gpt-image-2.5-sunburst

Approved Data Classifications

This model is only approved for Open Data. When leveraging NaviGator AI’s suite offerings, please ensure you are selecting models that meet the compliance requirements in accordance with UF’s Data Classifications, grant awards or project specifications, and state and federal law.

Description

gpt-image-2.5-sunburst is a text‑to‑image and image-to-image model from OpenAI that can generate high quality images that require a high level of output precision. This model will be able to follow your input directions very closely to generate images that more precisely reflect your intentions. It has 5 different quality settings that allow for fine grain control over the quality of the generated image or chose auto to let the model decide. The higher the quality the longer it takes to generate the image and the more tokens it uses therefore increasing costs. This models supports generating images up to maxium pixel count of 8,294,400 at various image resolutions.

Capabilities

Model	Knowledge Cutoff	Input	Output	Cost (per 1 million tokens)
gpt-image-2.5-sunburst	n/a	Text.Image	Image	$5/M text input / $8/M image input $8/M image output

Cost Estimates

Quality	Size	Output token estimate	Output cost estimate
low	1024 x 1024	196	$0.00588
medium	1024 x 1024	439	$0.01317
high	1024 x 1024	1,756	$0.05268
xhigh	1024 x 1024	3,122	$0.09366
max	1024 x 1024	7,024	$0.21072

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-2.5-sunburst",
  "prompt": "An Alligator walking around the University of Florida saying hi to students.",
  "size": "1024x1024",
  "quality": "low"
}'

python

from openai import OpenAI
import base64
client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.ai.it.ufl.edu/v1"
)

result = client.images.generate(
    model="gpt-image-2.5-sunburst",
    prompt="An Alligator walking around the University of Florida saying hi to students.",
    size="1024x1024",
    quality="low",
    response_format="b64_json"
)

image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the image to a file
with open("alligator.png", "wb") as f:
  f.write(image_bytes)

javascript

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

 const prompt = "An Alligator walking around the University of Florida saying hi to students.";

 const result = await openai.images.generate({
   model: "gpt-image-2.5-sunburst",
   prompt,
 });

 // Save the image to a file
 const image_base64 = result.data[0].b64_json;
 const image_bytes = Buffer.from(image_base64, "base64");
 fs.writeFileSync("alligator.png", image_bytes);

---

References

1. OpenAI
   https://openai.com/
2. GPT-Image-2.5 Sunburst Model page https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst
3. Cost Estimage Calculator
   https://developers.openai.com/api/docs/guides/image-generation#gpt-image-25-and-gpt-image-2-output-tokens
4. Model paramaters and prompting guide https://developers.openai.com/api/docs/guides/image-prompting#model-parameters
5. Artificial Analysis
   https://artificialanalysis.ai