# New Model Available: Hy4

> Source: <https://zenmux.ai/tencent/hy4>
> Published: 2026-11-04 06:39:44+00:00

Hy4 Preview is Tencent’s flagship open-source large language model, featuring a 1M-token context window and strong gains in long-horizon software engineering, document-intensive office work, game development, and scientific research. Designed for productivity-focused workflows, it is optimized to understand complex multi-file context, reason through difficult tasks, and generate high-quality outputs across coding, analysis, and research scenarios.

[Back to Models](https://zenmux.ai/models)

## Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

**$0.834**

*/ M tokens*

**$2.501**

*/ M tokens*

*Read:*

**0.042**/ M tokens

*Write:*

**-**/ M tokens1.05M--

## Uptime

24hours
Direct request success rate on AI Gateway and per-provider.

## Throughput

24hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

## Latency

24hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

## Activity

Token volume and request traffic to this model over time.

## Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced from[Artificial Analysis](https://artificialanalysis.ai/)

## Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. [View All](https://zenmux.ai/analytics/apps)

## Related Models

More models from [Tencent](https://zenmux.ai/tencent)