# Google Gemini

Generate text responses with Google's Gemini models. Provide a text prompt and, optionally, one or more images, audio clips, videos, or files as multimodal context.

## Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `prompt` | Text input to the model. Include detailed instructions, questions, or context. | STRING | Yes |  |
| `model` | The Gemini model used to generate the response. | COMBO | Yes | `"Gemini 3.1 Pro"`<br>`"Gemini 3.1 Flash-Lite"` |
| `seed` | Seed for sampling. Set to 0 for a random seed. Deterministic output isn't guaranteed. (default: 42) | INT | Yes | 0 to 2147483647 |
| `system_prompt` | Foundational instructions that dictate the model's behavior. (default: "") | STRING | No |  |

**Note:** When providing images, audio, or video as multimodal context, the node uploads media as URLs for the first 10 inputs. Any additional media is sent inline as base64 data, with a maximum inline payload of 18 MB. If the inline payload exceeds this limit, an error is raised.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `output` | The generated text response from the Gemini 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/GeminiNodeV2/en.md)

---
**Source fingerprint (SHA-256):** `ec9921f218a726082eb8987cf94b3575f61a3c6cf55fb33aeb81d42fad35d302`