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

# Image Generation

> AI SDK compatible image generation endpoint with streaming support

## Request Body

<ParamField body="prompt" type="string" required>
  Text prompt describing the image to generate
</ParamField>

<ParamField body="model" type="string" default="google/gemini-2.5-flash-image">
  Image model identifier
</ParamField>

<ParamField body="provider" type="string">
  Provider name (e.g., OpenAI, Google)
</ParamField>

<ParamField body="n" type="number" default="1">
  Number of images to generate
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  Enable streaming response
</ParamField>

## Response

<ResponseField name="data" type="array">
  Array of generated images

  <Expandable title="image properties">
    <ResponseField name="url" type="string">
      URL of the generated image
    </ResponseField>

    <ResponseField name="b64_json" type="string">
      Base64-encoded image data
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="created" type="number">
  Unix timestamp of creation
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.yourapp.com/api/ai/image/generation \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "prompt": "A futuristic city at sunset with flying cars",
      "model": "dall-e-3",
      "n": 1,
      "stream": false
    }'
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch('https://api.yourapp.com/api/ai/image/generation', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <token>',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      prompt: 'A futuristic city at sunset with flying cars',
      model: 'dall-e-3',
      n: 1,
      stream: false
    })
  });

  const data = await response.json();
  ```

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

  url = "https://api.yourapp.com/api/ai/image/generation"
  headers = {
      "Authorization": "Bearer <token>",
      "Content-Type": "application/json"
  }
  payload = {
      "prompt": "A futuristic city at sunset with flying cars",
      "model": "dall-e-3",
      "n": 1,
      "stream": False
  }

  response = requests.post(url, json=payload, headers=headers)
  data = response.json()
  ```
</RequestExample>

<ResponseExample>
  ```json Success Response theme={null}
  {
    "created": 1677652288,
    "data": [
      {
        "url": "https://cdn.example.com/images/generated/abc123.png",
        "b64_json": null
      }
    ]
  }
  ```

  ```json Success Response (Base64) theme={null}
  {
    "created": 1677652288,
    "data": [
      {
        "url": null,
        "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg=="
      }
    ]
  }
  ```

  ```json Streaming Response theme={null}
  data: {"type":"chunk","image":"data:image/png;base64,iVBORw0KG..."}

  data: {"type":"chunk","image":"data:image/png;base64,goAAAAN..."}

  data: {"type":"done","image":"data:image/png;base64,SUhEUgAA..."}
  ```

  ```json Error Response theme={null}
  {
    "success": false,
    "message": "Unauthorized"
  }
  ```
</ResponseExample>