OpenAI Generations

/v1/images/generations is the OpenAI Images API compatible synchronous image generation endpoint. The caller waits for the upstream response in the same HTTP request.

Interface

Item	Value
Method	POST
Path	/v1/images/generations
Content-Type	application/json
Authentication	Authorization: Bearer YOUR_API_KEY
Platform requirement	OpenAI platform group with image generation enabled

Request Parameters

Parameter	Type	Required	Description
model	string	No	Image model. Defaults to gpt-image-2. Must be a gpt-image-* model.
prompt	string	Yes	Image generation prompt.
size	string	No	Output size, such as 1024x1024.
n	integer	No	Number of images. Defaults to 1 and must be greater than 0.
response_format	string	No	Response format. b64_json is commonly used.
stream	boolean	No	Whether to stream the upstream response when supported.
quality	string	No	Native OpenAI image parameter, forwarded when supported upstream.
background	string	No	Native OpenAI image parameter, forwarded when supported upstream.
output_format	string	No	Native OpenAI image parameter, forwarded when supported upstream.
output_compression	integer	No	Native OpenAI image parameter, forwarded when supported upstream.
moderation	string	No	Native OpenAI image parameter, forwarded when supported upstream.
style	string	No	Native OpenAI image parameter, forwarded when supported upstream.

Request Example

curl https://llmapi.site/v1/images/generations \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-2",
    "prompt": "a product photo of a ceramic coffee cup on a white table",
    "size": "1024x1024",
    "n": 1,
    "response_format": "b64_json"
  }'

Response Example

{
  "created": 1779912000,
  "data": [
    {
      "b64_json": "..."
    }
  ]
}

Common Errors

Calling from a non-OpenAI group:

{
  "error": {
    "type": "not_found_error",
    "message": "Images API is not supported for this platform"
  }
}

Using a non-image model:

{
  "error": {
    "type": "invalid_request_error",
    "message": "images endpoint requires an image model"
  }
}

Boundaries

• This endpoint is only for OpenAI Images API compatible requests.
• Gemini native image requests should use /v1beta/models/{model}:generateContent.
• Use async image tasks for long-running or production bulk jobs.