Hy4 Preview — Tencent Hunyuan 4 Model

Hy4 Preview (Tencent Hunyuan 4, 腾讯混元Hy4) is Tencent's next-generation Mixture-of-Experts flagship model — the successor to Hy3, built for complex reasoning, coding, and agentic tasks.

770Btotal params (49B active)
78layers
256routed experts / layer
1Mcontext window
$0.834per 1M input
Try Hy4 Now — Free →

Model ID: tencent/hy4-preview · Available via OpenAI-compatible API

What is Hy4 Preview?

Announced by Tencent in its Q2 2026 earnings call and now in grey-testing, Hy4 is positioned as an "expert-level" model above Hy3 — with larger parameters, stronger reinforcement learning, and upgraded multimodal capabilities. It serves as the core engine of Tencent's WorkBuddy agent application. According to the official research page, Hy4 Preview is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team.

Hy4 Architecture (Official Specs)

The model comprises 770B total parameters, of which 49B are activated per token. Its backbone consists of 78 layers:

In addition to the backbone, 1 native MTP layer (Multi-Token Prediction, 10B total parameters, 0.7B activated) is built in for speculative decoding — accelerating inference by predicting multiple tokens ahead.

Architecture DetailValue
Total / Active parameters770B / 49B per token
Backbone layers78
Layer 1Dense FFN
Layers 2–78MoE (256 routed + 1 shared expert each)
Activated experts per tokenTop-8 routed + shared
MTP layer1 native (10B / 0.7B active), speculative decoding

Model Specifications

SpecificationValue
ArchitectureMixture-of-Experts (MoE)
Total / Active parameters770B / 49B
Backbone78 layers (1 dense + 77 MoE)
Context window1,048,576 tokens
Maximum output64,000 tokens
Input price$0.834 / 1M tokens
Output price$2.501 / 1M tokens
ProviderTencent Hy Team
Official research pagehy.tencent.ai/research/hy4-preview

Hy4 Preview vs. Other Flagship Models

Hy4 targets complex reasoning, coding, and agent scenarios — competing directly with DeepSeek, Kimi, and GPT-class frontier models. Full benchmark comparison on our Hy4 vs DeepSeek page.

ModelTypePositioning
Hy4 PreviewTencent Hunyuan expert MoEComplex reasoning / coding / agents
Hy3 PreviewTencent Hunyuan MoEGeneral-purpose
DeepSeek V-seriesMoEReasoning / coding
Kimi / GPT-classMoE / denseGeneral assistant

How to Access the Hy4 API

Hy4 Preview is currently served as a hosted API — the model ID is tencent/hy4-preview on OpenRouter. It is OpenAI-compatible, so you can call it through any gateway that supports the OpenAI API format. Create a free account at tokenra.io/register to start calling the model right away. See API docs for examples.

Backbone78 layers (1 dense FFN + 77 MoE) Context window1,048,576 tokens Maximum output64,000 tokens Input price$0.834 / 1M tokens Output price$2.501 / 1M tokens DeveloperTencent Hy Team

Hy4 Preview vs. Other Flagship Models

Hy4 targets complex reasoning, coding, and agent scenarios — competing directly with DeepSeek, Kimi, and GPT-class frontier models. Full benchmark comparison on our Hy4 vs DeepSeek page.

ModelTypePositioning
Hy4 PreviewTencent Hunyuan expert MoEComplex reasoning / coding / agents
Hy3 PreviewTencent Hunyuan MoEGeneral-purpose open-source
DeepSeek V-seriesMoEReasoning / coding
Kimi / GPT-classMoE / denseGeneral assistant

How to Access the Hy4 API

Hy4 Preview is currently served as a hosted API — the model ID is tencent/hy4-preview on OpenRouter. It is OpenAI-compatible, so you can call it through any gateway that supports the OpenAI API format. You can create a free account at tokenra.io/register to start calling the model right away. See API docs for examples.

Frequently Asked Questions

What is Hy4 Preview?

Hy4 Preview is Tencent Hunyuan's next-generation Mixture-of-Experts flagship model and the successor to Hy3. It has 770B total parameters with 49B activated per token, a 1,048,576 token context window, and a maximum output of 64,000 tokens.

What architecture does Hy4 use?

Hy4 uses a Mixture-of-Experts architecture with a 78-layer backbone. The first layer is a standard dense FFN; the remaining 77 layers each contain 256 routed experts plus 1 shared expert, with every token activating the top-8 routed experts along with the shared expert. A native MTP layer (10B total parameters, 0.7B activated) is built in for speculative decoding.

How do I access the Hy4 API?

Hy4 Preview is available through OpenAI-compatible API gateways. You can create a free account at tokenra.io/register to start calling the tencent/hy4-preview model ID.

Is Hy4 open source?

Tencent has publicly documented Hy4's architecture on the official research page and HuggingFace. The release is currently served as a hosted API (model ID tencent/hy4-preview on OpenRouter). For the latest weight availability and license, check the official HuggingFace repository.

How much does Hy4 cost?

On OpenRouter, Hy4 Preview is priced at $0.834 per 1M input tokens and $2.501 per 1M output tokens, with a 1,048,576 token context window.

What is the Hy4 context window?

Hy4 Preview supports a 1,048,576 token context window with a maximum output of 64,000 tokens.