Images

Generate images from text prompts.

Available image models depend on the model permissions assigned to the virtual API key, for example:

• gpt-image-1.5
• gpt-image-2

Endpoint

POST https://api.nexusmodels.cn/v1/images/generations

Headers

Authorization: Bearer YOUR_NEXUSMODELS_API_KEY
Content-Type: application/json

Request parameters

Parameter	Type	Required	Description
model	string	Yes	Image generation model name
prompt	string	Yes	Description of the image to generate
n	integer	No	Number of images to generate
size	string	No	Image size supported by the model
quality	string	No	Image quality supported by the model
background	string	No	Background type, such as transparent or opaque
output_format	string	No	Output format, such as png or jpeg
response_format	string	No	URL or Base64 response, depending on model support
user	string	No	End-user identifier

Example

curl -sS -X POST \
  'https://api.nexusmodels.cn/v1/images/generations' \
  -H 'Authorization: Bearer YOUR_NEXUSMODELS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-1.5",
    "prompt": "An artificial intelligence research center in a futuristic city, modern architecture and blue lighting",
    "size": "1024x1024",
    "quality": "high",
    "n": 1
  }'

URL response example

{
  "created": 1788163200,
  "data": [
    {
      "url": "https://example.com/generated-image.png"
    }
  ]
}

Base64 response example

Some models return Base64 image data directly:

{
  "created": 1788163200,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAA..."
    }
  ]
}

Save a Base64 image

Assuming the API response is saved as response.json:

jq -r '.data[0].b64_json' response.json \
  | base64 --decode \
  > generated-image.png

On macOS:

jq -r '.data[0].b64_json' response.json \
  | base64 -D \
  > generated-image.png