o1
o1 is a image-generation model from OpenAI, released December 17, 2024. The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...
by OpenAI · 200K token context window
Best for
- image generation from text
- creative design and ideation
Ways to use o1 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OpenAI API key. osFoundry discovers o1 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.
o1 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| o1 | OpenAI | — | 200K | $ 15.00 /1M | API only |
| MiniMax-01 | MiniMax | — | 1000K | $ 0.200 /1M | API only |
| Nova Lite 1.0 | Amazon | — | 300K | $ 0.060 /1M | API only |
| Sonar | Perplexity | — | 127K | $ 1.00 /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 o1
How much does o1 cost?
o1 is metered at $ 15.00 /1M for input, and $ 60.00 /1M for output. Bring your own OpenAI API key — osFoundry passes through provider pricing without markup.
Can I use o1 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 o1?
o1 supports a 200K token context window.
Can I run o1 locally?
No — o1 is hosted only and accessed via the OpenAI API.
What is o1 best at?
o1 is well-suited to image generation from text, creative design and ideation.
How do I use o1 in osFoundry?
Paste your OpenAI API key in the key dialog (or deploy the open weights for self-hostable models), assign o1 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by OpenAI on December 17, 2024. Source: https://openrouter.ai/openai/o1