OpenAI · Images · premium
GPT Image 2
The previous GPT Image, kept on the shelf for work already locked to it.
What it costs
| Quality · auto | 11 credits | ≈ $0.26 |
| Quality · low | 1 credit | ≈ $0.02 |
| Quality · medium | 4 credits | ≈ $0.10 |
| Quality · high | 11 credits | ≈ $0.26 |
Dollar figures are approximate, at the Starter plan's rate of $19.00 for 800 credits.
What AI video costs per second: 6 findings
What it takes
| Aspect ratios | 1:1 3:2 2:3 4:3 3:4 16:9 9:16 |
| Reference images | 7 |
When to reach for it
Kept on the shelf. GPT Image 2.5 replaced it on the same rate card — 1 credit on “low”, 11 on “auto” — and added two rungs above that, so there is no price left to argue for staying here. It sits in the picker under Legacy, one press away, for the recipes and saved work already locked to it.
What it was good at is what 2.5 is now better at: a prompt that is a set of instructions rather than a description. Three named objects in stated positions, a sign that has to read as particular words, a layout with a specific hierarchy. It holds compositional intent through a long prompt more reliably than most of the catalog, and that is what the premium tier bought.
Seven references, seven aspect ratios. Ratio coverage is narrower than Nano Banana's, so if the shape is unusual this was never the model, however well it follows instructions. If you are choosing today rather than re-running something, choose Flare.
How to prompt GPT Image 2
GPT Image 2 is the previous build, kept for recipes locked to it. It prompts like 2.5 Flare, but can return a 4:3 or 16:9 request on the nearest fixed square, 3:2 or 2:3 canvas and has no quality steps above high, so new work belongs on Flare or Sunburst.
Made with it
Call out the parts that matter
Your words, printed exactly as you wrote them.
Make it a moving page
Nine collage scenes, one shared look.
Lay it out as one page
A whole recipe poster, typeset in one image.
Explain it in fifteen seconds
Four flat-vector scenes, cut to the voice.
In the arena
Ranked #1 with a rating of 1591. 2 of 4
Week 36, 2026 — Arena week 36: every model can spell nowCompared with
- Nano Banana 2 vs GPT Image 2
GPT Image 2 when the prompt is a set of instructions; Nano Banana 2 when the shape is unusual or the volume is high.
Guides that cover it
- Grok Imagine Video 1.5: the complete prompting guide
One picture in, up to fifteen seconds out, with sound you cannot turn off. Nine rules, three pipelines and the failures worth knowing about first.
- P-Video: the complete guide to Pruna's four models
Four models, one family: a cheap generator and three performance rigs. What each one takes, what a take really costs, and the failures worth knowing first.
- Seedance 2.5: the complete prompting guide
Thirty seconds of video with sound from one written brief. Six rules, three pipelines and the failures worth knowing about before you spend anything.
- Veo 3.1: the complete prompting guide
Eight seconds of video that writes its own soundtrack. Three audio channels, seven rules, four pipelines and the failures worth knowing about first.
- Which image model to reach for, and when
Twelve image models, from half a credit to twenty-one. What each one is for, where the resolution setting changes the price, and when the cheap tier is right.
GPT Image 2 is one pick in the composer.
Every model in this catalog runs from the same prompt bar, priced in the same credits.
Sign up now