---
title: "Hy3"
route_path: "/model/hy3"
canonical_url: "https://www.pipellm.ai/model/hy3"
markdown_path: "/llms/models/hy3.md"
markdown_url: "https://www.pipellm.ai/llms/models/hy3.md"
content_type: "model-detail-page"
description: "Machine-readable detail page for Hy3."
generated_at: "2026-09-05T13:15:30.704Z"
---
Canonical page: https://www.pipellm.ai/model/hy3
Markdown mirror: https://www.pipellm.ai/llms/models/hy3.md
Content type: model-detail-page
Generated at: 2026-09-05T13:15:30.704Z
# Hy3
## Query Intents
- Understand pricing, provider availability, context window, and capabilities for Hy3.
- Compare Hy3 against other models available through PipeLLM.
- Find the canonical model identifier to use in SDK or API requests.
## Overview
Hy3 is Tencent's mixture-of-experts model for reasoning, software development, and agent workflows. It is designed to follow instructions across extended conversations and maintain the constraints needed for complex, multi-step work.

Its text-based capabilities suit coding assistance, document analysis, and productivity applications. Configurable reasoning allows applications to choose between direct responses and more deliberate problem solving.
## Model Metadata
- Display name: Hy3
- Model ID: hy3
- Provider family: Tencent
- Release date: Unknown
- Context window: 256K
- Max output: 128K
- Input modalities: text
- Output modalities: text
- Tool use support: Yes
- Computer use support: No
- Cache control support: No
## Official Pricing (per 1M tokens)
| Metric | <=200K Context | >200K Context |
| --- | --- | --- |
| Input Price | $0.15 | — |
| Output Price | $0.59 | — |
| Cache Read | $0.04 | — |
| Image Input | $0 | — |
| Image Output | $0 | — |

## Provider Availability
| Provider | Region | Context Window | Max Output | Input Price | Output Price | Cache Read | Cache Write |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Tokenhub | — | 256K | 128K | $0.15 | $0.59 | $0.04 | — |