Image
GPT Image 2
Create GPT Image 2 visuals from text or switch to image editing.
- Text to image
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for GPT Image 2. Review your own result before publishing.
A starting point.
Describe layout and write the exact wording required on signs or labels.
Before you publish.
Proofread text and inspect edges, repeated objects and edited regions.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
The default uses prompt. Editing additionally requires image_urls and accepts mask_url for regional edits; identify the parts that should remain unchanged.
Select quality, num_images and output_format. For a transparent background, use background with PNG or WebP and check the exported image’s transparency.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for openai/gpt-image-2. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 2 · Max. characters: 32000 |
background | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
output_format | Text | Optional | jpeg, png, webp |
quality | Text | Optional | auto, low, medium, high |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Image editingopenai/gpt-image-2/edit
Supported inputs
These fields come from the current studio form for openai/gpt-image-2/edit. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_urls | List | Required | Max. items: 16 |
prompt | Text | Required | Min. characters: 2 · Max. characters: 32000 |
background | Text | Optional | — |
mask_url | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
output_format | Text | Optional | jpeg, png, webp |
quality | Text | Optional | auto, low, medium, high |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use GPT Image 2 through the API.
Start with this model ID for the endpoint featured on this page:
openai/gpt-image-2
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-image ·
openai/gpt-image-2 - image-to-image ·
openai/gpt-image-2/edit
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.