
by EPFL-VILAB
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use flextok_d18_d28_dfn in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your EPFL-VILAB API key. osFoundry discovers flextok_d18_d28_dfn 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
flextok_d18_d28_dfn 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.
flextok_d18_d28_dfn vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| flextok_d18_d28_dfn | EPFL-VILAB | — | — | Free (local) | Yes |
| rus_cyrl_5mb | goldfish-models | — | — | Free (local) | Yes |
| EVE-Instruct | eve-esa | — | — | Free (local) | Yes |
| talkie-box | N8Programs | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about flextok_d18_d28_dfn
Is flextok_d18_d28_dfn free to use?
flextok_d18_d28_dfn 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 flextok_d18_d28_dfn 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 flextok_d18_d28_dfn locally?
Yes. flextok_d18_d28_dfn is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is flextok_d18_d28_dfn best at?
flextok_d18_d28_dfn is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use flextok_d18_d28_dfn in osFoundry?
Paste your EPFL-VILAB API key in the key dialog (or deploy the open weights for self-hostable models), assign flextok_d18_d28_dfn to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by EPFL-VILAB on March 19, 2025. Source: https://huggingface.co/EPFL-VILAB/flextok_d18_d28_dfn