Image model by OpenAI

GPT Image 2 All API

model: gpt-image-2-all

Call GPT Image 2 All with your KeelRouter API key, the same key you use for every other model. From $0.0068 per image, paid per call from a prepaid balance. Failed calls are free.

Pricing

OptionPrice
1K low$0.0068 per image
1K medium$0.033 per image
1K high$0.039 per image
2K low$0.0091 per image
4K low$0.015 per image

Call it

Async: POST /v1/images/generations returns a taskId; poll the same path with ?task_id= or pass a callback_url.

curl https://api.keelrouter.com/v1/images/generations \
  -H "Authorization: Bearer $KEELROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image-2-all",
  "prompt": "A lighthouse at dawn, watercolor",
  "resolution": "1K",
  "quality": "low"
}'

Parameters

NameTypeNotes
modelstringRequired. gpt-image-2-all
promptstringRequired.
sizestring
qualitystringOne of low, medium, high, auto. Default medium.
aspect_ratiostring
resolutionstringOne of 1K, 2K, 4K. Default 1K.
imagestring
image_urlsarray
backgroundstringOne of transparent, opaque, auto.
output_formatstringOne of png, jpeg, webp.
nnumberRange 1–….
callback_urlstringOptional https URL; we POST the result when the task ends

FAQ

How much does the GPT Image 2 All API cost on KeelRouter?
From $0.0068 per image. You pay per call from a prepaid USD balance; failed calls are not charged.
How do I call GPT Image 2 All?
POST to /v1/images/generations with model "gpt-image-2-all". You get a taskId back; poll the same endpoint with ?task_id= or pass a callback_url.
Is this the official GPT Image 2 All API?
No. KeelRouter is an independent API gateway. Requests run on GPT Image 2 All through our upstream providers, and the image model keeps its own safety filters.
How long are results kept?
Result files are kept for 30 days, then deleted. Download what you want to keep.

More from OpenAI

KeelRouter is an independent service and is not affiliated with OpenAI. GPT Image 2 All is a trademark of its owner, used here only to name the model a request runs on.