Skip to main content
Method: client.generate_image().

​
Example

image = client.generate_image({
    "model": "openai/gpt-image-1",
    "prompt": "A lighthouse at golden hour",
    "size": "1024x1024",
    "n": 1,
    "response_format": "url",
})

​
Key parameters

  • model (required): Image-capable model id (e.g., openai/gpt-image-1).
  • prompt (required): Text prompt.
  • n (1–10): Number of images to generate.
  • size: e.g., 1024x1024, 1024x1792, 1792x1024.
  • quality: standard or hd (model-dependent).
  • style: e.g., vivid or natural (model-dependent).
  • response_format: url or b64_json.
  • user: Optional end-user tag for safety/abuse tracking.

​
Returns

ImageGenerationResponse 
{
  "data": [
    {
      "url": "https://example.com/generated_image.png"
    }
  ]
}