Granite 4.1 8B
Granite 4.1 8B is a chat model from IBM, released April 30, 2026. Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
by IBM · 131K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Granite 4.1 8B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your IBM API key. osFoundry discovers Granite 4.1 8B 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 Granite 4.1 8B yourself
Granite 4.1 8B 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.
Granite 4.1 8B vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Granite 4.1 8B | IBM | — | 131K | $ 0.050 /1M | API only |
| CoBuddy (free) | Baidu Qianfan | — | 131K | Free | API only |
| Owl Alpha | openrouter | — | 1049K | Free | API only |
| Ring-2.6-1T (free) | inclusionAI | — | 262K | Free | 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 Granite 4.1 8B
How much does Granite 4.1 8B cost?
Granite 4.1 8B is metered at $ 0.050 /1M for input, and $ 0.100 /1M for output. Bring your own IBM API key — osFoundry passes through provider pricing without markup.
Can I use Granite 4.1 8B 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 Granite 4.1 8B?
Granite 4.1 8B supports a 131K token context window.
Can I run Granite 4.1 8B locally?
No — Granite 4.1 8B is hosted only and accessed via the IBM API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Granite 4.1 8B best at?
Granite 4.1 8B is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Granite 4.1 8B in osFoundry?
Paste your IBM API key in the key dialog (or deploy the open weights for self-hostable models), assign Granite 4.1 8B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by IBM on April 30, 2026. Source: https://openrouter.ai/ibm-granite/granite-4.1-8b