OpenAI Image Generator

Official Generate images from text prompts using OpenAI's GPT Image model.

What this tool does: Creates images from text descriptions using OpenAI's GPT Image model (gpt-image-1). Supports multiple sizes and quality levels. Images are uploaded to artifact storage and displayed inline in chat. Runs in a secure sandbox.

Setup

Get an OpenAI API key

Go to https://platform.openai.com/api-keys
Create a new API key
Ensure you have credits on your OpenAI account

Add workspace secret

Go to Settings > Integrations and create a new secret:

Secret Name	Description
`OPENAI_API_KEY`	Your OpenAI API key

This is a sandbox tool and OpenAI image generation has its own costs. Each execution uses workspace credits plus OpenAI's API charges.

Parameters

Parameter	Required	Description
`prompt`	Yes	Text description of the image to generate
`size`	No	`1024x1024` (default), `1536x1024` (landscape), `1024x1536` (portrait)
`quality`	No	`auto` (default), `low`, `medium`, `high`

Example Prompts

"Generate an image of a sunset over mountains in watercolor style"
"Create a logo concept for a coffee shop called 'Bean There'"
"Make a landscape image of a futuristic city at night"
"Generate a portrait-style illustration of a friendly robot"

Tool Definition

Input Parameters

sizestringImage size: '1024x1024' (default), '1536x1024' (landscape), '1024x1536' (portrait)

promptstringText description of the image to generate

qualitystringImage quality: 'auto' (default), 'low', 'medium', 'high'

Sandbox Configuration

Language: python

Timeout: 60s

Code

import json
import urllib.request
import urllib.error
import os
import base64

data = TOOL_INPUT
prompt = data.get('prompt', '')
size = data.get('size', '1024x1024')
quality = data.get('quality', 'auto')

if not prompt:
    print('Error: prompt is required')
else:
    api_key = os.environ.get('OPENAI_API_KEY', '')
    if not api_key:
        print('Error: OPENAI_API_KEY secret is required. Add it in Settings > Secrets.')
    else:
        try:
            url = 'https://api.openai.com/v1/images/generations'
            payload = json.dumps({
                'model': 'gpt-image-1',
                'prompt': prompt,
                'n': 1,
                'size': size,
                'quality': quality
            }).encode('utf-8')

            req = urllib.request.Request(url, data=payload, headers={
                'Authorization': f'Bearer {api_key}',
                'Content-Type': 'application/json'
            }, method='POST')
            with urllib.request.urlopen(req, timeout=50) as resp:
                result = json.loads(resp.read().decode('utf-8'))

            image = result['data'][0]
            image_b64 = image.get('b64_json', '')
            image_bytes = base64.b64decode(image_b64)

            artifact_key = upload_artifact(image_bytes, 'image/png')
            if artifact_key:
                print(json.dumps({
                    'artifact_key': artifact_key,
                    'contentType': 'image/png',
                    'revised_prompt': image.get('revised_prompt', ''),
                    'model': 'gpt-image-1',
                    'size': size
                }))
            else:
                print(json.dumps({
                    'message': 'Image generated but artifact storage unavailable.',
                    'revised_prompt': image.get('revised_prompt', ''),
                    'model': 'gpt-image-1',
                    'size': size
                }))
        except urllib.error.HTTPError as e:
            err_body = e.read().decode('utf-8') if e.fp else ''
            print(f'Error from OpenAI: {e.code} {err_body}')
        except Exception as e:
            print(f'Error: {e}')