Code beginner · 3 min read

How to generate images with DALL-E 3 in python

Q: How to generate images with DALL-E 3 in python

Use the OpenAI Python SDK with client.images.generate specifying model="dall-e-3" and a prompt to generate images with DALL-E 3.

Direct answer

Use the OpenAI Python SDK with client.images.generate specifying model="dall-e-3" and a prompt to generate images with DALL-E 3.

Setup

Install

bash

pip install openai

Env vars

OPENAI_API_KEY

Imports

python

import os
from openai import OpenAI

Examples

inA futuristic cityscape at sunset

outURL to generated image of a futuristic cityscape at sunset

inA cute golden retriever puppy playing in the snow

outURL to generated image of a golden retriever puppy in snow

inAn astronaut riding a horse on Mars

outURL to generated image of astronaut on horse on Mars

Integration steps

Install the OpenAI Python SDK and set your API key in the environment variable OPENAI_API_KEY
Import the OpenAI client and initialize it with your API key from os.environ
Call the images.generate method with model='dall-e-3' and provide a descriptive prompt
Specify the number of images and size if needed (e.g., 1024x1024)
Extract the image URL from the response's data array
Use or display the returned image URL as needed

Full code

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic cityscape at sunset",
    n=1,
    size="1024x1024"
)

image_url = response.data[0].url
print("Generated image URL:", image_url)

output

Generated image URL: https://openai-generated-images.s3.amazonaws.com/abc123def456.png

API trace

Request

json

{"model": "dall-e-3", "prompt": "A futuristic cityscape at sunset", "n": 1, "size": "1024x1024"}

Response

json

{"created": 1680000000, "data": [{"url": "https://openai-generated-images.s3.amazonaws.com/abc123def456.png"}]}

Extractresponse.data[0].url

Variants

Generate multiple images at once ›

When you want to generate multiple image variations for the same prompt in one API call.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic cityscape at sunset",
    n=3,
    size="1024x1024"
)

for i, img in enumerate(response.data):
    print(f"Image {i+1} URL:", img.url)

Generate smaller images for faster response ›

When you want faster generation and lower cost by requesting smaller image sizes.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic cityscape at sunset",
    n=1,
    size="512x512"
)

print("Generated image URL:", response.data[0].url)

Async image generation ›

When integrating image generation into an async Python application for concurrency.

python

import os
import asyncio
from openai import OpenAI

async def generate_image():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    response = await client.images.generate(
        model="dall-e-3",
        prompt="A futuristic cityscape at sunset",
        n=1,
        size="1024x1024"
    )
    print("Generated image URL:", response.data[0].url)

asyncio.run(generate_image())

Performance

Latency~2-5 seconds per image generation request

Cost~$0.02 per 1024x1024 image generated

Rate limitsDefault tier: 60 requests per minute, 1000 requests per day

Keep prompts concise but descriptive to avoid unnecessary token usage.
Generate fewer images per request to reduce cost.
Use smaller image sizes (512x512) for faster and cheaper generation.

Approach	Latency	Cost/call	Best for
Single image generation	~2-5s	~$0.02	Standard image generation
Multiple images per call	~3-7s	~$0.02 x n	Batch image variations
Smaller image size (512x512)	~1-3s	~$0.01	Faster, cheaper previews

✓

Quick tip

Use descriptive, detailed prompts to get higher quality and more relevant images from DALL-E 3.

⚠

Common mistake

Forgetting to specify the correct model name "dall-e-3" or missing the API key in environment variables causes authentication or model errors.

Verified 2026-04 · dall-e-3

Verify ↗