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

# gemini

> Generate text using Google Gemini models (embedded, no API key required)

**Server path:** `/embedded-gemini` | **Type:** Embedded | **PCID required:** No

## Tools

| Tool                                                    | Description                              |
| ------------------------------------------------------- | ---------------------------------------- |
| [`embedded-gemini_generate`](#embedded-gemini_generate) | Generate text using Google Gemini models |

***

## embedded-gemini\_generate

Generate text using Google Gemini models

**Parameters:**

| Parameter      | Type      | Required | Default              | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
| -------------- | --------- | -------- | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model`        | string    | No       | `"gemini-2.5-flash"` | <br />Select the appropriate Gemini model:<br />- gemini-3.1-pro-preview: Gemini 3.1 Pro with multimodal support and large context (advanced reasoning, complex tasks)<br />- gemini-3-flash-preview: Gemini 3 Flash, fast and cost-efficient with multimodal support (fast, general tasks)<br />- gemini-2.5-pro: Enhanced thinking and reasoning, multimodal understanding, advanced coding (advanced reasoning, coding)<br />- gemini-2.5-flash: Cost efficiency (fast, general tasks, supports higher token limits)<br /> |
| `systemPrompt` | string    | No       | —                    | System prompt to set behavior and context                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
| `userPrompt`   | string    | Yes      | —                    | User prompt containing the main request or conversation                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
| `fileUrls`     | string\[] | No       | —                    | Optional array of file URLs for multimodal analysis. Gemini supports Images (.jpg, .jpeg, .png, .webp), Videos (.mp4, .webm, .mkv, .mov), Documents (.pdf, .txt), Audio (.mp3, .wav, .webm, .m4a, .opus, .aac, .flac). Always include file URLs when analyzing specific files.                                                                                                                                                                                                                                                |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "model": {
        "type": "string",
        "enum": [
          "gemini-3.1-pro-preview",
          "gemini-3-flash-preview",
          "gemini-2.5-pro",
          "gemini-2.5-flash"
        ],
        "description": "\n    Select the appropriate Gemini model:\n    - gemini-3.1-pro-preview: Gemini 3.1 Pro with multimodal support and large context (advanced reasoning, complex tasks)\n    - gemini-3-flash-preview: Gemini 3 Flash, fast and cost-efficient with multimodal support (fast, general tasks)\n    - gemini-2.5-pro: Enhanced thinking and reasoning, multimodal understanding, advanced coding (advanced reasoning, coding)\n    - gemini-2.5-flash: Cost efficiency (fast, general tasks, supports higher token limits)\n  ",
        "default": "gemini-2.5-flash"
      },
      "systemPrompt": {
        "type": "string",
        "description": "System prompt to set behavior and context"
      },
      "userPrompt": {
        "type": "string",
        "description": "User prompt containing the main request or conversation"
      },
      "fileUrls": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Optional array of file URLs for multimodal analysis. Gemini supports Images (.jpg, .jpeg, .png, .webp), Videos (.mp4, .webm, .mkv, .mov), Documents (.pdf, .txt), Audio (.mp3, .wav, .webm, .m4a, .opus, .aac, .flac). Always include file URLs when analyzing specific files."
      }
    },
    "required": [
      "userPrompt"
    ]
  }
  ```
</Expandable>