Image Generation

Generate images from text prompts using the OpenAI-compatible Images API.

What you’ll learn:

How to generate images from text prompts
How to decode and save generated images
Available image generation models

Basic Usage

Python
curl

import base64
from openai import OpenAI

client = OpenAI()

prompt = """
A background with server racks and cables, with a futuristic city skyline
visible through a large window at sunrise. The room has blue and green LED
lights illuminating the equipment.
"""

result = client.images.generate(
    model="gpt-image-1",
    prompt=prompt,
)

# Decode and save the image
image_bytes = base64.b64decode(result.data[0].b64_json)
with open("generated_image.png", "wb") as f:
    f.write(image_bytes)

print("Image saved to generated_image.png")

curl -X POST "$OPENAI_BASE_URL/images/generations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-1",
    "prompt": "A futuristic data center at sunrise with blue LED lights"
  }'

Available Models

Model	Provider	Description
`gpt-image-1`	Azure	OpenAI’s image generation model

Next Steps

Multimodal — Analyze images with vision models
Asynchronous Requests — Queue image generation for batch processing
API Endpoints — Full endpoint reference