# Hy3

> Hy3 is an open-weight language model from Tencent (Hunyuan), released on 6 Jul 2026. It accepts text and generates text, with a 262K-token context window and up to 128K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.08 per million input tokens and $0.33 per million output tokens (OpenRouter), across 5 providers we track.

Source page: https://www.aimodel.directory/models/hy3
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Tencent (Hunyuan)
- **Release date:** 6 Jul 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/tencent/Hy3)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/tencent/Hy3)
- **Parameters:** 299B (source: Hugging Face, https://huggingface.co/tencent/Hy3)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Max output:** 128K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/tencent/Hy3.toml)
- **Hugging Face:** tencent/Hy3 (source: Hugging Face, https://huggingface.co/tencent/Hy3)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.08 | $0.33 | $0.02 | 262K |
| DeepInfra | $0.13 | $0.53 | $0.03 | 262K |
| SiliconFlow | $0.13 | $0.53 | $0.03 | 262K |
| Hugging Face Inference Providers | $0.14 | $0.58 | – | 262K |
| Vercel AI Gateway | $0.14 | $0.58 | $0.04 | 262K |

## FAQ

### What is the context window of Hy3?

Hy3 has a context window of 262,144 tokens (262K) and can generate up to 128,000 tokens in a single response, according to models.dev.

### How much does the Hy3 API cost?

Hy3 is listed from $0.08 per million input tokens and $0.33 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is Hy3 open source?

Hy3 is an open-weight model: its weights are published on Hugging Face as tencent/Hy3 under the apache-2.0 license. Check the license terms before commercial use.

### When was Hy3 released?

Tencent (Hunyuan) released Hy3 on 6 Jul 2026, according to models.dev.

### Which providers offer Hy3?

We track Hy3 on 5 providers: OpenRouter, DeepInfra, SiliconFlow, Hugging Face Inference Providers, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Hy3", https://www.aimodel.directory/models/hy3