Trinity Large Preview
Arcee AI's Trinity Large Preview is a chat model. Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing,...
by Arcee AI · 131K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Trinity Large Preview in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Arcee AI API key. osFoundry discovers Trinity Large 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.
Run Trinity Large Preview yourself
Trinity Large Preview 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.
Trinity Large Preview vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Trinity Large Preview | Arcee AI | — | 131K | $ 0.150 /1M | API only |
| Step 3.5 Flash | StepFun | — | 262K | $ 0.100 /1M | API only |
| Solar Pro 3 | Upstage | — | 128K | $ 0.150 /1M | API only |
| Qwen3 Coder Next | Qwen | — | 262K | $ 0.110 /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 Trinity Large Preview
How much does Trinity Large Preview cost?
Trinity Large Preview is metered at $ 0.150 /1M for input, and $ 0.450 /1M for output. Bring your own Arcee AI API key — osFoundry passes through provider pricing without markup.
Can I use Trinity Large 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 Trinity Large Preview?
Trinity Large Preview supports a 131K token context window.
Can I run Trinity Large Preview locally?
No — Trinity Large Preview is hosted only and accessed via the Arcee AI API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Trinity Large Preview best at?
Trinity Large Preview is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Trinity Large Preview in osFoundry?
Paste your Arcee AI API key in the key dialog (or deploy the open weights for self-hostable models), assign Trinity Large Preview to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Arcee AI on January 27, 2026. Source: https://openrouter.ai/arcee-ai/trinity-large-preview