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

# Chat

> Generate a text response with a Google Gemini model.

The Google Gemini **Chat** action sends one prompt and an optional system
instruction to a Gemini model. It returns the model's response as text.

## Inputs

| Input                   | Type                         | Required | Description                                                                                                |
| ----------------------- | ---------------------------- | -------- | ---------------------------------------------------------------------------------------------------------- |
| **Third-party account** | Google Generative AI account | Yes      | The API key used for the request.                                                                          |
| **Prompt**              | String                       | Yes      | The user request sent to Gemini.                                                                           |
| **Model**               | Enum                         | Yes      | Gemini 2.5 Pro, 2.5 Flash, 2.0 Flash, 2.0 Flash Lite, 1.5 Pro, or 1.5 Flash. Defaults to Gemini 2.5 Flash. |
| **Temperature**         | Number                       | No       | Response randomness from `0` to `2`. Defaults to `1`.                                                      |
| **System Prompt**       | String                       | No       | Instructions that define role, style, or constraints.                                                      |

## Output

| Output       | Type   | Description                      |
| ------------ | ------ | -------------------------------- |
| **Response** | String | Gemini's complete text response. |

<Note>
  This action is stateless and text-only. Include all required context in the
  current prompt, and use a separate action when you need image generation.
</Note>