# Hy4 preview

> Hy4 preview is an open-weight language model from Tencent (Hunyuan), released on 28 Aug 2026. It accepts text and generates text, with a 1M-token context window and up to 64K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.75 per million input tokens and $2.25 per million output tokens (OpenRouter), across 4 providers we track.

Source page: https://www.aimodel.directory/models/hy4-preview
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Tencent (Hunyuan)
- **Release date:** 28 Aug 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/tencent/Hy4-preview)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/tencent/Hy4-preview)
- **Parameters:** 780B (source: Hugging Face, https://huggingface.co/tencent/Hy4-preview)
- **Context window:** 1M (1,048,576 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Max output:** 64K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy4-preview.toml)
- **Hugging Face:** tencent/Hy4-preview (source: Hugging Face, https://huggingface.co/tencent/Hy4-preview)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.75 | $2.25 | $0.04 | 1M |
| DeepInfra | $0.83 | $2.50 | $0.04 | 1M |
| Hugging Face Inference Providers | $0.83 | $2.50 | – | 1M |
| Vercel AI Gateway | $0.83 | $2.50 | $0.04 | 1M |

## FAQ

### What is the context window of Hy4 preview?

Hy4 preview has a context window of 1,048,576 tokens (1M) and can generate up to 64,000 tokens in a single response, according to models.dev.

### How much does the Hy4 preview API cost?

Hy4 preview is listed from $0.75 per million input tokens and $2.25 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is Hy4 preview open source?

Hy4 preview is an open-weight model: its weights are published on Hugging Face as tencent/Hy4-preview under the apache-2.0 license. Check the license terms before commercial use.

### When was Hy4 preview released?

Tencent (Hunyuan) released Hy4 preview on 28 Aug 2026, according to models.dev.

### Which providers offer Hy4 preview?

We track Hy4 preview on 4 providers: OpenRouter, DeepInfra, Hugging Face Inference Providers, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Hy4 preview", https://www.aimodel.directory/models/hy4-preview