GPT Image 2 is OpenAI's image generation model, released in April 2026. It is autoregressive rather than diffusion based, reasons about the prompt before generating, and is the strongest model available for rendering readable text inside an image.

Should I use GPT Image 2 or GPT Image 2.5 Flare?

Flare, in almost every case. It is the newer generation, it costs the same 3 to 9 credits, and it is faster and better at references. GPT Image 2 stays available for reproducibility: if a pipeline was tuned against it, older API ids still resolve to it.

How much does GPT Image 2 cost on APImage?

3 to 9 credits per image, depending on size and quality. It is included on every plan, including the free tier.

Can it render languages other than English?

Yes. Non Latin scripts were a long standing weak spot across the category and GPT Image 2 handles them, which is what makes it usable for localised creative.

Does it support transparent backgrounds?

Yes, transparent PNG output is available on Plus and above. For cutting out an existing image, the dedicated background removal tool is a flat 2 credits.

Can I edit an image I already have?

Yes. GPT Image 2 does image to image and editing, and takes up to four reference images per generation.

Text that rendersOpenAI

GPT Image 2.
The one that can spell.

OpenAI's image model reasons about the prompt before it draws, and it renders type cleanly enough to put on a poster. Every plan on APImage includes it, from 3 credits an image.

Generate with GPT Image 2 See pricing

3 to 9 credits per image. Included on every plan, including the free tier. 4K output on Plus and above.

OpenAI

GPT Image 2

What is GPT Image 2?

GPT Image 2 is OpenAI's image generation model, released in April 2026. Unlike diffusion models it is autoregressive and reasons about a prompt before generating, which is why it follows complicated instructions more faithfully and, above all, renders readable text. Type inside a generated image has been the standing failure of the whole category, including non Latin scripts, and GPT Image 2 is the model that fixed it. On APImage it costs 3 to 9 credits an image, is included on every plan down to the free tier, and sits in the same studio as the Flux models so you can run a prompt through both and keep the better one.

One subscription, every model

One pool of credits

No per model surcharge

API and MCP access included

Specifications

Provider: OpenAI
Released: April 2026
Architecture: Autoregressive, reasons before generating
Resolution: Up to 4K on Plus and above, longest edge 3840px
Text rendering: Best in class, including non Latin scripts
Reference images: Up to 4 per generation
Transparency: Transparent PNG on Plus and above
Modes: Text to image, image to image, editing
Plans: Every plan, including free
Cost: 3 to 9 credits per image

Why this model

What GPT Image 2 does that the others do not.

Type you can actually read

Headlines, packaging copy, UI labels, signage. The words come out spelled correctly, in the font weight you asked for, including in scripts other models mangle.

It thinks first

Reasoning before generation means a prompt with five constraints comes back with five constraints met, not three and a shrug.

Screens and interfaces

Notably strong at UI and screenshot generation, which is otherwise a reliable way to produce something that looks like software from a dream.

Photoreal when you need it

A real step up on skin, texture and light over the previous generation, so it is not only a text tool.

What people make with it

Where it earns its credits in real work.

Thumbnails and posters

Anything where the words are half the design. This is the model that gets the words right.

Packaging and labels

Product copy, ingredient panels, brand marks. Legible at the size a customer sees them.

Ad creative with a headline

The offer has to be readable in the feed. Generate the whole frame rather than compositing text on afterwards.

App and site mockups

Interface concepts with real labels, for a deck that has to look like a product and not a placeholder.

Localised creative

Non Latin scripts render properly, so one design ships in more than one market.

How it works

1Open the image studio and pick GPT Image 2.
2Describe the image, and put the exact words you want rendered in quotes.
3Add up to four reference images for style, product or likeness.
4Set the size, generate, and iterate on the prompt rather than in an editor.

Create your account and try it

Or use one of these

GPT Image 2 is not the right answer to everything. Your plan includes all of them, so switching model costs nothing.

GPT Image 2.5 Flare

Almost always. Same credits, half the latency, better references. This is the default now.

See GPT Image 2.5 Flare

Flux 2 Max

There is no text in the frame and you want maximum photographic detail.

Flux 2 Klein 9B

You are iterating and want the cheapest, fastest look at a composition.

What it costs

3 to 9 credits per image

Included on every plan, including the free tier. 4K output on Plus and above.

No separate subscription

GPT Image 2 is on the same plan as every other model on APImage, priced in the same credits out of the same pool. Run the same prompt through three models and keep the one that looks right.