GPT Image 2

Generate images from text or edit images using references.

POST

/api/v1/generations

Example request

Set your FLUX_API_KEY before running. See the parameters below for supported settings.

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gpt-image-2",
  "input": {
    "prompt": "Editorial fashion portrait in natural light",
    "aspect_ratio": "4:5",
    "resolution": "2k",
    "quality": "high"
  }
}'

Parameters

Set model to gpt-image-2. These fields belong inside input.

Parameter	Description
`prompt` string · Required	Describe the image you want to create. Maximum 20,000 characters.
`image_urls` string[] · Optional	Public HTTPS reference images. Omit for text-to-image. Up to 16 items.
`aspect_ratio` string · Optional	Requested image proportions. `auto1:11:22:12:33:24:33:44:55:416:99:1621:9` Default: `auto`
`resolution` string · Optional	Output resolution tier. Values are case-sensitive. `1k2k4k` Default: `1k`
`quality` string · Optional	Image quality. Affects credit cost. `lowmediumhigh` Default: `medium`

Reference media

Use your own publicly accessible HTTPS media URLs. Links must remain valid throughout queueing and generation. Base64 and file upload bodies are not supported by this endpoint.

Image-to-image

cURL

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gpt-image-2",
  "input": {
    "prompt": "Editorial fashion portrait in natural light",
    "aspect_ratio": "4:5",
    "resolution": "2k",
    "quality": "high",
    "image_urls": [
      "https://example.com/front.jpg",
      "https://example.com/back.jpg"
    ]
  }
}'

Credits

Quality	1k	2k	4k
low	3	5	8
medium	6	8	10
high	20	25	30

Credits per image. The example uses 25 credits.

Constraints

4k supports only 1:2, 2:1, 16:9, 9:16 and 21:9.

Use returned dimensions when available.

Response

A successful submission returns HTTP 202 and a request ID. Response excerpt:

JSON

{
  "id": "REQUEST_ID",
  "model": "gpt-image-2",
  "status": "processing"
}

Continue readingPoll & download