GPT Image Models | OpenModels Documentation

GPT image models use the image generation endpoint.

curl https://api.getopenmodels.com/v1/images \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OM_API_KEY" \
  -d '{
    "model": "gpt-image-2",
    "route": { "provider": "<provider-for-this-model>" },
    "route_mode": "balanced",
    "prompt": "An elegant commercial product photograph: a transparent modern glass tumbler filled with ice cubes and lemon slices, with a bold, clearly printed label reading \"PURE FRESH\" on the glass. The background is a clean light-blue gradient with professional studio lighting.",
    "n": 1,
    "size": "1024x1024",
    "quality": "low"
  }'

For GPT image models, set image generation options as top-level fields in the request body. The route and route_mode fields in the example are OpenModels routing options; remove them to use the default available route.

Field	Type	Notes
`prompt`	string	Required text description of the desired image.
`n`	integer	Number of images to generate. Valid range: `1`-`10`.
`size`	string	Output image size. Common values: `auto`, `1024x1024`, `1536x1024`, `1024x1536`. `gpt-image-2` also accepts custom `WIDTHxHEIGHT` values when both edges are multiples of `16`, the aspect ratio is between `1:3` and `3:1`, and the image stays within current pixel and edge limits.
`quality`	string	Rendering quality. Valid values: `auto`, `low`, `medium`, `high`. Use `low` for fast drafts and `medium` or `high` for final assets.
`output_format`	string	Image format. Valid values: `png`, `jpeg`, `webp`. Default: `png`.
`output_compression`	integer	Compression level from `0` to `100`. Only applies when `output_format` is `jpeg` or `webp`.
`background`	string	Background handling. Use `auto` or `opaque`; `gpt-image-2` does not support transparent backgrounds.
`moderation`	string	Content moderation strictness. Valid values: `auto`, `low`. Default: `auto`.