Inflection 3 Pi
Inflection 3 Pi is a chat model from Inflection, released October 11, 2024. Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...
by Inflection · 8K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Inflection 3 Pi in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Inflection API key. osFoundry discovers Inflection 3 Pi 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.
Inflection 3 Pi vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Inflection 3 Pi | Inflection | — | 8K | $ 2.50 /1M | API only |
| Qwen2.5 7B Instruct | Qwen | — | 33K | $ 0.040 /1M | API only |
| Magnum v4 72B | anthracite-org | — | 16K | $ 3.00 /1M | API only |
| Rocinante 12B | TheDrummer | — | 33K | $ 0.170 /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 Inflection 3 Pi
How much does Inflection 3 Pi cost?
Inflection 3 Pi is metered at $ 2.50 /1M for input, and $ 10.00 /1M for output. Bring your own Inflection API key — osFoundry passes through provider pricing without markup.
Can I use Inflection 3 Pi 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 Inflection 3 Pi?
Inflection 3 Pi supports a 8K token context window.
Can I run Inflection 3 Pi locally?
No — Inflection 3 Pi is hosted only and accessed via the Inflection API.
What is Inflection 3 Pi best at?
Inflection 3 Pi is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Inflection 3 Pi in osFoundry?
Paste your Inflection API key in the key dialog (or deploy the open weights for self-hostable models), assign Inflection 3 Pi to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Inflection on October 11, 2024. Source: https://openrouter.ai/inflection/inflection-3-pi