gpt-image-1

Approved Data Classifications

Description

gpt-image-1 is a text‑to‑image model from OpenAI that turns your words into pictures in seconds. You get three options to choose from, Low for when you need a quick sketch, Medium for everyday visuals, and High when you want every pixel to pop. You can create images up to 1536×1024, whether it’s a thumbnail for your blog, a slide for your talk, or a colorful illustration for your next lesson. Just send a prompt through the simple API or the NaviGator Toolkit UI, and your idea springs to life without any fuss or hidden fees.

Capabilities

Model	Training Data	Input	Output	Quality	1024×1024	1024×1536	1536×1024
gpt-image-1	n/a	Text	Image	Low	$0.011/image	$0.016/image	$0.016/image
				Med	$0.042/image	$0.063/image	$0.063/image
				High	$0.167/image	$0.25/image	$0.25/image

info

• estimated image size is 1024 x 1024
• All prices listed are based on 1 image

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/images/generations \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
  "model": "gpt-image-1",
  "prompt": "An Alligator walking around the University of Florida saying hi to students.",
  "size": "1024x1024",
  "quality": "low"
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.images.generate(
      model="gpt-image-1",
      prompt="An Alligator walking around the University of Florida saying hi to students.",
      size="1024x1024",
      quality="low",
      response_format="url"
  )

  image_url = response.data[0].url

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.images.generate({
    model: "gpt-image-1",
    prompt: "An Alligator walking around the University of Florida saying hi to students.",
    size: "1024x1024",
    quality: "standard",
    response_format: "url",
});

image_url = response.data[0].url;

When to use

You should consider gpt-image-1 whenever you need to convert text descriptions into visual content quickly and reliably. Its Low‑quality tier is perfect for rapid prototyping or generating placeholders at minimal cost, while the Medium tier offers a balanced mix of speed and fidelity for most production‑ready assets. If you require the highest level of detail—for marketing materials, detailed illustrations, or publication‑quality graphics—the High tier delivers premium results with fine‑grain control over color, lighting, and composition.

This model is especially well suited for design workflows that demand on‑the‑fly visuals—such as concept art, slide decks, or educational illustrations—without the overhead of manual editing or multiple software tools. With a straightforward API and seamless integration into the NaviGator Toolkit, gpt-image-1 enables designers, developers, and educators to incorporate custom imagery into their projects in seconds, all while maintaining clear cost predictability and minimal setup.