GPT Image 2
Second-generation OpenAI visual model with in-image typography, wide aspect ratios, and up to 4K output.
| Property | Value |
|---|---|
modelSlug | gpt-image-2 |
| Kind | Image |
| Maker | OpenAI |
Copies per request (variations) | 1 to 5 |
| How the cost is counted | per copy |
| Over MCP | yes, with the generate tool |
Credit amounts are left out because they change. The lowest price is creditCost on GET /v1/models, and POST /v1/jobs answers with the exact creditCost of a request.
input fields
Send the fields below inside the input object. A field you leave out takes its Default. Unknown field names are dropped without an error, so check the spelling if a setting seems to have no effect.
| Field | Type | Required | Default | Rules |
|---|---|---|---|---|
prompt | string | yes | – | Up to 20,000 characters |
reference_images | string[] (image upload ids) | – | – | Reference images. Up to 16 files |
aspect_ratio | string (one of) | – | auto | auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21 |
resolution | string (one of) | – | 1K | 1K, 2K, 4K |
background | string (one of) | – | auto | auto, opaque, transparent |
Rules by setting
This model runs a different version depending on what you send. The rules below are checked before any credits move; a request that breaks one is refused with 400 and a message naming the field.
Every request
- Refused combinations:
resolution=2Kwithaspect_ratio=auto;resolution=4Kwithaspect_ratio=auto;resolution=2Kwithaspect_ratio=5:4;resolution=2Kwithaspect_ratio=4:5;resolution=2Kwithaspect_ratio=3:1;resolution=2Kwithaspect_ratio=1:3;resolution=2Kwithaspect_ratio=9:21;resolution=4Kwithaspect_ratio=1:1;resolution=4Kwithaspect_ratio=3:1;resolution=4Kwithaspect_ratio=1:3;resolution=4Kwithaspect_ratio=9:21.
Without a reference file and resolution = 4K
backgroundis not used; any value sent is ignored.- Takes no files in
reference_images; a request that fills one is refused.
Without a reference file and resolution = 2K
backgroundis not used; any value sent is ignored.- Takes no files in
reference_images; a request that fills one is refused.
Without a reference file and resolution = 1K
- Takes no files in
reference_images; a request that fills one is refused.
With a reference file and resolution = 4K
backgroundis not used; any value sent is ignored.reference_images: required; up to 16 files.
With a reference file and resolution = 2K
backgroundis not used; any value sent is ignored.reference_images: required; up to 16 files.
With a reference file and resolution = 1K
reference_images: required; up to 16 files.
Example request
{
"modelSlug": "gpt-image-2",
"input": {
"prompt": "Product photo of white running shoes on a river stone, soft side light in the morning"
}
}