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

# Gemini 2.0 Flash

> Call Google Gemini 2.0 Flash via Gemini API for AI image editing.

Gemini 2.0 Flash is Google's multimodal model with image editing capabilities, available through Starrise AI via the native Gemini API. It can edit existing images based on text instructions.

## Key Capabilities

* **Image editing** — Modify existing images using natural language instructions
* **Multimodal input** — Accepts both text instructions and source images
* **Text generation** — Also supports standard text generation tasks
* **Efficient and flexible** — Suitable for a variety of multimodal tasks

## Quick Example

<CodeGroup>
  ```bash cURL theme={null}
  curl "https://ai.alad.com/v1beta/models/gemini-2.0-flash:generateContent?key=YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "contents": [
        {
          "role": "user",
          "parts": [
            { "text": "Replace the background with a beach scene" },
            { "inline_data": { "mime_type": "image/png", "data": "BASE64_DATA" } }
          ]
        }
      ],
      "generationConfig": {
        "responseModalities": ["IMAGE"]
      }
    }'
  ```

  ```python Python theme={null}
  import requests
  import base64

  url = "https://ai.alad.com/v1beta/models/gemini-2.0-flash:generateContent"
  params = {"key": "YOUR_API_KEY"}

  with open("input.png", "rb") as f:
      image_b64 = base64.b64encode(f.read()).decode()

  data = {
      "contents": [
          {
              "role": "user",
              "parts": [
                  {"text": "Replace the background with a beach scene"},
                  {"inline_data": {"mime_type": "image/png", "data": image_b64}}
              ]
          }
      ],
      "generationConfig": {
          "responseModalities": ["IMAGE"]
      }
  }

  response = requests.post(url, params=params, json=data)
  result = response.json()
  output = result["candidates"][0]["content"]["parts"][0]["inline_data"]["data"]
  with open("output.png", "wb") as f:
      f.write(base64.b64decode(output))
  ```
</CodeGroup>

## Parameters

| Parameter                             | Type   | Required | Description                                           |
| ------------------------------------- | ------ | -------- | ----------------------------------------------------- |
| `key`                                 | string | Yes      | API key (query parameter)                             |
| `contents`                            | array  | Yes      | Array of `{ role, parts }` with text and inline\_data |
| `generationConfig.responseModalities` | array  | Yes      | Must include `IMAGE`                                  |

<Card title="API Reference" icon="code" href="/en/api-reference/model-api/google/gemini-2-0-flash">
  View the interactive API Playground for Gemini 2.0 Flash.
</Card>