GPT Image 2.5 Sunburst API

openai/gpt-image-2.5-sunburst
GPT Image 2.5 Sunburst generates and edits images from text and image inputs, and is the tier OpenAI recommends where editing precision matters most.
Output
$39 / 1M tokens
Released
Sep 9, 2026

Overview

What Is GPT Image 2.5 Sunburst?

GPT Image 2.5 Sunburst is the precision-oriented tier of OpenAI's GPT Image 2.5 family. It generates and edits images from text and image inputs, and OpenAI positions it for workflows where editing precision matters most — production-ready campaign creative and polished product imagery.

The 2.5 generation as a whole brings sharper detail, stronger style adherence and more control over edits than the previous generation.

Technical Specifications

  • Supported inputs: Image, Text
  • Output: Image
  • Endpoints: /images/generations and /images/edits
  • Inpainting supported
  • Quality settings: low, medium, high, xhigh, max, auto

API Pricing

Image generation:

  • Input: $10.40 / 1M tokens
  • Output: $39.00 / 1M tokens

Text input:

  • Input: $6.50 / 1M tokens
  • Cached input: $1.625 / 1M tokens

Sunburst or Flare?

Sunburst is the choice when edits must land exactly as briefed. Pick GPT Image 2.5 Flare instead for everyday generation, rapid prototyping and high volume, where speed matters more.

Available on AI/ML API since September 9, 2026.

Uptime and performance

  • Uptime (24h): 100%
  • Uptime (7d): 99.0%
  • Availability (24h): 96.0%
  • Error rate (24h): 4.0%
  • End-to-end latency (24h median): 24.7s

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

GPT Image 2.5 Sunburst is documented for premium visual workflows that benefit from tighter control across edits. It is suited to production-ready campaign creative. It is also suited to polished product imagery. The model is described as a fit for workflows where editing precision matters most, including precise editing of text-and-image inputs.

How to use GPT Image 2.5 Sunburst API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to openai/gpt-image-2.5-sunburst.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "openai/gpt-image-2.5-sunburst",
      "prompt": "A cat holding a sign that says hello"
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-image-2.5-sunburst",
    "prompt": "A cat holding a sign that says hello"
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-image-2.5-sunburst","prompt":"A cat holding a sign that says hello"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

GPT Image 2.5 Sunburst API Pricing

TypePrice
Input
$6.5 / 1M tokens
Output
$39 / 1M tokens
Cached input
$1.625 / 1M tokens

GPT Image 2.5 Sunburst Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Image Editing Arena
1176
Human preference Elo from blind pairwise comparisons of edited images, measured independently by Artificial AnalysisSourceSeptember 21, 2026

GPT Image 2.5 Sunburst vs other models

ModelInputOutputContextBest for
$6.5 / 1M tokens
$39 / 1M tokens
Precise image editing
$6.5 / 1M tokens
$39 / 1M tokens
Fast, high-volume image generation
$6.5 / 1M tokens
$39 / 1M tokens
Image generation at scale
$0.325 / 1M tokens
$78 / 1M tokens
128K tokens
Image generation at scale
$0.325 / gen
Image generation at scale

Frequently asked questions

GPT Image 2.5 Sunburst is the precision-oriented tier of OpenAI's GPT Image 2.5 family. It generates and edits images from text and image inputs.

Use Sunburst when editing precision matters most, for example production-ready campaign creative or polished product imagery. Flare is the better fit when speed and volume matter more.

Yes. Editing is its main purpose: it supports the image edits endpoint, and inpainting is a supported feature.

Six settings are available: low, medium, high, xhigh, max and auto.

It takes text and image input and returns images.

Two: image generations and image edits.

OpenAI describes the 2.5 models as offering sharper detail, stronger style adherence and more control over edits than the previous generation.

Send a request to the image generations endpoint with the model id openai/gpt-image-2.5-sunburst, and a prompt describing the image you want.

Start building with GPT Image 2.5 Sunburst

Get API Key
1000+ models, one API.