OpenAI · Released April 21, 2026

GPT Image 2 AI Image Generator

OpenAI's gpt-image-2 reasons about the layout before it draws. Multilingual text, high-fidelity edits and faithful instruction following, online and without watermark. 4 credits per image on Aura AI, with GPT Image 1.5 from 2 credits.

4
Credits per Image
5
Aspect Ratios
Edit
High-Fidelity Mode
OpenAI
Reasoning Model

GPT Image 2 on Aura AI

MakerOpenAI
ModesText to image, image edit
VariantsGPT Image 2, 1.5, 1
OutputStill image, no watermark
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4
EditingGPT Image 2 Edit, 1.5 Edit
Credits2 to 4 per image
PlanStarter, Pro, Premium

What is GPT Image 2?

GPT Image 2, known in the API as gpt-image-2, is OpenAI's image generation and editing model, released on April 21, 2026 together with ChatGPT Images 2.0. It is the third model in the line after GPT Image 1 (April 2025) and GPT Image 1.5 (December 16, 2025), which made edits more precise and up to four times faster. GPT Image 2 is OpenAI's quality-first follow-up and the first OpenAI image model with a native reasoning step: it plans the composition, the elements and the text before it renders a pixel, which is why it behaves less like a paint tool and more like a designer that reads the whole brief.

The practical gains are in three areas. Text rendering now covers dense paragraphs, small lettering and non-Latin scripts including Chinese, Japanese, Korean, Hindi and Bengali, the weak spot of every earlier OpenAI image model. Resolution moves from three fixed sizes to custom dimensions, with native output up to 3840 x 2160 upstream. Editing changes philosophy too: where GPT Image 1.5 exposed a low or high input fidelity switch, GPT Image 2 processes every input at high fidelity by default, so faces, logos and fine detail survive a change. OpenAI also corrected the warm color cast of 1.5 toward neutral reproduction. In the API, the high quality tier at 1024 x 1024 costs $0.211 per image upstream, against $0.133 for GPT Image 1.5.

On Aura AI, GPT Image 2 runs in the text-to-image tool at a flat 4 credits per image, in five aspect ratios, and as GPT Image 2 Edit in the image editor at 4 credits per edit. GPT Image 1.5 is there too at 2 credits for both modes, and GPT Image 1 at 3 credits. Output is delivered without watermark, and the same credits work on Nano Banana, FLUX 2, Seedream 5.0 and the rest of the catalog.

What's New in GPT Image 2

Six capabilities that separate gpt-image-2 from GPT Image 1.5 and GPT Image 1

Reasoning Before Rendering

GPT Image 2 thinks through the request first: what goes where, which elements matter, how the text fits. Multi-part prompts with several subjects and constraints land far more often on the first try.

Multilingual, Dense Text

Paragraphs, small lettering and mixed-language layouts come out readable, including Chinese, Japanese, Korean, Hindi and Bengali. Menus, packaging and UI mockups no longer need a second pass in a design tool.

High-Fidelity Edits by Default

Every edit input is processed at high fidelity, with no toggle to remember. A person's face, a product label or a logo stays exactly as it was in the source while the rest of the scene changes.

Custom Dimensions up to 4K UHD

Instead of three fixed sizes, GPT Image 2 accepts custom dimensions upstream with native output up to 3840 x 2160. Wide banners, tall stories and print layouts are generated at the right shape.

UI and Screenshot Generation

Because it plans structure, GPT Image 2 is unusually good at app screens, dashboards, slides and web mockups that look like real software rather than an impression of it.

Neutral Color and Photorealism

OpenAI corrected the warm cast that GPT Image 1.5 was known for. Skin tones, whites and product colors reproduce neutrally, and photorealistic scenes gain in material detail and lighting.

How to Use GPT Image 2 on Aura AI

Four steps from prompt to a finished image, or from a photo to a faithful edit

  1. Open the Text to Image tool for a new image, or the Image Editor to change one of your own. Sign in with your Aura AI account.
  2. Pick GPT Image 2 in the model selector, or GPT Image 1.5 when you want cheaper drafts (in the editor, GPT Image 2 Edit or GPT Image 1.5 Edit). Choose one of the five aspect ratios. The credit cost is shown before you generate.
  3. Write the brief the way you would for a designer: subject, layout, style, and every line of text in quotation marks. GPT Image 2 reasons over the whole prompt, so long, structured instructions work better than keyword lists.
  4. Generate, compare and download the image without watermark. Every result is saved to your history and can go straight into Image to Video to become a clip.

GPT Image 2 Pricing in Credits

Flat cost per image, no resolution or aspect ratio multiplier

Variant Mode Credits per image Best for
GPT Image 2Text to image4 creditsFinal assets, dense text, UI mockups, complex briefs
GPT Image 2 EditImage edit4 creditsHigh-fidelity edits of photos, products and logos
GPT Image 1.5Text to image2 creditsQuick drafts and volume generation
GPT Image 1.5 EditImage edit2 creditsFast, precise edits at the lowest cost
GPT Image 1Text to image3 creditsThe original 2025 model, for matching earlier work
Every GPT Image variant is available on every plan: Starter ($14/mo), Pro ($59/mo) and Premium ($99/mo). Each plan includes a monthly credit allowance shared across all image and video models. Only successful generations are charged.

GPT Image 2 vs Nano Banana vs FLUX 2 vs Seedream 5.0

How OpenAI's image model compares to the other flagship generators on Aura AI

Feature GPT Image 2 Nano Banana FLUX 2 Seedream 5.0
Maker OpenAI Google DeepMind Black Forest Labs ByteDance
Latest release Apr 2026 Feb 2026 (Nano Banana 2) Dec 2025 (FLUX 2 Max) Jul 2026 (5.0 Pro)
Credits, text to image 4 (1.5: 2) 3 1 to 3 3 to 4
Credits, image edit 4 (1.5: 2) 2 to 3 2 to 3 2 to 4
Reasoning step Native Yes Not advertised Since 5.0
Max resolution (upstream) 3840 x 2160 4K 4 megapixels 4K
Non-Latin text CJK, Hindi, Bengali Multilingual Not specified Chinese, English
Plan All plans All plans All plans All plans

What to Make with GPT Image 2

Where reasoning, text and faithful edits pay off

App and Web Mockups

Describe a screen and GPT Image 2 lays it out like a product designer: navigation, cards, buttons and readable labels in the right places.

Example Prompt: "Mobile banking app home screen, balance card at top reading '$4,280.12', four quick actions, recent transactions list, clean light theme, 9:16"

Multilingual Marketing

Run one campaign in several scripts. The same poster can carry a Japanese, Korean or Hindi headline with correct characters, which earlier OpenAI models could not do reliably.

Example Prompt: "Ramen shop poster, large Japanese headline '本日の一杯' with English subline 'Bowl of the day', steam rising from a bowl, warm red and black palette, 3:4"

Product Edits That Keep the Logo

Upload a packshot and ask for a new setting or season. High-fidelity input handling keeps the label, typography and brand marks intact while the environment changes around them.

Example Prompt: "Place this coffee bag on a rustic wooden table with morning light and scattered beans, keep the label and logo exactly as in the source, 4:3"

Infographics and Slides

Charts, step diagrams and comparison slides benefit from the reasoning step: hierarchy is planned first, so labels line up with what they describe.

Example Prompt: "Slide explaining a three-step onboarding flow, numbered columns 'Sign up', 'Connect', 'Launch', flat icons, navy and white, 16:9"

GPT Image 2 FAQ

Common questions about GPT Image 2 on Aura AI

What is GPT Image 2? +
GPT Image 2 (API name gpt-image-2) is OpenAI's image generation and editing model, released on April 21, 2026 alongside ChatGPT Images 2.0. It is the first OpenAI image model with a native reasoning step, so it plans the layout and elements before rendering. It succeeds GPT Image 1.5 (December 2025) and GPT Image 1 (April 2025). On Aura AI it is available for text-to-image and image editing, without watermark.
How many credits does GPT Image 2 cost on Aura AI? +
GPT Image 2 costs 4 credits per generated image in text-to-image mode and 4 credits per edit in the image editor. GPT Image 1.5 costs 2 credits for both generation and edits, and GPT Image 1 costs 3 credits per image. All costs are flat, with no aspect ratio multiplier, and only successful generations are charged.
Which plan do I need to use GPT Image 2 on Aura AI? +
GPT Image 2, GPT Image 2 Edit, GPT Image 1.5 and GPT Image 1 are available on every Aura AI plan: Starter ($14/mo), Pro ($59/mo) and Premium ($99/mo). Each plan includes a monthly credit allowance shared across all image and video models, on web, iOS, Android and Windows.
What is the difference between GPT Image 2 and GPT Image 1.5? +
GPT Image 2 adds a reasoning stage, extends readable text to scripts such as Chinese, Japanese, Korean, Hindi and Bengali, supports custom dimensions with native output up to 3840 x 2160 upstream, and treats every edit input at high fidelity by default. GPT Image 1.5 is the faster, cheaper model with three fixed sizes and a warmer color cast. On Aura AI GPT Image 2 costs 4 credits and GPT Image 1.5 costs 2, so 1.5 is the pick for quick drafts and 2 for final assets.
Can GPT Image 2 edit my own photos? +
Yes. Upload a photo in the Aura AI image editor, choose GPT Image 2 Edit and describe the change. Because the model processes inputs at high fidelity, faces, logos and fine details of the source survive the edit. You can swap backgrounds, change clothing, remove objects, restyle a product shot or rewrite the text in an image.

Generate GPT Image 2 Images Online

OpenAI's reasoning image model, 4 credits per image, high-fidelity edits, no watermark. Available on every plan, worldwide.