> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# TencentHyNode - ComfyUI Built-in Node Documentation

> This node generates text responses with Tencent's Hy4 model.

This node generates text responses with Tencent's Hy4 model. It sends a text prompt, plus optionally one or more images as context, and returns the model's answer as text.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| - | - | - | - | - |
| `model` | The model used to generate the answer. Selecting it reveals its inputs below. Default: `"Hy4"`. | DYNAMIC\_COMBO | Yes | `"Hy4"` |

### Hy4 Inputs

These inputs appear when `model` is set to `"Hy4"`.

| Parameter | Description | Data Type | Required | Range |
| - | - | - | - | - |
| `prompt` | The message to send to the model. Must not be empty. Default: "" (empty string). | STRING | Yes | At least 1 character |
| `images` | Up to 20 images. Each image in a batch counts. Default: no images. | AUTOGROW | No | 0 to 20 images |
| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default: 42. | INT | Yes | 0 to 2147483647 |
| `system_prompt` | Foundational instructions that dictate the model's behavior. Default: "" (empty string). | STRING | No | - |
| `reasoning` | The model thinks before answering. Answers take longer and use more tokens, and very hard tasks can time out. Default: False. | BOOLEAN | Yes | true false |
| `temperature` | Controls randomness. Results still vary at 0. Default: 1.0. | FLOAT | Yes | 0.0 to 1.4 (step: 0.01) |
| `max_tokens` | Maximum number of tokens to generate, including reasoning tokens when `reasoning` is on. Very long answers can time out. Default: 32000. | INT | Yes | 1 to 64000 |

**Constraints:**

* At most 20 images are accepted per request, counting each image of a batch.
* Tencent's content filter can block a request, which raises an error.
* If `max_tokens` runs out before the answer finishes, the node raises an error: raise `max_tokens` or turn `reasoning` off.

## Outputs

| Output Name | Description | Data Type |
| - | - | - |
| `STRING` | The text answer from the Hy4 model. | STRING |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentHyNode/en.md)

***

**Source fingerprint (SHA-256):** `c7c1d2908d2fba8172fa279b7d273f5f3f96cf10b531f81650824fc8e0176f21`


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.