R1 0528
R1 0528 (DeepSeek, 2025) is an chat model. May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
by DeepSeek · 164K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use R1 0528 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your DeepSeek API key. osFoundry discovers R1 0528 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 R1 0528 yourself
R1 0528 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.
R1 0528 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| R1 0528 | DeepSeek | — | 164K | $ 0.500 /1M | API only |
| Grok 3 | xAI | — | 131K | $ 3.00 /1M | API only |
| Gemma 3n 4B | Google | — | 33K | $ 0.060 /1M | API only |
| Maestro Reasoning | Arcee AI | — | 131K | $ 0.900 /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 R1 0528
How much does R1 0528 cost?
R1 0528 is metered at $ 0.500 /1M for input, and $ 2.15 /1M for output. Bring your own DeepSeek API key — osFoundry passes through provider pricing without markup.
Can I use R1 0528 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 R1 0528?
R1 0528 supports a 164K token context window.
Can I run R1 0528 locally?
No — R1 0528 is hosted only and accessed via the DeepSeek API. An open-weights equivalent is available to self-host — see the cross-link above.
What is R1 0528 best at?
R1 0528 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use R1 0528 in osFoundry?
Paste your DeepSeek API key in the key dialog (or deploy the open weights for self-hostable models), assign R1 0528 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by DeepSeek on May 28, 2025. Source: https://openrouter.ai/deepseek/deepseek-r1-0528