OpenAI Images API

Generate and edit images through the Qiuqiu Token OpenAI-compatible image API.

Use the OpenAI-compatible image generation and image editing endpoints when calling gpt-image-2 through Qiuqiu Token. Before sending requests, complete the account, balance, and API token setup in Quick Start. Choose a Visual token group that supports gpt-image-2, and do not leave the token in default.

For complete field definitions, available values, and response structures, see:

Generate images

The generation endpoint uses a JSON request body.

curl https://api.qiuqiutoken.net/v1/images/generations \
-H "Authorization: Bearer sk-your-token" \
-H "Content-Type: application/json" \
-d '{
  "model": "gpt-image-2",
  "prompt": "An orange cat wearing a transparent raincoat on a neon rainy street, cinematic composition",
  "size": "1024x1024",
  "quality": "high",
  "output_format": "png"
}'

Generation parameters

Field	Required	Notes
`prompt`	Required	Image prompt. Include the subject, scene, lighting, composition, and style.
`model`	Recommended	Use `gpt-image-2` through the Qiuqiu Token gateway.
`size`	Optional	Common values include `1024x1024`, `1536x1024`, `1024x1536`, and `auto`.
`quality`	Optional	Common values are `low`, `medium`, `high`, and `auto`. Higher quality is usually slower and more expensive.
`background`	Optional	Common values are `transparent`, `opaque`, and `auto`. Transparent output requires `png` or `webp`.
`output_format`	Optional	Common values are `png`, `jpeg`, and `webp`.
`output_compression`	Optional	Official range is `0` to `100`; meaningful only for `jpeg` or `webp`.
`n`	Optional	Number of images. The official range is `1` to `10`.
`moderation`	Optional	GPT Image moderation level. Common values are `low` and `auto`.
`user`	Optional	End-user identifier for audit, risk control, or log correlation.

Generation response

GPT Image models usually return Base64 image content instead of a directly accessible image URL. Read data[*].b64_json:

{
  "created": 1711111111,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ]
}

Edit images

The editing endpoint uses multipart/form-data to upload the source image, an optional mask, and the text prompt. The OpenAI reference describes input images as an images array; with multipart upload, image[]=@... is a common form.

curl https://api.qiuqiutoken.net/v1/images/edits \
-H "Authorization: Bearer sk-your-token" \
-F "model=gpt-image-2" \
-F "image[]=@./input.png" \
-F "mask=@./mask.png" \
-F "prompt=Keep the subject pose, change the background to a neon rainy street, and enhance cinematic reflections" \
-F "size=1024x1024" \
-F "quality=high" \
-F "background=transparent" \
-F "input_fidelity=high" \
-F "output_format=png" \
-F "n=1"

Editing parameters

Field	Required	Notes
`images` / `image[]`	Required	Input images to edit. GPT Image officially supports up to 16 input images; with multipart upload, `image[]=@./input.png` is common.
`prompt`	Required	Describe what to keep, replace, or add.
`model`	Recommended	Use `gpt-image-2` through the Qiuqiu Token gateway.
`mask`	Optional	Provide a mask as a file upload or another officially supported image reference. Transparent areas indicate editable regions.
`size`	Optional	Common values include `1024x1024`, `1536x1024`, `1024x1536`, and `auto`.
`quality`	Optional	Common values are `low`, `medium`, `high`, and `auto`.
`background`	Optional	Common values are `transparent`, `opaque`, and `auto`. Transparent output requires `png` or `webp`.
`input_fidelity`	Optional	Controls how strongly source-image details are preserved. Common values are `low` and `high`.
`output_format`	Optional	Common values are `png`, `jpeg`, and `webp`.
`output_compression`	Optional	Official range is `0` to `100`; meaningful only for `jpeg` or `webp`.
`n`	Optional	Number of returned images. The official range is `1` to `10`.
`moderation`	Optional	GPT Image moderation level. Common values are `low` and `auto`.
`user`	Optional	End-user identifier for audit, risk control, or log correlation.

Save the returned image

After receiving b64_json, decode it before writing the image file.

import base64

b64 = "paste data[*].b64_json here"
with open("gpt-image-output.png", "wb") as f:
  f.write(base64.b64decode(b64))

If the request uses background=transparent, prefer png or webp when saving; otherwise transparency may be lost.