Cogito v2.1 671B
Built by Deep Cogito, Cogito v2.1 671B is an chat model with a 128K token context window. Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...
by Deep Cogito · 128K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Cogito v2.1 671B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Deep Cogito API key. osFoundry discovers Cogito v2.1 671B 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.
Cogito v2.1 671B vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Cogito v2.1 671B | Deep Cogito | — | 128K | $ 1.25 /1M | API only |
| Olmo 3 32B Think | AllenAI | — | 66K | $ 0.150 /1M | API only |
| Kimi K2 Thinking | MoonshotAI | — | 262K | $ 0.600 /1M | API only |
| INTELLECT-3 | Prime Intellect | — | 131K | $ 0.200 /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 Cogito v2.1 671B
How much does Cogito v2.1 671B cost?
Cogito v2.1 671B is metered at $ 1.25 /1M for input, and $ 1.25 /1M for output. Bring your own Deep Cogito API key — osFoundry passes through provider pricing without markup.
Can I use Cogito v2.1 671B 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 Cogito v2.1 671B?
Cogito v2.1 671B supports a 128K token context window.
Can I run Cogito v2.1 671B locally?
No — Cogito v2.1 671B is hosted only and accessed via the Deep Cogito API.
What is Cogito v2.1 671B best at?
Cogito v2.1 671B is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Cogito v2.1 671B in osFoundry?
Paste your Deep Cogito API key in the key dialog (or deploy the open weights for self-hostable models), assign Cogito v2.1 671B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Deep Cogito on November 13, 2025. Source: https://openrouter.ai/deepcogito/cogito-v2.1-671b