MODEL PROFILE

Hy4 preview

腾讯 · hy4-preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Text generationreasoningstructured_outputstools
Context window1,048,576 Token
Input → OutputText → Text
Model weightsOpen weights
Profile updated2026/11/7 08:59:37
OVERVIEW

Model overview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Mixture-of-experts architecture with 49B active parameters selected from 770B total parameters
  • Optimized for coding agents, complex tool-use workflows, and productivity tasks
  • Supports structured outputs and reasoning-intensive workloads

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · tencent/hy4-preview ↗USD 0.7506USD 2.2509Per million tokens2026/11/2 06:25:22
OpenRouter · tencent/hy4-preview · 阶梯定价
[
  {
    "utc_start": 0,
    "utc_end": 1600,
    "prompt": "0.000000834",
    "completion": "0.000002501",
    "input_cache_read": "0.000000042"
  },
  {
    "utc_start": 1600,
    "utc_end": 0,
    "prompt": "0.0000007506",
    "completion": "0.0000022509",
    "input_cache_read": "0.0000000378"
  }
]

Some channels offer cache discounts. Check the source for cache read, write and additional fees.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

What is the parameter count of Hy4 preview?

Hy4 preview has 49 billion active parameters out of a total of 770 billion parameters.

Which tasks is Hy4 preview specifically designed for?

It is designed for coding agents, complex tool-use workflows, and productivity tasks.

Where can I find official model documentation or weights?

Official resources are available on OpenRouter (https://openrouter.ai/tencent/hy4-preview) and Hugging Face (https://huggingface.co/tencent/Hy4-preview).

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。