How does GPT Image 2 pricing work?

Credit-based: 1 credit = $0.001 USD. The basic channel is flat per resolution (1k, 2k, 4k). The stable channel prices per cell — aspect ratio × resolution × quality tier — and the estimator on this page reflects exactly the cell that will be billed at submit time. No hidden fees on either GPT Image 2 channel, and no monthly platform fee.

Can GPT Image 2 edit existing images?

Yes. Pass URLs in `image_urls` and the GPT Image 2 model switches to image-to-image. Add `mask_url` to inpaint a region — the masked area gets regenerated, the rest stays untouched. Up to 16 reference images feed into a single request, public HTTPS only (no base64 or `data:` URIs).

How do I run my first GPT Image 2 generation?

Create an API key from the dashboard, then POST to `/api/v1/images/generations` with `model: gpt-image-2` and a prompt. The endpoint returns a task ID immediately — poll `/api/v1/tasks/:id` until status is completed and download the image from our CDN. The full quickstart sits at the top of this page with a runnable curl block.

What's the difference between the two GPT Image 2 channels?

The basic channel (`gpt-image-2`) is the cheapest path: one image per call, flat price per resolution, prompt and reference URLs only. The stable channel (`gpt-image-2-official`) unlocks batches up to four, quality tiers, inpainting masks, transparent backgrounds, and per-format compression. Send a stable-only field on the basic channel and the request is rejected with HTTP 400 — no silent fallback.

Does GPT Image 2 support transparent backgrounds?

Yes, on the stable channel. Set `background: transparent` and `output_format: png`, and GPT Image 2 returns a PNG with alpha — ready for product cutouts, overlay assets, and UI illustrations. Transparent output isn't available on the basic channel; use the stable variant when you need it.

How fast is GPT Image 2 generation?

Most calls finish in 10 to 60 seconds. The playground on this page streams live status while a task runs, and the same status is exposed on the polling endpoint so you can wire a progress bar into your own app. GPT Image 2 timing scales mostly with quality tier and target resolution.

Where is the full GPT Image 2 API reference?

The complete parameter list, error codes, channel comparison, and runnable examples live at `/docs/api/models/gpt-image-2`. Both GPT Image 2 channels share the same endpoint shape — only the `model` field differs — so a single integration covers both variants and either price tier.

GPT Image 2 API — OpenAI Image Generation, One Endpoint

GPT Image 2 generates and edits images through one OpenAI-style API. Async tasks, credit pricing, two variants — production-ready in minutes.

Model type:

Price

est$0.007– $0.02per image

Per-call billing tiered by resolution.

Same API endpoint. The model parameter selects the variant.

Try GPT Image 2 View API Docs

01playground

InputsPOST /api/v1/images/generations

Prompt*

Free text · required · ≤ 4000 chars

Provide a prompt or at least one reference image / video / frame.

Size

auto picks ratio from prompt or refs

Resolution

4k needs widescreen ratio

Reference images

Drag images here or click to upload

Up to 16 · uploaded to R2

Outputidle

try one of these prompts

02use cases

What you can build

Real workflows powered by this model.

01/case

Refresh product photos in batches

Edit existing e-commerce shots without a reshoot. Swap colorways, change backgrounds, or restyle for a new season — GPT Image 2 keeps the original product untouched while the surrounding scene gets reworked. One image URL goes in, an updated render comes out. Run a hundred SKUs through the same prompt template and the catalog stays visually consistent.

Edit a photo

Marketing creatives generated with GPT Image 2

02/case

Generate ad creatives at draft speed

Spin four hero variants from a single prompt with the stable channel of GPT Image 2 (n=4). Pick the winner, ship to social, iterate on the rest. The basic channel handles single-image drafts when budget matters more than choice. Same endpoint either way — switch with one string in the request body.

Reference-driven composition with GPT Image 2

03/case

Compose scenes from reference images

Pass up to 16 reference images and the model fuses them into a new composition that respects your brand. Add a mask URL for inpainting — replace a sky, repaint a wall, or swap a logo without redrawing the surrounding pixels. GPT Image 2 handles the fine edges and texture transitions automatically.

03pricing

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

Mode	Category	Unit	Price
Self
└	1K	1 image	$0.007 7 credits
└	2K	1 image	$0.014 14 credits
└	4K	1 image	$0.02 20 credits
Stable
└	Low	1 image	$0.006 6 credits
└	Medium	1 image	$0.047 47 credits
└	High	1 image	$0.186 186 credits
└	High 4K	1 image	$1.467 1467 credits

05why

Why reAPI

Two variants, one endpoint

Send model `gpt-image-2` for the cheap basic channel — single image, flat per-resolution price. Send `gpt-image-2-official` for the stable channel: batches up to four, quality tiers, inpainting masks, transparent backgrounds, output format and compression control. Switch channels by changing one string. No client refactor, no second SDK to learn.

Credits, not surprises

1 credit equals $0.001 USD. The live estimator on this page costs your exact configuration before you submit, so the GPT Image 2 charge in your dashboard matches what you saw at request time. No metering surprises, no minimum commitment, no monthly platform fee — only what your app actually generates.

Async by default

Submit a task, get an ID instantly, poll until done. Nothing to time out, nothing to retry. The same async pattern slots into serverless functions, queue workers, and edge runtimes — wherever you run, the GPT Image 2 endpoint fits the shape your stack already uses.

06quickstart

Integrate GPT Image 2 in three steps

step 01
Create an API key
Sign up and grab a key from the dashboard. Free signup credits cover a few hundred basic-channel generations before you ever top up — enough to ship the first feature and watch the bill stay at zero.
Open
step 02
Submit a generation
POST a JSON body with `model`, `prompt`, and any optional fields to `/api/v1/images/generations`. Pick `gpt-image-2` for cheap drafts or the stable variant for the full feature set. The endpoint returns a task ID immediately so the request never blocks your handler.
Open
step 03
Poll the result
GET `/api/v1/tasks/:id` until status flips to `completed`. The GPT Image 2 response holds image URLs on our CDN — stable for seven days. Mirror them to your own storage if you need them longer than that.
Open

07faq

Frequently asked questions

Common questions about this model.

GPT Image 2 is OpenAI's text-to-image and image-editing model. reAPI exposes it through one async endpoint with credit-based pricing, so you skip the upstream billing surface entirely while still calling the same underlying model. Two channels are available, priced and feature-scoped independently — pick the one that fits each request.

09api reference

docs/api/gpt-image-2

API reference

Drop-in code and the full parameter table.

View full reference

POST /api/v1/images/generations
Authorization: Bearer $REAPI_API_KEY
Content-Type: application/json

{
  "prompt": "..."
}

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.

Try GPT Image 2 Get API key

What you can build

Real workflows powered by this model.

01/case