Aion-RP 1.0 (8B)
Aion-RP 1.0 (8B) is a chat model from AionLabs, released February 4, 2025. Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
by AionLabs · 33K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Aion-RP 1.0 (8B) in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your AionLabs API key. osFoundry discovers Aion-RP 1.0 (8B) 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.
Aion-RP 1.0 (8B) vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Aion-RP 1.0 (8B) | AionLabs | — | 33K | $ 0.800 /1M | API only |
| Qwen-Plus | Qwen | — | 1000K | $ 0.260 /1M | API only |
| o3 Mini | OpenAI | — | 200K | $ 1.10 /1M | API only |
| Mistral Small 3 | Mistral | — | 33K | $ 0.050 /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 Aion-RP 1.0 (8B)
How much does Aion-RP 1.0 (8B) cost?
Aion-RP 1.0 (8B) is metered at $ 0.800 /1M for input, and $ 1.60 /1M for output. Bring your own AionLabs API key — osFoundry passes through provider pricing without markup.
Can I use Aion-RP 1.0 (8B) 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 Aion-RP 1.0 (8B)?
Aion-RP 1.0 (8B) supports a 33K token context window.
Can I run Aion-RP 1.0 (8B) locally?
No — Aion-RP 1.0 (8B) is hosted only and accessed via the AionLabs API.
What is Aion-RP 1.0 (8B) best at?
Aion-RP 1.0 (8B) is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Aion-RP 1.0 (8B) in osFoundry?
Paste your AionLabs API key in the key dialog (or deploy the open weights for self-hostable models), assign Aion-RP 1.0 (8B) to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by AionLabs on February 4, 2025. Source: https://openrouter.ai/aion-labs/aion-rp-llama-3.1-8b