GPT Image 2

Text-to-Image • OpenAI • Proxied

OpenAI's next-generation image model that creates and edits images from text prompts, with support for multiple quality levels, sizes, and output formats. Note: transparent backgrounds are not supported — use openai/gpt-image-1.5 for transparent PNGs.

Model Info
Terms and License	link ↗
More information	link ↗
Pricing	View pricing in the Cloudflare dashboard ↗

Usage

const response = await env.AI.run(
  'openai/gpt-image-2',
  {
    prompt: 'A golden retriever puppy playing in autumn leaves',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Response 200 Simple Generation

Examples

High Quality — Generate a high-quality detailed image

const response = await env.AI.run(
  'openai/gpt-image-2',
  {
    prompt:
      'A detailed botanical illustration of exotic tropical flowers with fine line work and watercolor textures',
    quality: 'high',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Response 200 High Quality

Custom Size — Generate a portrait-oriented image

const response = await env.AI.run(
  'openai/gpt-image-2',
  {
    prompt:
      'A towering redwood forest with sunbeams filtering through the canopy, misty atmosphere',
    size: '1024x1536',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Response 200 Custom Size

WebP Output — Generate an image in WebP format for smaller file size

const response = await env.AI.run(
  'openai/gpt-image-2',
  {
    prompt:
      'A neon-lit cyberpunk cityscape at night with rain-slicked streets and holographic billboards',
    quality: 'high',
    output_format: 'webp',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Response 200 WebP Output

Image Edit — Edit an existing image by providing it as base64 (a raw string or a data:image/{png|jpeg|webp};base64,... URI). This routes the call to OpenAI's /v1/images/edits endpoint. The example uses a tiny 32x32 smiley-face PNG - real inputs are the full base64 encoding of your source image.

const response = await env.AI.run(
  'openai/gpt-image-2',
  {
    prompt:
      'Transform this cartoon smiley into a photorealistic 3D clay sculpture sitting on a marble pedestal, studio lighting',
    image:
      'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Response 200 Image Edit

prompt

stringrequiredText prompt describing the image to generate or edit

image

stringBase64-encoded input image for image editing

quality

stringenum: low, medium, high, autoQuality of the generated image

size

stringenum: 1024x1024, 1024x1536, 1536x1024, autoSize of the generated image

background

stringenum: transparent, opaque, autoBackground transparency setting. Use transparent for images with no background, opaque for a solid background, or auto to let the model decide.

output_format

stringenum: png, webp, jpegOutput format for the generated image

image

stringformat: uriURL to the generated image

API Schemas

Input
Output

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "prompt": {
      "description": "Text prompt describing the image to generate or edit",
      "type": "string"
    },
    "image": {
      "description": "Base64-encoded input image for image editing",
      "type": "string"
    },
    "quality": {
      "description": "Quality of the generated image",
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high",
        "auto"
      ]
    },
    "size": {
      "description": "Size of the generated image",
      "type": "string",
      "enum": [
        "1024x1024",
        "1024x1536",
        "1536x1024",
        "auto"
      ]
    },
    "background": {
      "description": "Background transparency setting. Use transparent for images with no background, opaque for a solid background, or auto to let the model decide.",
      "type": "string",
      "enum": [
        "transparent",
        "opaque",
        "auto"
      ]
    },
    "output_format": {
      "description": "Output format for the generated image",
      "type": "string",
      "enum": [
        "png",
        "webp",
        "jpeg"
      ]
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "image": {
      "description": "URL to the generated image",
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "image"
  ],
  "additionalProperties": false
}