Hy3 preview
Tencent's Hy3 preview is a chat model. Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
by Tencent · 262K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Hy3 preview in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Tencent API key. osFoundry discovers Hy3 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 Hy3 preview yourself
Hy3 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.
Hy3 preview vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Hy3 preview | Tencent | — | 262K | $ 0.066 /1M | API only |
| Ling-2.6-1T | inclusionAI | — | 262K | $ 0.300 /1M | API only |
| MiMo-V2.5-Pro | Xiaomi | — | 1049K | $ 1.00 /1M | API only |
| DeepSeek V4 Flash | DeepSeek | — | 1049K | $ 0.126 /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 Hy3 preview
How much does Hy3 preview cost?
Hy3 preview is metered at $ 0.066 /1M for input, and $ 0.260 /1M for output. Bring your own Tencent API key — osFoundry passes through provider pricing without markup.
Can I use Hy3 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 Hy3 preview?
Hy3 preview supports a 262K token context window.
Can I run Hy3 preview locally?
No — Hy3 preview is hosted only and accessed via the Tencent API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Hy3 preview best at?
Hy3 preview is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Hy3 preview in osFoundry?
Paste your Tencent API key in the key dialog (or deploy the open weights for self-hostable models), assign Hy3 preview to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Tencent on April 22, 2026. Source: https://openrouter.ai/tencent/hy3-preview