GPT-4o Search Preview
Released by OpenAI in 2025, GPT-4o Search Preview is an chat model. GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
by OpenAI · 128K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use GPT-4o Search Preview in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OpenAI API key. osFoundry discovers GPT-4o Search Preview 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.
GPT-4o Search Preview vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| GPT-4o Search Preview | OpenAI | — | 128K | $ 2.50 /1M | API only |
| Reka Flash 3 | rekaai | — | 66K | $ 0.100 /1M | API only |
| Command A | Cohere | — | 256K | $ 2.50 /1M | API only |
| Skyfall 36B V2 | TheDrummer | — | 33K | $ 0.550 /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 GPT-4o Search Preview
How much does GPT-4o Search Preview cost?
GPT-4o Search Preview is metered at $ 2.50 /1M for input, and $ 10.00 /1M for output. Bring your own OpenAI API key — osFoundry passes through provider pricing without markup.
Can I use GPT-4o Search Preview 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 GPT-4o Search Preview?
GPT-4o Search Preview supports a 128K token context window.
Can I run GPT-4o Search Preview locally?
No — GPT-4o Search Preview is hosted only and accessed via the OpenAI API.
What is GPT-4o Search Preview best at?
GPT-4o Search Preview is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use GPT-4o Search Preview in osFoundry?
Paste your OpenAI API key in the key dialog (or deploy the open weights for self-hostable models), assign GPT-4o Search Preview 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 March 12, 2025. Source: https://openrouter.ai/openai/gpt-4o-search-preview