Create image

POST

/images/generations

Creates an image from a text prompt using supported GPT Image models. Only non-stream requests
are currently supported: omit stream or set it to false. Results are not converted into
Chat Completions choices.

Request

Header Params

Body Params application/jsonRequired

Example

{
    "model": "openai/gpt-image-2",
    "prompt": "A small red cube on a white background.",
    "size": "1024x1024",
    "quality": "medium"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/images/generations' \
--header 'x-opengateway-user-id;' \
--header 'x-opengateway-session-id;' \
--header 'x-sionic-task-id;' \
--header 'Content-Type: application/json' \
--data '{
    "model": "openai/gpt-image-2",
    "prompt": "A small red cube on a white background.",
    "size": "1024x1024",
    "quality": "medium"
}'

Responses

🟢200OK

application/json

OpenAI-compatible image generation response.

Bodyapplication/json

Example

{
    "created": 1734567890,
    "data": [
        {
            "b64_json": "iVBORw0KGgo..."
        }
    ],
    "quality": "medium",
    "size": "1024x1024",
    "usage": {
        "input_tokens": 20,
        "output_tokens": 1056,
        "total_tokens": 1076,
        "input_tokens_details": {
            "text_tokens": 20
        },
        "output_tokens_details": {
            "image_tokens": 1056
        }
    }
}

🟠400Bad Request

🟠401Unauthorized

🟠402

🟠429

🔴500Server Error

🔴503Service Unavailable

Modified at 2026-10-27 15:03:30

Create embeddings

Edit image